#251 by GitHub stars
Galaxy-Dawn/claude-scholar
Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/agent-identifier/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/architecture-design/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/bug-detective/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/citation-verification/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/code-review-excellence/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/command-development/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/daily-coding/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/daily-paper-generator/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/defuddle/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/doc-coauthoring/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/expression-skill/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/frontend-design/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/git-workflow/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/hook-development/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/kaggle-learner/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/latex-conference-template-organizer/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/mcp-integration/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/ml-paper-writing/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/nature-data/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/nature-polishing/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/nature-response/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/nature-writing/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/obsidian-kb-artifacts/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/obsidian-literature-workflow/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/obsidian-project-kb-core/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/obsidian-source-ingestion/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/paper-self-review/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/planning-with-files/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/plugin-structure/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/post-acceptance/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/publication-chart-skill/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/research-ideation/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/results-analysis/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/results-report/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/review-response/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/skill-development/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/skill-improver/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/skill-quality-reviewer/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/ui-ux-pro-max/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
skills/uv-package-manager/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/verification-loop/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/web-design-reviewer/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/webapp-testing/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d394fb599ed9 → d394fb599ed9
skills/writing-anti-ai/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d394fb599ed9 → d394fb599ed9
skills/zotero-obsidian-bridge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d394fb599ed9 → d394fb599ed9
View on GitHubAdd to my skills
Verified commit d394fb599ed9e6ea2212a9e6daa864345fe97a26
git clone --filter=blob:none --no-checkout https://github.com/Galaxy-Dawn/claude-scholar.git .hotskills/galaxy-dawn-claude-scholar && git -C .hotskills/galaxy-dawn-claude-scholar checkout --detach d394fb599ed9e6ea2212a9e6daa864345fe97a26
# Copy each selected skill directory from .hotskills/galaxy-dawn-claude-scholar into .claude/skills/<skill-name>/6kGitHub stars
56stars in 7 days
45skills in this repository
8commits in 30 days
Heat
6.4- Star growth, last 7 daysAhead of 83% of tracked repositories
- Star growth, last 24 hoursAhead of 73% of tracked repositories
- Rank movement, last 7 daysAhead of 54% of tracked repositories
- Commits, last 30 daysAhead of 74% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- agent-identifier
skills/agent-identifier - architecture-design
skills/architecture-design - bug-detective
skills/bug-detective - citation-verification
skills/citation-verification - code-review-excellence
skills/code-review-excellence - command-development
skills/command-development - daily-coding
skills/daily-coding - daily-paper-generator
skills/daily-paper-generator - defuddle
skills/defuddle - doc-coauthoring
skills/doc-coauthoring - expression-skill
skills/expression-skill - frontend-design
skills/frontend-design - git-workflow
skills/git-workflow - hook-development
skills/hook-development - kaggle-learner
skills/kaggle-learner - latex-conference-template-organizer
skills/latex-conference-template-organizer - mcp-integration
skills/mcp-integration - ml-paper-writing
skills/ml-paper-writing - nature-data
skills/nature-data - nature-polishing
skills/nature-polishing - nature-response
skills/nature-response - nature-writing
skills/nature-writing - obsidian-kb-artifacts
skills/obsidian-kb-artifacts - obsidian-literature-workflow
skills/obsidian-literature-workflow - obsidian-project-kb-core
skills/obsidian-project-kb-core - obsidian-source-ingestion
skills/obsidian-source-ingestion - paper-self-review
skills/paper-self-review - planning-with-files
skills/planning-with-files - plugin-structure
skills/plugin-structure - post-acceptance
skills/post-acceptance - publication-chart-skill
skills/publication-chart-skill - research-ideation
skills/research-ideation - results-analysis
skills/results-analysis - results-report
skills/results-report - review-response
skills/review-response - skill-development
skills/skill-development - skill-improver
skills/skill-improver - skill-quality-reviewer
skills/skill-quality-reviewer - ui-ux-pro-max
skills/ui-ux-pro-max - uv-package-manager
skills/uv-package-manager - verification-loop
skills/verification-loop - web-design-reviewer
skills/web-design-reviewer - webapp-testing
skills/webapp-testing - writing-anti-ai
skills/writing-anti-ai - zotero-obsidian-bridge
skills/zotero-obsidian-bridge
How it works
agent-identifier
When your agent uses it
Use when creating or configuring Claude Code agents and their frontmatter.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
2,529 tokensWhen the skill is activated
Reference documents
11,821 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- When Not to Use
- Agent File Structure
- Frontmatter Fields
- System Prompt Design
- Creating Agents
- Validation Rules
- Agent Organization
- Testing Agents
- Quick Reference
- Additional Resources
- Implementation Workflow
Scripts executed separately
scripts/validate-agent.sh
Files
../../.claude-plugin/marketplace.jsonasset532 bytes../../.claude-plugin/plugin.jsonasset615 bytes../../hooks/hooks.jsonasset1,414 bytes../../hooks/hooks.jsonasset1,414 bytes../../hooks/hooks.jsonasset1,414 bytes../../hooks/hooks.jsonasset1,414 bytes../../hooks/hooks.jsonasset1,414 bytes../../hooks/hooks.jsonasset1,414 bytesSKILL.mdcore10,630 bytesexamples/agent-creation-prompt.mddoc9,390 bytesexamples/complete-agent-examples.mddoc14,117 bytesreferences/agent-creation-system-prompt.mddoc8,879 bytesreferences/system-prompt-design.mddoc9,998 bytesreferences/triggering-examples.mddoc11,613 bytesscripts/validate-agent.shruns5,796 bytes
Read SKILL.md
# Agent Development for Claude Code Plugins
## Overview
Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.
**Key concepts:**
- Agents are FOR autonomous work, commands are FOR user-initiated actions
- Markdown file format with YAML frontmatter
- Triggering via description field with examples
- System prompt defines agent behavior
- Model and color customization
## When to Usearchitecture-design
When your agent uses it
Use only when creating new registrable ML components that require Factory or Registry patterns.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
1,996 tokensWhen the skill is activated
Reference documents
3,991 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- When Not to Use
- Core Design Patterns
- Directory Structure
- Module Organization
- Code Style Guidelines
- Configuration Management
- When Working on This Project
- Additional Resources
Scripts executed separately
examples/augmentation_example.pyexamples/custom_dataset.pyexamples/custom_model.pyexamples/pipeline_example.sh
Files
SKILL.mdcore9,177 bytesSKILL.mdcore9,177 bytesSKILL.mdcore9,177 bytesSKILL.mdcore9,177 bytesSKILL.mdcore9,177 bytesSKILL.mdcore9,177 bytesexamples/augmentation_example.pyruns3,167 bytesexamples/config_example.yamlasset2,391 bytesexamples/custom_dataset.pyruns1,508 bytesexamples/custom_model.pyruns6,269 bytesexamples/pipeline_example.shruns5,140 bytesreferences/auto_import.mddoc3,437 bytesreferences/code_style.mddoc5,357 bytesreferences/factory_pattern.mddoc1,481 bytesreferences/registry_pattern.mddoc2,576 bytesreferences/structure.mddoc4,926 bytes
Read SKILL.md
# Architecture Design - ML Project Template
This skill defines the standard code architecture for machine learning projects based on the template structure. When modifying or extending code, follow these patterns to maintain consistency.
## Overview
The project follows a modular, extensible architecture with clear separation of concerns. Each module (data, model, trainer, analysis) is independently organized using factory and registry patterns for maximum flexibility.
## When to Use
Use this skill when:
- Creating a new Dataset class that needs `@register_dataset`
- Creating a new Model class that needs `@register_model`
- Creating a new module directory with `__init__.py` factory wiringbug-detective
When your agent uses it
This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
2,114 tokensWhen the skill is activated
Reference documents
4,840 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Philosophy
- Debugging Workflow
- Python Common Error Patterns
- JavaScript/TypeScript Common Error Patterns
- Bash/Zsh Common Error Patterns
- Common Debugging Commands
- Preventive Debugging
- Debugging Checklist
- Additional Resources
Scripts executed separately
examples/debugging-workflow.pyexamples/debugging-workflow.shexamples/error-handling-patterns.py
Files
SKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesSKILL.mdcore8,550 bytesexamples/debugging-workflow.pyruns6,308 bytesexamples/debugging-workflow.shruns8,851 bytesexamples/error-handling-patterns.pyruns8,701 bytesreferences/common-patterns.mddoc5,641 bytesreferences/debugging-tools.mddoc405 bytesreferences/javascript-errors.mddoc490 bytesreferences/python-errors.mddoc5,617 bytesreferences/shell-errors.mddoc3,607 bytes
Read SKILL.md
# Bug Detective
A systematic debugging workflow for investigating and resolving code errors, exceptions, and failures. Provides structured debugging methods and common error pattern recognition.
## Core Philosophy
Debugging is a scientific problem-solving process that requires:
1. **Understand the problem** - Clearly define symptoms and expected behavior
2. **Gather evidence** - Collect error messages, logs, stack traces
3. **Form hypotheses** - Infer possible causes based on evidence
4. **Verify hypotheses** - Confirm or eliminate causes through experiments
5. **Resolve the issue** - Apply fixes and verify
## Debugging Workflowcitation-verification
When your agent uses it
This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providing detailed verification principles and common error patterns.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,679 tokensWhen the skill is activated
Reference documents
8,955 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Problems
- Verification Principles
- Verification Workflow
- Usage Guide
- Best Practices
- Summary
Scripts executed separately
scripts/api-clients.pyscripts/format-checker.pyscripts/verify-citations.py
Files
SKILL.mdcore7,593 bytesSKILL.mdcore7,593 bytesreferences/README.mddoc2,454 bytesreferences/api-usage.mddoc8,259 bytesreferences/common-errors.mddoc8,561 bytesreferences/verification-rules.mddoc10,079 bytesscripts/README.mddoc2,264 bytesscripts/api-clients.pyruns16,723 bytesscripts/format-checker.pyruns18,560 bytesscripts/verify-citations.pyruns21,742 bytes
Read SKILL.md
# Citation Verification Reference Guide
A reference guide for citation verification in academic paper writing, providing verification principles and best practices.
**Core Principle**: Proactively verify every citation during the writing process using programmatic or canonical scholarly sources first: arXiv, DOI/CrossRef, Semantic Scholar, publisher landing pages, and Zotero metadata. Google Scholar is useful for manual discovery, but it is not the canonical verification authority.
## Core Problems
Citation issues in academic papers seriously impact research integrity:
1. **Fake citations** - Citing non-existent papers (common issue with AI-generated citations)
2. **Incorrect information** - Mismatched authors, titles, years, etc.
3. **Inconsistent formatting** - Mixed citation formats
4. **Missing citations** - Referenced but uncited workcode-review-excellence
When your agent uses it
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
3,200 tokensWhen the skill is activated
Reference documents
294 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Core Principles
- Review Process
- Review Techniques
- Language-Specific Patterns
- Advanced Review Patterns
- Giving Difficult Feedback
- Best Practices
- Common Pitfalls
- Templates
- Resources
Scripts executed separately
scripts/pr-analyzer.py
Files
SKILL.mdcore13,677 bytesSKILL.mdcore13,677 bytesassets/pr-review-template.mddoc99 bytesassets/review-checklist.mddoc120 bytesreferences/code-review-best-practices.mddoc590 bytesreferences/common-bugs-checklist.mddoc256 bytesreferences/security-review-guide.mddoc305 bytesscripts/pr-analyzer.pyruns1,367 bytes
Read SKILL.md
# Code Review Excellence
Transform code reviews from gatekeeping to knowledge sharing through constructive feedback, systematic analysis, and collaborative improvement.
## When to Use This Skill
- Reviewing pull requests and code changes
- Establishing code review standards for teams
- Mentoring junior developers through reviews
- Conducting architecture reviews
- Creating review checklists and guidelines
- Improving team collaboration
- Reducing code review cycle time
- Maintaining code quality standardscommand-development
When your agent uses it
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
4,296 tokensWhen the skill is activated
Reference documents
32,260 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Command Basics
- File Format
- YAML Frontmatter Fields
- Dynamic Arguments
- File References
- Bash Execution in Commands
- Command Organization
- Best Practices
- Common Patterns
- Troubleshooting
- Plugin-Specific Features
- Integration with Plugin Components
- Validation Patterns
Files
README.mddoc7,651 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesSKILL.mdcore18,981 bytesexamples/plugin-commands.mddoc13,989 bytesexamples/simple-commands.mddoc8,675 bytesreferences/advanced-workflows.mddoc13,618 bytesreferences/documentation-patterns.mddoc14,971 bytesreferences/frontmatter-reference.mddoc9,162 bytesreferences/interactive-commands.mddoc20,980 bytesreferences/marketplace-considerations.mddoc16,437 bytesreferences/plugin-features-reference.mddoc14,622 bytesreferences/testing-strategies.mddoc14,803 bytes
Read SKILL.md
# Command Development for Claude Code
## Overview
Slash commands are frequently-used prompts defined as Markdown files that Claude executes during interactive sessions. Understanding command structure, frontmatter options, and dynamic features enables creating powerful, reusable workflows.
**Key concepts:**
- Markdown file format for commands
- YAML frontmatter for configuration
- Dynamic arguments and file references
- Bash execution for context
- Command organization and namespacing
## Command Basicsdaily-coding
When your agent uses it
Use for everyday coding tasks that involve writing or modifying source code.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
479 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- When Not to Use
- Core Checklist
- Quick Reference
Files
SKILL.mdcore2,123 bytesSKILL.mdcore2,123 bytesSKILL.mdcore2,123 bytesSKILL.mdcore2,123 bytes
Read SKILL.md
# Daily Coding Checklist
A minimal coding quality assurance checklist ensuring every code modification follows best practices.
## When to Use
Use this skill for:
- Implementing new features
- Adding code or modifying existing code
- User requests like "write a...", "implement...", "add...", or "modify..."
- Any coding task that involves Edit or Write tools
## When Not to Use
daily-paper-generator
When your agent uses it
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
1,037 tokensWhen the skill is activated
Reference documents
4,767 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Output Format
- Quick Reference
- Workflow
- Additional Resources
- Important Notes
Scripts executed separately
scripts/arxiv_search.py
Files
SKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesSKILL.mdcore4,137 bytesexample/daily paper example.mddoc6,245 bytesreferences/keywords.mddoc1,757 bytesreferences/quality-criteria.mddoc4,543 bytesreferences/writing-style.mddoc4,681 bytesscripts/arxiv_search.pyruns9,827 bytes
Read SKILL.md
# Daily Paper Generator
## Overview
Discover, screen, and summarize recent papers for any research topic.
Supported sources:
- arXiv
- bioRxiv
- both (`--source both`)
Core workflow:
1. Define topic query and time window
2. Search papers from arXiv / bioRxivdefuddle
When your agent uses it
Extract clean Markdown from web pages. In the KB workflow, use it as a utility under obsidian-source-ingestion.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
81 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore330 bytesSKILL.mdcore330 bytes
Read SKILL.md
# Defuddle
Use Defuddle as a utility for `obsidian-source-ingestion`.
Typical KB target for web content:
- `Sources/Web/`
Typical command:
```bash
defuddle parse <url> --md
```doc-coauthoring
When your agent uses it
This skill should be used when the user asks to co-author documentation, draft a proposal, write a technical spec, create a decision doc or RFC, or structure a substantial document through iterative collaboration and reader testing.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
3,386 tokensWhen the skill is activated
Reference documents
327 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Runtime contract
- When to Offer This Workflow
- Stage 1: Context Gathering
- Stage 2: Refinement & Structure
- Stage 3: Reader Testing
- Final Review
- Tips for Effective Guidance
- Reference Files
Files
SKILL.mdcore16,350 bytesreferences/DOC-TYPES.mddoc435 bytesreferences/READER-TEST.mddoc438 bytesreferences/RUNTIME-MATRIX.mddoc686 bytes
Read SKILL.md
# Doc Co-Authoring Workflow
This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.
## Runtime contract
Use `references/RUNTIME-MATRIX.md` to decide what is available in the current environment before offering connectors, artifacts, or reader-test subagents.
If no artifact-like surface is available, default to a normal markdown file in a user-specified path or an explicitly named working file. Do not assume artifacts are available.
## When to Offer This Workflow
**Trigger conditions:**
- User mentions writing documentation: "write a doc", "draft a proposal", "create a spec", "write up"expression-skill
When your agent uses it
This skill should be used when the user asks for efficient communication, task reports, file-operation summaries, research discussion, study-note synthesis, planning, writing feedback, or responses that need conclusion-first structure, concrete evidence, risk disclosure, and useful next steps.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
2,114 tokensWhen the skill is activated
Reference documents
4,600 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Goal
- Default Workflow
- Clarification And Question Policy
- Communication Defaults
- Core Rules
- Scenario Rules
- Critique And Rebuttal
- Common Output Shapes
- Load When Needed
- Boundaries
- Final answer checklist
Files
README.mddoc4,624 bytesREADME.zh-CN.mddoc4,701 bytesSKILL.mdcore9,789 bytesSKILL.mdcore9,789 bytesSKILL.mdcore9,789 bytesexamples/code-task.mddoc519 bytesexamples/file-operation.mddoc364 bytesexamples/long-running-job.mddoc465 bytesexamples/research-discussion.mddoc723 bytesexamples/writing-revision.mddoc778 bytesreferences/communication-sop.mddoc5,877 bytesreferences/user-preferences.mddoc1,752 bytes
Read SKILL.md
# Expression Skill
Use this skill to communicate with high signal, low noise, and visible judgment. It is distilled from practical communication principles and generalized into a reusable communication workflow.
## Goal
Put the user's current problem at the center. Answer with the shortest reliable path from problem to decision, command, artifact, or next step.
Default priorities:
1. conclusion
2. evidence or reason
3. risk, uncertainty, or boundary
4. concrete actionfrontend-design
When your agent uses it
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
866 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Design Thinking
- Frontend Aesthetics Guidelines
Files
LICENSE.txtdoc10,174 bytesSKILL.mdcore4,455 bytes
Read SKILL.md
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.
The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints.
## Design Thinking
Before coding, understand the context and commit to a BOLD aesthetic direction:
- **Purpose**: What problem does this interface solve? Who uses it?
- **Tone**: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction.
- **Constraints**: Technical requirements (framework, performance, accessibility).
- **Differentiation**: What makes this UNFORGETTABLE? What's the one thing someone will remember?
**CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.
git-workflow
When your agent uses it
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team collaboration.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
2,851 tokensWhen the skill is activated
Reference documents
7,689 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Commit Message Standards
- Branch Management Strategy
- Workflows
- Merge Strategy
- Conflict Resolution
- .gitignore Standards
- Tag Management
- Team Collaboration Standards
- Common Issues
- Best Practices Summary
- Additional Resources
- Summary
Scripts executed separately
examples/workflow-commands.sh
Files
SKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesSKILL.mdcore11,972 bytesexamples/commit-messages.txtdoc1,041 bytesexamples/workflow-commands.shruns2,961 bytesreferences/advanced-usage.mddoc7,766 bytesreferences/branching-strategies.mddoc4,074 bytesreferences/collaboration.mddoc2,256 bytesreferences/commit-conventions.mddoc3,340 bytesreferences/conflict-resolution.mddoc2,679 bytesreferences/gitignore-guide.mddoc4,305 bytesreferences/merge-strategies.mddoc3,110 bytes
Read SKILL.md
# Git Workflow Standards
This document defines the project's Git usage standards, including commit message format, branch management strategy, workflows, merge strategies, and more. Following these standards improves collaboration efficiency, enables traceability, supports automation, and reduces conflicts.
## Commit Message Standards
The project follows the **Conventional Commits** specification:
```
<type>(<scope>): <subject>
<body>
<footer>hook-development
When your agent uses it
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
3,985 tokensWhen the skill is activated
Reference documents
7,651 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Hook Types
- Hook Configuration Formats
- Hook Events
- Hook Output Format
- Hook Input Format
- Environment Variables
- Plugin Hook Configuration
- Matchers
- Security Best Practices
- Performance Considerations
- Temporarily Active Hooks
- Hook Lifecycle and Limitations
- Debugging Hooks
- Quick Reference
- Additional Resources
- Implementation Workflow
Scripts executed separately
../../hooks/hooks.json../../hooks/hooks.json../../hooks/hooks.json../../hooks/hooks.json../../hooks/hooks.json../../hooks/hooks.jsonexamples/load-context.shexamples/validate-bash.shexamples/validate-write.shscripts/hook-linter.shscripts/test-hook.shscripts/validate-hook-schema.sh
Files
../../hooks/hooks.jsonruns1,414 bytes../../hooks/hooks.jsonruns1,414 bytes../../hooks/hooks.jsonruns1,414 bytes../../hooks/hooks.jsonruns1,414 bytes../../hooks/hooks.jsonruns1,414 bytes../../hooks/hooks.jsonruns1,414 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesSKILL.mdcore16,246 bytesexamples/load-context.shruns1,690 bytesexamples/validate-bash.shruns1,304 bytesexamples/validate-write.shruns1,222 bytesreferences/advanced.mddoc10,148 bytesreferences/migration.mddoc8,299 bytesreferences/patterns.mddoc7,144 bytesscripts/README.mddoc3,677 bytesscripts/hook-linter.shruns4,200 bytesscripts/test-hook.shruns5,336 bytesscripts/validate-hook-schema.shruns5,081 bytes
Read SKILL.md
# Hook Development for Claude Code Plugins
## Overview
Hooks are event-driven automation scripts that execute in response to Claude Code events. Use hooks to validate operations, enforce policies, add context, and integrate external tools into workflows.
**Key capabilities:**
- Validate tool calls before execution (PreToolUse)
- React to tool results (PostToolUse)
- Enforce completion standards (Stop, SubagentStop)
- Load project context (SessionStart)
- Automate workflows across the development lifecycle
## Hook Typeskaggle-learner
When your agent uses it
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,118 tokensWhen the skill is activated
Reference documents
324,563 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Knowledge Categories
- Quick Reference
- Self-Evolving
- Knowledge Extraction Standard
- Additional Resources
Files
SKILL.mdcore4,537 bytesreferences/knowledge/.archive/cv.mddoc248 bytesreferences/knowledge/.archive/multimodal.mddoc256 bytesreferences/knowledge/.archive/nlp.mddoc113,409 bytesreferences/knowledge/.archive/tabular.mddoc24,748 bytesreferences/knowledge/.archive/time-series.mddoc342,505 bytesreferences/knowledge/nlp/aimo-2-2025.mddoc38,830 bytesreferences/knowledge/nlp/arc-prize-2025.mddoc52,735 bytesreferences/knowledge/nlp/eedi-2024.mddoc7,812 bytesreferences/knowledge/nlp/konwinski-prize-2025-6th-place-study.mddoc10,104 bytesreferences/knowledge/nlp/konwinski-prize-2025-comparison.mddoc36,027 bytesreferences/knowledge/nlp/konwinski-prize-2025.mddoc20,740 bytesreferences/knowledge/nlp/map-2024.mddoc14,261 bytesreferences/knowledge/tabular/amp-parkinsons-2021.mddoc16,978 bytesreferences/knowledge/time-series/birdclef-2023.mddoc52,419 bytesreferences/knowledge/time-series/birdclef-2024.mddoc160,078 bytesreferences/knowledge/time-series/birdclef-plus-2025.mddoc68,730 bytesreferences/knowledge/time-series/detect-behavior-sensor-2025.mddoc60,346 bytesreferences/knowledge/time-series/detect-sleep-states-2023.mddoc57,362 bytesreferences/knowledge/time-series/hms-2024.mddoc58,913 bytes
Read SKILL.md
# Kaggle Learner
Extract and apply knowledge from Kaggle competition winning solutions. This skill provides access to a continuously updated knowledge base of techniques, code patterns, and best practices from top Kaggle competitors.
## Overview
Kaggle competitions are at the forefront of practical machine learning. Winning solutions often innovate with novel techniques, clever feature engineering, and optimized pipelines. This skill captures that knowledge and makes it accessible for your projects.
## When to Use
Use this skill when:
- Studying for a Kaggle competition
- Looking for proven techniques in a specific domain (NLP, CV, etc.)
- Need code templates for common ML taskslatex-conference-template-organizer
When your agent uses it
Organize messy conference LaTeX template .zip files into clean Overleaf-ready structure. Use when the user asks to "organize LaTeX template", "clean up .zip template", or "prepare Overleaf submission template".
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
3,535 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Working Mode
- Complete Workflow
- Step 1: Extract and Analyze
- Step 2: Diagnose Issues
- Step 3: Ask for Conference Information
- Step 4: Present Cleanup Plan
- Step 5: Execute Cleanup
- Step 6: Generate README
- Notes
- Error Handling
- Common Conference Template Types
- Quick Reference
Files
SKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytes
Read SKILL.md
# LaTeX Conference Template Organizer
## Overview
Transform messy conference LaTeX template .zip files into clean, Overleaf-ready submission templates. Official conference templates often contain excessive example content, instructional comments, and disorganized file structures. This skill converts them into templates ready for writing.
## Working Mode
**Analyze-then-confirm mode**: First analyze issues and present them to the user, then execute cleanup after confirmation.
## Complete Workflow
```
Receive .zip filemcp-integration
When your agent uses it
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
3,034 tokensWhen the skill is activated
Reference documents
8,181 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- MCP Server Configuration Methods
- MCP Server Types
- Environment Variable Expansion
- MCP Tool Naming
- Lifecycle Management
- Authentication Patterns
- Integration Patterns
- Security Best Practices
- Error Handling
- Performance Considerations
- Testing MCP Integration
- Debugging
- Quick Reference
- Additional Resources
- Implementation Workflow
Files
SKILL.mdcore12,519 bytesSKILL.mdcore12,519 bytesexamples/http-server.jsonasset502 bytesexamples/sse-server.jsonasset413 bytesexamples/stdio-server.jsonasset686 bytesreferences/authentication.mddoc10,196 bytesreferences/server-types.mddoc10,613 bytesreferences/tool-usage.mddoc11,674 bytes
Read SKILL.md
# MCP Integration for Claude Code Plugins
## Overview
Model Context Protocol (MCP) enables Claude Code plugins to integrate with external services and APIs by providing structured tool access. Use MCP integration to expose external service capabilities as tools within Claude Code.
**Key capabilities:**
- Connect to external services (databases, APIs, file systems)
- Provide 10+ related tools from a single service
- Handle OAuth and complex authentication flows
- Bundle MCP servers with plugins for automatic setup
## MCP Server Configuration Methods
ml-paper-writing
When your agent uses it
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper discovery/evaluation criteria.
What it loads into context
Frontmatter
147 tokensAlways available to the agent
SKILL.md
10,352 tokensWhen the skill is activated
Reference documents
58,399 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Default operating order
- Claim ledger gate
- Core Philosophy: Collaborative Writing
- ⚠<U+FE0F> CRITICAL: Never Hallucinate Citations
- Workflow 0: Starting from a Research Repository
- When to Use This Skill
- Workflow: Literature Research & Paper Discovery
- Knowledge Base: Paper-Miner Installed Writing Memory
- Balancing Proactivity and Collaboration
- The Narrative Principle
- Paper Structure Workflow
- Writing Philosophy for Top ML Conferences
- Conference Requirements Quick Reference
- Using LaTeX Templates Properly
- Conference Resubmission & Format Conversion
- Citation Workflow (Hallucination Prevention)
- Common Issues and Solutions
- Reviewer Evaluation Criteria
- Tables and Figures
- References & Resources
Scripts executed separately
templates/neurips2025/Makefile
Files
SKILL.mdcore44,243 bytesSKILL.mdcore44,243 bytesSKILL.mdcore44,243 bytesSKILL.mdcore44,243 bytesSKILL.mdcore44,243 bytesSKILL.mdcore44,243 bytesSKILL.mdcore44,243 bytesSKILL.mdcore44,243 bytesSKILL.mdcore44,243 bytesreferences/OPERATING-MODES.mddoc921 bytesreferences/checklists.mddoc10,774 bytesreferences/citation-workflow.mddoc15,167 bytesreferences/knowledge/README.mddoc1,984 bytesreferences/knowledge/design-simplification-papers-kaiming-he.mddoc21,234 bytesreferences/knowledge/kaiming_he_injection_record.jsonasset6,154 bytesreferences/knowledge/paper-miner-writing-memory.mddoc1,133 bytesreferences/knowledge/rethinking-papers-kaiming-he.mddoc33,598 bytesreferences/knowledge/review-response.mddoc11,873 bytesreferences/knowledge/structure.mddoc10,010 bytesreferences/knowledge/submission-guides.mddoc8,905 bytesreferences/knowledge/theory-driven-papers-kaiming-he.mddoc19,067 bytesreferences/knowledge/writing-techniques.mddoc19,367 bytesreferences/literature-research/arxiv-search-guide.mddoc5,644 bytesreferences/literature-research/paper-quality-criteria.mddoc7,127 bytesreferences/reviewer-guidelines.mddoc10,451 bytesreferences/sources.mddoc7,310 bytesreferences/writing-guide.mddoc16,297 bytestemplates/README.mddoc6,707 bytestemplates/aaai2026/README.mddoc17,987 bytestemplates/aaai2026/aaai2026-unified-supp.texasset4,548 bytestemplates/aaai2026/aaai2026-unified-template.texasset63,140 bytestemplates/aaai2026/aaai2026.bibasset4,766 bytestemplates/aaai2026/aaai2026.bstasset30,207 bytestemplates/aaai2026/aaai2026.styasset11,802 bytestemplates/acl/README.mddoc2,126 bytestemplates/acl/acl.styasset11,615 bytestemplates/acl/acl_latex.texasset14,533 bytestemplates/acl/acl_lualatex.texasset3,050 bytestemplates/acl/acl_natbib.bstasset45,186 bytestemplates/acl/anthology.bib.txtdoc1,169 bytestemplates/acl/custom.bibasset2,071 bytestemplates/acl/formatting.mddoc17,923 bytestemplates/colm2025/README.mddoc51 bytestemplates/colm2025/colm2025_conference.bibasset496 bytestemplates/colm2025/colm2025_conference.bstasset26,973 bytestemplates/colm2025/colm2025_conference.pdfasset122,635 bytestemplates/colm2025/colm2025_conference.styasset7,727 bytestemplates/colm2025/colm2025_conference.texasset12,830 bytestemplates/colm2025/fancyhdr.styasset20,521 bytestemplates/colm2025/math_commands.texasset12,284 bytestemplates/colm2025/natbib.styasset45,154 bytestemplates/iclr2026/fancyhdr.styasset20,521 bytestemplates/iclr2026/iclr2026_conference.bibasset629 bytestemplates/iclr2026/iclr2026_conference.bstasset26,973 bytestemplates/iclr2026/iclr2026_conference.pdfasset200,508 bytestemplates/iclr2026/iclr2026_conference.styasset9,025 bytestemplates/iclr2026/iclr2026_conference.texasset16,899 bytestemplates/iclr2026/math_commands.texasset12,284 bytestemplates/iclr2026/natbib.styasset45,154 bytestemplates/icml2026/algorithm.styasset2,223 bytestemplates/icml2026/algorithmic.styasset7,414 bytestemplates/icml2026/example_paper.bibasset2,051 bytestemplates/icml2026/example_paper.pdfasset193,509 bytestemplates/icml2026/example_paper.texasset29,714 bytestemplates/icml2026/fancyhdr.styasset31,715 bytestemplates/icml2026/icml2026.bstasset27,147 bytestemplates/icml2026/icml2026.styasset27,344 bytestemplates/icml2026/icml_numpapers.pdfasset2,823 bytestemplates/neurips2025/Makefileruns1,054 bytestemplates/neurips2025/extra_pkgs.texasset2,837 bytestemplates/neurips2025/main.texasset574 bytestemplates/neurips2025/neurips.styasset11,625 bytes
Read SKILL.md
# ML Paper Writing for Top AI Conferences
Expert-level guidance for writing publication-ready papers targeting **NeurIPS, ICML, ICLR, ACL, AAAI, and COLM**. This skill combines writing philosophy from top researchers (Nanda, Farquhar, Karpathy, Lipton, Steinhardt) with practical tools: LaTeX templates, citation verification APIs, and conference checklists.
## Default operating order
Use this skill in the following order unless the task is unusually narrow:
1. lock the operating mode from `references/OPERATING-MODES.md`,
2. understand the repo or draft context,
3. use `references/citation-workflow.md` as the **canonical citation authority**,
4. load venue- or template-specific references only after the main writing path is clear.
Google Scholar may still help with manual discovery, but it is **not** the canonical verification authority in this skill. Default verification should use programmatic sources such as Semantic Scholar, CrossRef, and arXiv.
nature-data
When your agent uses it
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data, supplementary datasets, DataCite-style dataset references, FAIR metadata for academic publication, or Chinese-to-English data availability wording for Chinese-speaking authors preparing Nature-family submissions.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
1,347 tokensWhen the skill is activated
Reference documents
6,768 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Chinese-user operating mode
- Default stance
- Workflow
- Output format
- Related files
- Source hierarchy
Files
README.mddoc2,667 bytesSKILL.mdcore6,726 bytesSKILL.mdcore6,726 bytesSKILL.mdcore6,726 bytesSKILL.mdcore6,726 bytesSKILL.mdcore6,726 bytesagents/openai.yamlasset270 bytesreferences/chinese-author-alignment.mddoc5,010 bytesreferences/fair-metadata-checklist.mddoc4,076 bytesreferences/policy-principles.mddoc5,305 bytesreferences/repository-and-identifiers.mddoc4,390 bytesreferences/source-basis.mddoc5,391 bytesreferences/statement-patterns.mddoc7,193 bytes
Read SKILL.md
# Nature Data Availability Skill
Use this skill to turn a manuscript's supporting data into a transparent, Nature-ready data
availability package: statement text, repository plan, dataset citations, and missing-information
flags.
The governing policy layer is Springer Nature / Nature Portfolio data policy. The implementation
layer is FAIR data practice and DataCite-style citation metadata.
For academic wording only, the active installed
`skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md`
under the current client's skill home may offer relevant phrasing examples.
Use it only when it contains source-attributed availability language. Journal
policy and the author's actual data-access facts take precedence. If the memorynature-polishing
When your agent uses it
Polish, restructure, or translate academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from Academic Phrasebank. Use whenever the user asks to polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section, or Chinese academic draft for publication-quality English.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,946 tokensWhen the skill is activated
Reference documents
5,003 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Default stance
- Mined writing memory
- When to open extra files
- Core architecture
- Section responsibilities
- Sentence and paragraph control
- Citation, ethics, and AI boundaries
- Output format
Files
README.mddoc2,868 bytesSKILL.mdcore14,337 bytesSKILL.mdcore14,337 bytesSKILL.mdcore14,337 bytesSKILL.mdcore14,337 bytesSKILL.mdcore14,337 bytesSKILL.mdcore14,337 bytesreferences/phrasebank-playbook.mddoc3,671 bytesreferences/published-article-patterns.mddoc4,320 bytesreferences/section-moves.mddoc5,769 bytesreferences/style-guardrails.mddoc2,669 bytesreferences/writing-strategy.mddoc4,425 bytes
Read SKILL.md
# Nature-Style Academic Polishing
Use this skill to improve scientific writing at two levels:
- `main strategy`: paper architecture, published-article patterns, section logic, reader workflow, evidence thresholds, and ethics
- `reference support`: reusable phrase families, move patterns, transitions, and style checks
The main strategy should come from the course notes in `Chapter1-Week1-7` and
the curated article-pattern reference. The wording layer should come from
`Academic Phrasebank`.
## Default stance
- Language serves argument. Do not polish sentences while leaving the reasoning broken.nature-response
When your agent uses it
Draft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions. Use when the user provides reviewer comments, editor decision letters, revision notes, response drafts, or asks how to respond to major/minor revision requests, rebuttal letters, response to reviewers, peer-review reports, 审稿意见回复, 逐点回复, 修回信, 大修回复, 小修回复, or 如何回复 reviewer.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
1,425 tokensWhen the skill is activated
Reference documents
11,493 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Default stance
- Mined writing memory
- Accepted inputs
- Workflow
- Output format
- Red lines
- Related files
- Source hierarchy
Files
README.mddoc4,219 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesexamples/conflicting-reviewers.mddoc1,467 bytesexamples/major-revision-with-missing-evidence.mddoc1,502 bytesexamples/minor-revision.mddoc1,719 bytesreferences/action-mapping.mddoc3,706 bytesreferences/chinese-author-alignment.mddoc3,341 bytesreferences/comment-taxonomy.mddoc4,168 bytesreferences/difficult-cases.mddoc4,073 bytesreferences/intake-and-routing.mddoc4,999 bytesreferences/qa-checklist.mddoc3,164 bytesreferences/response-structure.mddoc3,621 bytesreferences/source-basis.mddoc3,228 bytesreferences/tone-and-stance.mddoc3,336 bytestests/conflicting-reviewers.mddoc1,817 bytestests/defensive-draft-audit.mddoc1,768 bytestests/evaluation-summary.mddoc2,205 bytestests/impossible-experiment.mddoc1,673 bytestests/major-revision-missing-evidence.mddoc1,818 bytestests/minor-revision.mddoc1,396 bytestests/rubric.mddoc2,682 bytes
Read SKILL.md
# Nature Reviewer Response Skill
Use this skill to convert editor decision letters, reviewer comments, author notes, or
draft rebuttals into an auditable point-by-point response package for manuscript revisions.
The response letter is an editor-facing verification document. The goal is to show that every
reviewer concern has been understood, addressed, and mapped to a concrete manuscript change,
justified scientific response, or unresolved author action.
## Default stance
- Preserve each reviewer comment faithfully before responding.
- Every reviewer concern must be answered, cross-referenced, or explicitly marked as unresolved.
- Map every response to manuscript evidence, a revision location, a justified disagreement, or `AUTHOR_INPUT_NEEDED`.nature-writing
When your agent uses it
Draft, restructure, or plan Nature-style manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts. Use when the user wants to write or rebuild an abstract, introduction, results narrative, discussion, conclusion, title, or full manuscript argument rather than only polish finished prose.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,530 tokensWhen the skill is activated
Reference documents
21,293 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core stance
- Mined writing memory
- When to open extra files
- Intake
- Writing workflow
- Section defaults
- Output format
Files
README.mddoc2,183 bytesSKILL.mdcore7,520 bytesSKILL.mdcore7,520 bytesagents/openai.yamlasset270 bytesreferences/abstract.mddoc3,628 bytesreferences/article-architecture.mddoc3,221 bytesreferences/chinese-author-workflow.mddoc1,452 bytesreferences/conclusion.mddoc1,244 bytesreferences/examples/abstract-examples.mddoc875 bytesreferences/examples/abstract/template-a.mddoc950 bytesreferences/examples/abstract/template-b.mddoc3,265 bytesreferences/examples/abstract/template-c.mddoc1,750 bytesreferences/examples/index.mddoc2,402 bytesreferences/examples/introduction-examples.mddoc1,544 bytesreferences/examples/introduction/novel-task-challenge-decomposition.mddoc1,550 bytesreferences/examples/introduction/pipeline-not-recommended-abstract-only.mddoc2,976 bytesreferences/examples/introduction/pipeline-version-1-one-contribution-multi-advantages.mddoc2,039 bytesreferences/examples/introduction/pipeline-version-2-two-contributions.mddoc2,049 bytesreferences/examples/introduction/pipeline-version-3-new-module-on-existing-pipeline.mddoc1,514 bytesreferences/examples/introduction/pipeline-version-4-observation-driven.mddoc1,441 bytesreferences/examples/introduction/technical-challenge-version-1-existing-task.mddoc2,690 bytesreferences/examples/introduction/technical-challenge-version-2-existing-task-insight-backed-by-traditional.mddoc3,848 bytesreferences/examples/introduction/technical-challenge-version-3-novel-task.mddoc1,629 bytesreferences/examples/introduction/version-1-task-then-application.mddoc727 bytesreferences/examples/introduction/version-2-application-first.mddoc405 bytesreferences/examples/introduction/version-3-general-to-specific-setting.mddoc847 bytesreferences/examples/introduction/version-4-open-with-challenge.mddoc1,753 bytesreferences/examples/method-examples.mddoc1,028 bytesreferences/examples/method/example-of-the-three-elements.mddoc7,440 bytesreferences/examples/method/method-writing-common-issues-note.mddoc355 bytesreferences/examples/method/module-design-instant-ngp.mddoc4,557 bytesreferences/examples/method/module-motivation-patterns.mddoc410 bytesreferences/examples/method/module-triad-neural-body.mddoc763 bytesreferences/examples/method/neural-body-annotated-figure-text.mddoc2,845 bytesreferences/examples/method/overview-template.mddoc2,054 bytesreferences/examples/method/pre-writing-questions.mddoc479 bytesreferences/examples/method/section-skeleton.mddoc110 bytesreferences/experiments.mddoc4,476 bytesreferences/introduction.mddoc15,015 bytesreferences/method.mddoc6,256 bytesreferences/paper-review.mddoc5,428 bytesreferences/paragraph-flow.mddoc1,695 bytesreferences/related-work.mddoc1,283 bytes
Read SKILL.md
# Nature-Style Scientific Writing
Use this skill when the user needs help creating or rebuilding manuscript prose,
not merely polishing existing sentences.
## Core stance
- Author evidence comes first. Do not invent results, mechanisms, references,
methods, novelty, sample sizes, statistics or limitations.
- Write the argument before writing the sentences.
- Make the paper easy to judge: relevance, novelty, trust, reuse and meaning.
- Use ambitious but bounded claims.
- If essential evidence is missing, write a placeholder or ask for the missing
input instead of filling the gap.obsidian-kb-artifacts
When your agent uses it
Use this skill for Obsidian-native formatting and derived artifacts such as Markdown formatting, wikilinks, registry tables, canvas files, optional Bases, CLI operations, and link repair. This skill does not decide knowledge routing.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
267 tokensWhen the skill is activated
Reference documents
1,870 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Responsibilities
- Rules
- Read next
Files
SKILL.mdcore1,210 bytesSKILL.mdcore1,210 bytesreferences/BASES.mddoc954 bytesreferences/CANVAS.mddoc4,203 bytesreferences/CLI.mddoc797 bytesreferences/LINK-REPAIR.mddoc108 bytesreferences/OBSIDIAN-MARKDOWN.mddoc2,106 bytesreferences/REGISTRY-TABLES.mddoc129 bytes
Read SKILL.md
# Obsidian KB Artifacts
This skill handles format and artifact concerns only.
## Responsibilities
- Obsidian Markdown formatting
- wikilinks and embeds
- registry table formatting
- canvas generation and validation
- optional Bases generation
- Obsidian CLI operations
- link repair in canonical notes
- lint-report formattingobsidian-literature-workflow
When your agent uses it
Use this skill for project-scoped literature review built on Sources/Papers, with synthesis landing in Knowledge, writing handoff in Writing, and the default literature canvas under Maps/literature.canvas.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
407 tokensWhen the skill is activated
Reference documents
1,107 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Main flow
- Default outputs
- Rules
- Read next
Scripts executed separately
scripts/build_literature_canvas.pyscripts/build_literature_graph.py
Files
SKILL.mdcore1,724 bytesSKILL.mdcore1,724 bytesSKILL.mdcore1,724 bytesSKILL.mdcore1,724 bytesreferences/CANVAS-WORKFLOW.mddoc1,778 bytesreferences/CLAIM-EXTRACTION.mddoc2,072 bytesreferences/GRAPH-WORKFLOW.mddoc768 bytesreferences/LITERATURE-CANVAS.mddoc145 bytesreferences/LITERATURE-OVERVIEW.mddoc132 bytesreferences/METHOD-TAXONOMY.mddoc137 bytesreferences/PAPER-NOTE-SCHEMA.mddoc163 bytesreferences/RESEARCH-GAPS.mddoc106 bytesscripts/build_literature_canvas.pyruns23,178 bytesscripts/build_literature_graph.pyruns9,648 bytes
Read SKILL.md
# Obsidian Literature Workflow
This skill owns the **project literature workflow**.
## Main flow
```text
Sources/Papers/ -> Knowledge/ -> Writing/ -> Maps/literature.canvas
```
## Default outputs
- `Sources/Papers/{paper-slug}.md`
- `Knowledge/Literature Overview.md`obsidian-project-kb-core
When your agent uses it
Use this as the main Claude Scholar skill for a vault-first, project-scoped Obsidian research knowledge base rooted at Research/{project-slug}/. It owns bootstrap, routing, daily logging, hub/plan/index maintenance, registry updates, lifecycle actions, and lint orchestration.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
528 tokensWhen the skill is activated
Reference documents
1,198 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core rules
- Responsibilities
- Deterministic helpers
- Read next
Scripts executed separately
scripts/kb_canvas_check.pyscripts/kb_common.pyscripts/kb_index_check.pyscripts/kb_link_check.pyscripts/kb_lint.pyscripts/kb_registry_check.pyscripts/kb_scaffold.pyscripts/project_kb.py
Files
SKILL.mdcore2,204 bytesSKILL.mdcore2,204 bytesreferences/BINDING-LAYER.mddoc482 bytesreferences/DAILY-PROMOTION.mddoc563 bytesreferences/DIRECTORY-SCHEMA.mddoc753 bytesreferences/HUB-PLAN-INDEX.mddoc1,042 bytesreferences/LIFECYCLE.mddoc927 bytesreferences/LINT.mddoc433 bytesreferences/REGISTRY.mddoc857 bytesscripts/kb_canvas_check.pyruns1,926 bytesscripts/kb_common.pyruns31,366 bytesscripts/kb_index_check.pyruns1,845 bytesscripts/kb_link_check.pyruns2,593 bytesscripts/kb_lint.pyruns9,813 bytesscripts/kb_registry_check.pyruns2,180 bytesscripts/kb_scaffold.pyruns1,661 bytesscripts/project_kb.pyruns21,178 bytes
Read SKILL.md
# Obsidian Project KB Core
This is the **main workflow authority** for project-scoped Obsidian knowledge maintenance.
Default project root:
```text
Research/{project-slug}/
```
Default structure:
```text
00-Hub.mdobsidian-source-ingestion
When your agent uses it
Use this skill to ingest external materials into the current project-scoped Obsidian KB as source notes under Sources/Papers, Sources/Web, Sources/Docs, Sources/Data, Sources/Interviews, or Sources/Notes.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
254 tokensWhen the skill is activated
Reference documents
196 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Targets
- Core rules
- Read next
Files
SKILL.mdcore1,017 bytesSKILL.mdcore1,017 bytesSKILL.mdcore1,017 bytesSKILL.mdcore1,017 bytesSKILL.mdcore1,017 bytesSKILL.mdcore1,017 bytesreferences/DATA-SOURCE-NOTES.mddoc115 bytesreferences/INTERVIEW-SOURCE-NOTES.mddoc134 bytesreferences/PAPER-SOURCE-NOTES.mddoc207 bytesreferences/SOURCE-TYPES.mddoc309 bytesreferences/WEB-SOURCE-NOTES.mddoc160 bytes
Read SKILL.md
# Obsidian Source Ingestion
Use this skill when external material should become a project-local source note.
## Targets
- `Sources/Papers/`
- `Sources/Web/`
- `Sources/Docs/`
- `Sources/Data/`
- `Sources/Interviews/`
- `Sources/Notes/`
## Core rulespaper-self-review
When your agent uses it
This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before submission", "audit claims", "check overclaiming", "verify whether results support claims", or mentions systematic paper quality checking. Provides comprehensive quality assurance checklist for academic papers.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,170 tokensWhen the skill is activated
Reference documents
243 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Features
- Quality Checklist
- When to Use
- Review Process
- Best Practices
- Summary
- Reference Files
Files
SKILL.mdcore6,032 bytesexamples/example-self-review.mddoc363 bytesreferences/FINAL-VERDICT.mddoc245 bytesreferences/SECTION-CHECKLIST.mddoc547 bytes
Read SKILL.md
# Paper Self-Review
A systematic paper quality checking tool that helps researchers conduct comprehensive self-review before submission.
## Core Features
### 1. Structure Review
Check whether all sections of the paper are complete and conform to academic standards:
- Does the Abstract include problem, method, results, and contributions?
- Does the Introduction clearly articulate research motivation and background?
- Is the Method detailed enough to be reproducible?
- Do the Results sufficiently support the conclusions?
- Does the Discussion address limitations and future work?planning-with-files
When your agent uses it
Use this by default for non-trivial multi-step work that needs persistent planning, progress tracking, or durable notes on disk. Trigger when a task will likely span multiple tool calls, research steps, verification loops, or enough context that the plan should not live only in transient chat memory.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
1,020 tokensWhen the skill is activated
Reference documents
1,905 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- The 3-File Pattern
- Core Workflow
- task_plan.md Template
- notes.md Template
- Critical Rules
- When to Use This Pattern
- Anti-Patterns to Avoid
- Advanced Patterns
Files
SKILL.mdcore4,290 bytesSKILL.mdcore4,290 bytesSKILL.mdcore4,290 bytesSKILL.mdcore4,290 bytesexamples.mddoc4,426 bytesreference.mddoc3,478 bytes
Read SKILL.md
# Planning with Files
Work like Manus: use persistent markdown files as your working memory on disk.
This is not just an optional planning style. It should be the default persistence layer for complex Codex work.
Use it proactively when:
- the task will likely take more than a few tool calls
- progress needs to be tracked across phases
- findings or evidence must be preserved while working
- the task may branch, pause, or resume later
- relying on chat context alone would be fragile
plugin-structure
When your agent uses it
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
3,218 tokensWhen the skill is activated
Reference documents
14,853 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Directory Structure
- Plugin Manifest (plugin.json)
- Component Organization
- Portable Path References
- File Naming Conventions
- Auto-Discovery Mechanism
- Best Practices
- Common Patterns
- Troubleshooting
Files
README.mddoc3,210 bytesSKILL.mdcore13,796 bytesSKILL.mdcore13,796 bytesSKILL.mdcore13,796 bytesSKILL.mdcore13,796 bytesSKILL.mdcore13,796 bytesSKILL.mdcore13,796 bytesSKILL.mdcore13,796 bytesexamples/advanced-plugin.mddoc18,746 bytesexamples/minimal-plugin.mddoc1,731 bytesexamples/standard-plugin.mddoc13,310 bytesreferences/component-patterns.mddoc12,086 bytesreferences/manifest-reference.mddoc12,061 bytes
Read SKILL.md
# Plugin Structure for Claude Code
## Overview
Claude Code plugins follow a standardized directory structure with automatic component discovery. Understanding this structure enables creating well-organized, maintainable plugins that integrate seamlessly with Claude Code.
**Key concepts:**
- Conventional directory layout for automatic discovery
- Manifest-driven configuration in `.claude-plugin/plugin.json`
- Component-based organization (commands, agents, skills, hooks)
- Portable path references using `${CLAUDE_PLUGIN_ROOT}`
- Explicit vs. auto-discovered component loading
## Directory Structurepost-acceptance
When your agent uses it
This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster", "write promotion content", "create Twitter thread", or mentions post-acceptance conference preparation. Provides comprehensive workflow for presentation, poster, and promotion content creation.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
1,297 tokensWhen the skill is activated
Reference documents
2,020 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Features
- When to Use
- Workflow
- Best Practices
- Summary
- Reference Files
Files
SKILL.mdcore5,922 bytesSKILL.mdcore5,922 bytesexamples/post-acceptance-plan.mddoc204 bytesreferences/deliverable-checklists.mddoc344 bytesreferences/design-guidelines.mddoc2,454 bytesreferences/poster-templates/basic-poster-template.mddoc496 bytesreferences/presentation-templates/basic-template.mddoc420 bytesreferences/promotion-examples/twitter-example.mddoc711 bytesreferences/xquik-promotion.mddoc3,097 bytes
Read SKILL.md
# Post-Acceptance Conference Preparation
A post-acceptance conference preparation workflow that helps researchers efficiently complete presentations, posters, and promotional content.
## Core Features
### 1. Presentation Slide Creation
Guidance for creating conference presentation slides:
**Time Control**
- 15-minute talk: 10-15 slides
- 20-minute talk: 15-20 slides
- 30-minute talk: 20-30 slidespublication-chart-skill
When your agent uses it
This skill should be used when the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants an existing scientific figure/table reviewed and upgraded.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
2,818 tokensWhen the skill is activated
Reference documents
13,276 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Goal
- Use this skill when
- Do not use this skill for
- Primary contract
- Default workflow
- Missing dependency behavior
- Composite assembly rule
- Output style rules
- Recommended response shape
- Resources
Scripts executed separately
scripts/ensure_publication_tooling.py
Files
SKILL.mdcore13,221 bytesexamples/01-benchmark-comparison-figure.mddoc839 bytesexamples/02-ablation-figure.mddoc798 bytesexamples/03-calibration-evaluation-figure.mddoc721 bytesexamples/04-forest-diagnostic-figure.mddoc691 bytesexamples/05-publication-table-from-excel.mddoc940 bytesexamples/06-mixed-figure-table-results.mddoc795 bytesexamples/07-revision-from-weak-chart.mddoc888 bytesexamples/08-review-existing-figure-or-table.mddoc1,164 bytesreferences/chart-selection.mddoc2,500 bytesreferences/composite-assembly.mddoc985 bytesreferences/execution-and-verification.mddoc4,568 bytesreferences/pubfig-recipes.mddoc2,409 bytesreferences/publication-qa-checklist.mddoc1,632 bytesreferences/pubtab-recipes.mddoc3,279 bytesreferences/source-guides/pubfig-api-map.mddoc4,954 bytesreferences/source-guides/pubfig-architecture.mddoc5,775 bytesreferences/source-guides/pubfig-export-flow.mddoc6,496 bytesreferences/source-guides/pubtab-architecture.mddoc5,756 bytesreferences/source-guides/pubtab-backend-and-preview.mddoc6,034 bytesreferences/source-guides/pubtab-cli-api-flow.mddoc4,772 bytesreferences/workflow.mddoc2,233 bytesscripts/ensure_publication_tooling.pyruns5,428 bytes
Read SKILL.md
# Publication Chart Skill
## Goal
Use this skill to turn research results into **publication-grade figures and tables** with an end-to-end workflow.
Primary production stack:
- **`pubfig`** for figures
- **`pubtab`** for publication tables
This skill covers the full delivery chain:
1. understand the scientific communication goal,research-ideation
When your agent uses it
This skill should be used when the user asks to "brainstorm research ideas", "use 5W1H framework", "identify research gaps", "conduct gap analysis", "start research project", "conduct literature review", "define research question", "select research method", "plan research", or mentions research project initiation phase. Provides comprehensive guidance for research startup workflow from idea generation to planning.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,984 tokensWhen the skill is activated
Reference documents
14,845 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Features
- When to Use
- Integration with Other Systems
- Additional Resources
Files
SKILL.mdcore9,743 bytesSKILL.mdcore9,743 bytesexamples/example-literature-review.mddoc3,476 bytesexamples/example-research-proposal.mddoc5,158 bytesreferences/5w1h-framework.mddoc4,878 bytesreferences/gap-analysis-guide.mddoc7,490 bytesreferences/literature-search-strategies.mddoc6,493 bytesreferences/method-selection-guide.mddoc4,137 bytesreferences/research-contract.mddoc4,121 bytesreferences/research-planning.mddoc3,695 bytesreferences/research-question-formulation.mddoc5,727 bytesreferences/zotero-integration-guide.mddoc5,695 bytes
Read SKILL.md
# Research Ideation
Supports the complete workflow for the research project initiation phase, from vague idea to a traceable research contract: research question, hypothesis, evidence needs, falsification criteria, method selection, and next action.
## Core Features
### 1. Idea Brainstorming (5W1H Framework)
Systematically brainstorm research ideas using the 5W1H framework:
- **What**: What problem or phenomenon to study
- **Why**: Why this problem is important
- **Who**: Target audience and stakeholders
- **When**: Time scope and context of the research
- **Where**: Application scenarios and domainsresults-analysis
When your agent uses it
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on strict analysis bundles, not Results-section prose.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,970 tokensWhen the skill is activated
Reference documents
11,386 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core contract
- Non-negotiable quality bar
- Standard workflow
- Output structure
- Figure interpretation rule
- Read-only audit mode
- Failure mode policy
- Reference files
- Example files
Files
../research-ideation/references/research-contract.mddoc4,121 bytesSKILL.mdcore9,498 bytesUSAGE.mddoc2,938 bytesexamples/example-analysis-report.mddoc2,208 bytesexamples/example-figure-catalog.mddoc1,371 bytesexamples/example-stats-appendix.mddoc1,244 bytesreferences/analysis-depth.mddoc844 bytesreferences/common-pitfalls.mddoc998 bytesreferences/figure-interpretation.mddoc939 bytesreferences/statistical-methods.mddoc16,437 bytesreferences/statistical-reporting.mddoc1,082 bytesreferences/visualization-best-practices.mddoc6,589 bytes
Read SKILL.md
# Results Analysis
Run **strict, evidence-first experimental analysis** for ML/AI research.
Use this skill to produce a **strict analysis bundle**:
- `analysis-report.md`
- `stats-appendix.md`
- `figure-catalog.md`
- `figures/`
When the user asks for review, audit, no-write, dry-run, or when inputs are incomplete, use **read-only audit mode** instead of producing files or figures. In that mode, output only valid/invalid statistics, blockers, claim candidates, and what evidence is missing. If invoked by `/analyze-results`, the command layer may write a blocker summary, but this skill should not create figures, reports, or polished conclusions from incomplete evidence.
Do **not** use this skill to draft a paper `Results` section or a full experiment wrap-up report. Those belong to `ml-paper-writing` or `results-report`.
results-report
When your agent uses it
This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
1,408 tokensWhen the skill is activated
Reference documents
2,186 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role boundary
- Default output
- Required frontmatter
- Default report structure
- Workflow
- Required quality bar
- Reference files
Files
SKILL.mdcore6,374 bytesexamples/example-results-report.mddoc4,021 bytesreferences/EVIDENCE-PROPAGATION.mddoc1,433 bytesreferences/decision-oriented-analysis.mddoc542 bytesreferences/figure-interpretation.mddoc628 bytesreferences/report-naming.mddoc1,067 bytesreferences/report-structure.mddoc1,392 bytesreferences/statistical-completeness.mddoc543 bytes
Read SKILL.md
# Results Report
Write the **complete post-experiment summary report** after analysis artifacts are ready.
This skill is for the stage **after** `results-analysis`.
## Role boundary
### `results-analysis` does
- strict statistics,
- real figures,
- figure interpretation scaffolding,
- stats appendix.
review-response
When your agent uses it
Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,175 tokensWhen the skill is activated
Reference documents
15,122 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Features
- Workflow
- When to Use
- Usage Steps
- Core Principles
- Success Factors (Based on ICLR Spotlight Paper Analysis)
- Integration with active installed writing memory
- Evidence anchor rule
- Reference Documents
- Related Tools
Files
SKILL.mdcore5,760 bytesreferences/rebuttal-templates.mddoc17,298 bytesreferences/response-strategies.mddoc19,245 bytesreferences/review-classification.mddoc3,478 bytesreferences/successful-cases.mddoc10,729 bytesreferences/tone-guidelines.mddoc9,844 bytes
Read SKILL.md
# Review Response
A systematic review response workflow that helps researchers efficiently and professionally reply to reviewer comments.
## Core Features
1. **Review Analysis** - Parse and classify reviewer comments (Major/Minor/Typo/Misunderstanding)
2. **Response Strategy** - Develop response strategies for different comment types (Accept/Defend/Clarify/Experiment)
3. **Rebuttal Writing** - Write structured, professional rebuttal documents
4. **Tone Management** - Optimize tone to maintain professionalism, respect, and evidence-based arguments
## Workflow
```skill-development
When your agent uses it
This skill should be used when the user asks to create a new skill, repair an existing skill, improve trigger descriptions, reorganize skill structure, or make a Claude skill more reusable and internally consistent.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
961 tokensWhen the skill is activated
Reference documents
2,645 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Goal
- Core rules
- Default workflow
- Typical repair patterns
- Recommended output shape
- References
Files
SKILL.mdcore4,468 bytesSKILL.mdcore4,468 bytesreferences/checklist.mddoc640 bytesreferences/integrity-checks.mddoc610 bytesreferences/skill-creator-original.mddoc11,547 bytes
Read SKILL.md
# Skill Development
Use this skill to create or repair Claude skills in the **current local environment**, not in an abstract plugin template.
## Goal
Produce a skill that is:
- easy to trigger,
- lean at the `SKILL.md` layer,
- backed by real `references/`, `examples/`, and `scripts/` files when they are mentioned,
- free of dead local references.
## Core rules
skill-improver
When your agent uses it
This skill should be used when the user asks to "apply skill improvements", "update skill from plan", "execute improvement plan", "fix skill issues", "implement skill recommendations", or mentions applying improvements from quality review reports. Reads improvement-plan-{name}.md files generated by skill-quality-reviewer and intelligently merges and executes the suggested changes to improve Claude Skills quality.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
1,607 tokensWhen the skill is activated
Reference documents
7,167 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Workflow
- When to Use
- Step-by-Step Guide
- Priority Handling
- Integration with Skill Quality Reviewer
- Additional Resources
- Best Practices
- Usage Examples
Scripts executed separately
scripts/backup-skill.shscripts/verify-update.sh
Files
SKILL.mdcore7,085 bytesSKILL.mdcore7,085 bytesSKILL.mdcore7,085 bytesSKILL.mdcore7,085 bytesexamples/improvement-plan-example.mddoc2,090 bytesexamples/update-report-example.mddoc1,256 bytesreferences/error-handling.mddoc812 bytesreferences/merge-strategies.mddoc14,439 bytesreferences/plan-format.mddoc10,884 bytesreferences/supported-updates.mddoc791 bytesscripts/backup-skill.shruns1,432 bytesscripts/verify-update.shruns7,080 bytes
Read SKILL.md
# Skill Improver
Execute improvement plans generated by `skill-quality-reviewer` to automatically update and fix issues in Claude Skills.
## Core Workflow
```
Read improvement-plan-{name}.md
↓
Parse improvement items (High/Medium/Low priority)
↓
Group changes by file
↓
Detect and resolve conflictsskill-quality-reviewer
When your agent uses it
This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report". Evaluates local skills across description quality, content organization, writing style, and structural integrity.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
2,794 tokensWhen the skill is activated
Reference documents
8,925 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use This Skill
- Review Modes
- Analysis Workflow
- Output Templates
- Quick Wins (Easy Fixes)
- Estimated Time to Complete
- Expected Score Improvement
Scripts executed separately
scripts/extract-yaml.shscripts/skill-audit.py
Files
SKILL.mdcore12,010 bytesSKILL.mdcore12,010 bytesreferences/batch-review-template.mddoc164 bytesreferences/examples-bad.mddoc13,094 bytesreferences/examples-good.mddoc10,893 bytesreferences/scoring-criteria.mddoc12,750 bytesscripts/extract-yaml.shruns728 bytesscripts/skill-audit.pyruns1,174 bytes
Read SKILL.md
# Skill Quality Reviewer
## Overview
A meta-skill for evaluating the quality of Claude Skills. Perform comprehensive analysis across four key dimensions—description quality (25%), content organization (30%), writing style (20%), and structural integrity (25%)—to generate weighted scores, letter grades, and actionable improvement plans.
Use this skill to validate skills before sharing, identify improvement opportunities, or ensure compliance with skill development best practices.
## When to Use This Skill
**Invoke this skill when:**
- Analyzing a skill's quality before distribution
- Reviewing skill documentation for best practices
- Evaluating adherence to skill development standardsui-ux-pro-max
When your agent uses it
This skill should be used when the user asks to design or review a UI, create a landing page or dashboard, choose colors or typography, improve accessibility, or implement polished frontend interfaces with a clear design system.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
984 tokensWhen the skill is activated
Reference documents
163 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Core workflow
- Default output shape
- Safety rules
- References
Scripts executed separately
scripts/search.py
Files
SKILL.mdcore4,268 bytesSKILL.mdcore4,268 bytesSKILL.mdcore4,268 bytesSKILL.mdcore4,268 bytesSKILL.mdcore4,268 bytesdata/ui-reasoning.csvasset2,097 bytesreferences/USAGE.mddoc727 bytesscripts/search.pyruns12,628 bytes
Read SKILL.md
# UI/UX Pro Max
Use this skill to turn a vague UI request into a **concrete design system plus implementation guidance**.
## Role
This skill is for:
- design-system selection,
- palette and typography choices,
- UX review and remediation,
- stack-aware frontend implementation guidance,
- lightweight design-system persistence for multi-page work.
It is **not** a replacement for product strategy or user research. Use it to make execution sharper after the product direction is already roughly known.uv-package-manager
When your agent uses it
Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
4,181 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Core Concepts
- Installation
- Quick Start
- Virtual Environment Management
- Package Management
- Python Version Management
- Project Configuration
- Advanced Workflows
- Performance Optimization
- Comparison with Other Tools
- Common Workflows
- Tool Integration
- Troubleshooting
- Best Practices
- Migration Guide
- Command Reference
- Resources
- Best Practices Summary
Files
SKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytesSKILL.mdcore16,063 bytes
Read SKILL.md
# UV Package Manager
Comprehensive guide to using uv, an extremely fast Python package installer and resolver written in Rust, for modern Python project management and dependency workflows.
## When to Use This Skill
- Setting up new Python projects quickly
- Managing Python dependencies faster than pip
- Creating and managing virtual environments
- Installing Python interpreters
- Resolving dependency conflicts efficiently
- Migrating from pip/pip-tools/poetry
- Speeding up CI/CD pipelines
- Managing monorepo Python projectsverification-loop
When your agent uses it
This skill should be used when the user asks to "verify code", "run verification", "check quality", "validate changes", or before creating a PR. Provides comprehensive verification including build, type check, lint, tests, security scan, and diff review.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
963 tokensWhen the skill is activated
Reference documents
225 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Verification Phases
- Output Format
- Continuous Mode
- Integration with Hooks
- Reference Files
Files
SKILL.mdcore3,550 bytesSKILL.mdcore3,550 bytesSKILL.mdcore3,550 bytesSKILL.mdcore3,550 bytesSKILL.mdcore3,550 bytesSKILL.mdcore3,550 bytesSKILL.mdcore3,550 bytesexamples/example-verification-report.mddoc197 bytesreferences/REPORT-TEMPLATE.mddoc248 bytesreferences/STACK-DETECTION.mddoc420 bytes
Read SKILL.md
# Verification Loop Skill
A comprehensive verification system for Claude Code sessions.
## When to Use
Invoke this skill:
- After completing a feature or significant code change
- Before creating a PR
- When you want to ensure quality gates pass
- After refactoring
## Verification Phases
web-design-reviewer
When your agent uses it
This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
2,460 tokensWhen the skill is activated
Reference documents
3,479 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope of Application
- Prerequisites
- Workflow Overview
- Step 1: Information Gathering Phase
- Step 2: Visual Inspection Phase
- Step 3: Issue Fixing Phase
- Step 4: Re-verification Phase
- Output Format
- Required Capabilities
- Reference Implementation
- Best Practices
- Troubleshooting
Files
SKILL.mdcore10,535 bytesSKILL.mdcore10,535 bytesSKILL.mdcore10,535 bytesSKILL.mdcore10,535 bytesSKILL.mdcore10,535 bytesreferences/framework-fixes.mddoc7,437 bytesreferences/visual-checklist.mddoc5,989 bytes
Read SKILL.md
# Web Design Reviewer
This skill enables visual inspection and validation of website design quality, identifying and fixing issues at the source code level.
## Scope of Application
- Static sites (HTML/CSS/JS)
- SPA frameworks such as React / Vue / Angular / Svelte
- Full-stack frameworks such as Next.js / Nuxt / SvelteKit
- CMS platforms such as WordPress / Drupal
- Any other web application
## Prerequisites
webapp-testing
When your agent uses it
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
894 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Decision Tree: Choosing Your Approach
- Example: Using with_server.py
- Reconnaissance-Then-Action Pattern
- Common Pitfall
- Best Practices
- Reference Files
Scripts executed separately
examples/console_logging.pyexamples/element_discovery.pyexamples/static_html_automation.pyscripts/with_server.py
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore3,929 bytesSKILL.mdcore3,929 bytesSKILL.mdcore3,929 bytesSKILL.mdcore3,929 bytesSKILL.mdcore3,929 bytesSKILL.mdcore3,929 bytesSKILL.mdcore3,929 bytesSKILL.mdcore3,929 bytesSKILL.mdcore3,929 bytesexamples/console_logging.pyruns1,027 bytesexamples/element_discovery.pyruns1,463 bytesexamples/static_html_automation.pyruns953 bytesscripts/with_server.pyruns3,693 bytes
Read SKILL.md
# Web Application Testing
To test local web applications, write native Python Playwright scripts.
**Helper Scripts Available**:
- `scripts/with_server.py` - Manages server lifecycle (supports multiple servers)
**Always run scripts with `--help` first** to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather than ingested into your context window.
## Decision Tree: Choosing Your Approach
```
User task → Is it static HTML?
├─ Yes → Read HTML file directly to identify selectorswriting-anti-ai
When your agent uses it
This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to eliminate AI writing patterns from prose. Supports both English and Chinese text. Based on Wikipedia's "Signs of AI writing" guide, detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI vocabulary, negative parallelisms, and excessive conjunctive phrases.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,360 tokensWhen the skill is activated
Reference documents
6,840 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use This Skill
- Core Rules (快速检查清单)
- Common AI Patterns (常见 AI 模式)
- Personality and Soul (注入灵魂)
- Workflow (工作流程)
- Quick Scoring (快速评分)
- Examples (示例)
- Quick Reference (快速参考)
- Additional Resources
- Best Practices
- License
- Attribution
Files
SKILL.mdcore9,508 bytesSKILL.mdcore9,508 bytesexamples/chinese.mddoc3,690 bytesexamples/english.mddoc4,215 bytesreferences/patterns-chinese.mddoc9,321 bytesreferences/patterns-english.mddoc10,020 bytesreferences/phrases-to-cut.mddoc324 bytesreferences/wikipedia-source.mddoc211 bytes
Read SKILL.md
# Writing Anti-AI
Remove AI-generated writing patterns from text to make it sound natural and human-written. Supports both English and Chinese.
When editing academic prose, check the active installed
`skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md`
under the current client's skill home for relevant source-attributed writing
examples. Use it only to guide natural structure and rhythm. Keep the author's
meaning, evidence, and target venue constraints intact. If the memory is absent
or irrelevant, continue with this skill's own pattern references.
## Overview
This skill identifies and eliminates predictable AI writing patterns from prose, based on [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup.zotero-obsidian-bridge
When your agent uses it
Use this skill when Zotero is the literature source of truth and the project KB should receive source notes under Sources/Papers plus project-linked synthesis in Knowledge and Writing.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
426 tokensWhen the skill is activated
Reference documents
3,021 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Evidence extraction requirement
Scripts executed separately
scripts/verify_paper_notes.py
Files
../research-ideation/references/research-contract.mddoc4,121 bytesSKILL.mdcore2,056 bytesSKILL.mdcore2,056 bytesSKILL.mdcore2,056 bytesSKILL.mdcore2,056 bytesSKILL.mdcore2,056 bytesexamples/example-collection-inventory.mddoc770 bytesreferences/COLLECTION-INVENTORY-SCHEMA.mddoc1,110 bytesreferences/LOCAL-ZOTERO-FALLBACK.mddoc788 bytesreferences/PAPER-NOTE-SCHEMA.mddoc2,157 bytesreferences/WORKFLOW.mddoc4,232 bytesscripts/verify_paper_notes.pyruns7,344 bytes
Read SKILL.md
# Zotero Obsidian Bridge
Use this skill when papers live in Zotero and the project KB should receive project-local notes.
Default flow:
```text
Zotero -> Sources/Papers -> Knowledge -> Writing -> Maps/literature.canvas
```
Rules:
- one canonical paper note per paper under `Sources/Papers/`
- literature synthesis goes to `Knowledge/`
- writing-oriented outputs go to `Writing/`Skills included
- agent-identifier
- architecture-design
- bug-detective
- citation-verification
- code-review-excellence
- command-development
- daily-coding
- daily-paper-generator
- defuddle
- doc-coauthoring
- expression-skill
- frontend-design
- git-workflow
- hook-development
- kaggle-learner
- latex-conference-template-organizer
- mcp-integration
- ml-paper-writing
- nature-data
- nature-polishing
- nature-response
- nature-writing
- obsidian-kb-artifacts
- obsidian-literature-workflow
- obsidian-project-kb-core
- obsidian-source-ingestion
- paper-self-review
- planning-with-files
- plugin-structure
- post-acceptance
- publication-chart-skill
- research-ideation
- results-analysis
- results-report
- review-response
- skill-development
- skill-improver
- skill-quality-reviewer
- ui-ux-pro-max
- uv-package-manager
- verification-loop
- web-design-reviewer
- webapp-testing
- writing-anti-ai
- zotero-obsidian-bridge
Repository facts
- License
- MIT
- Created
- Jan 27, 2026
- Last pushed
- Oct 19, 2026
- Forks
- 469
- Open issues
- 0
- Project activity
- Active
Rank over the last 12 weeks
Now #251 · best #207 · down 23 in 30 days
- #244 on Nov 2
- #245 on Nov 3
- #247 on Nov 4
- #248 on Nov 5
- #249 on Nov 6
- #251 since Nov 7
66 earlier periods
- #195 on Aug 2
- #198 on Aug 8
- #202 on Aug 9
- #207 from Aug 10 to Aug 11
- #205 on Aug 12
- #207 from Aug 13 to Aug 14
- #208 on Aug 15
- #207 on Aug 16
- #208 on Aug 17
- #210 on Aug 18
- #209 on Aug 19
- #207 on Aug 20
- #210 on Aug 21
- #207 on Aug 22
- #214 on Aug 23
- #213 on Aug 24
- #214 from Aug 25 to Aug 26
- #215 on Aug 27
- #213 from Aug 28 to Aug 29
- #211 from Aug 30 to Aug 31
- #217 on Sep 1
- #213 on Sep 2
- #219 on Sep 3
- #216 on Sep 4
- #219 on Sep 5
- #216 on Sep 6
- #218 from Sep 7 to Sep 8
- #219 from Sep 9 to Sep 12
- #221 from Sep 13 to Sep 16
- #222 on Sep 17
- #225 on Sep 18
- #223 on Sep 19
- #225 on Sep 20
- #226 from Sep 21 to Sep 22
- #225 on Sep 23
- #224 on Sep 24
- #223 on Sep 25
- #224 on Sep 26
- #225 on Sep 27
- #228 from Sep 28 to Sep 29
- #225 on Sep 30
- #227 on Oct 1
- #229 on Oct 2
- #225 on Oct 3
- #223 on Oct 4
- #224 on Oct 5
- #226 on Oct 6
- #229 on Oct 7
- #228 on Oct 8
- #232 on Oct 9
- #229 on Oct 10
- #230 on Oct 11
- #233 on Oct 12
- #234 on Oct 13
- #232 from Oct 14 to Oct 15
- #231 on Oct 16
- #233 from Oct 17 to Oct 19
- #234 on Oct 20
- #235 on Oct 21
- #234 on Oct 22
- #235 from Oct 23 to Oct 25
- #237 on Oct 28
- #240 on Oct 29
- #243 on Oct 30
- #244 on Oct 31
- #242 on Nov 1
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
Changed on Oct 27, 2026
No longer found: Access to secrets
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 239 notes
hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/architecture-design/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/architecture-design/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/architecture-design/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/architecture-design/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/architecture-design/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/bug-detective/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 60 dangerous shell commandsin 22 files: ml-paper-writing/templates/aaai2026/aaai2026-unified-template.tex:121 bug-detective/SKILL.md:158 git-workflow/references/advanced-usage.md:130 and 19 more
- 894 network referencesin 90 files: ml-paper-writing/references/sources.md:11 kaggle-learner/references/knowledge/.archive/time-series.md:804 kaggle-learner/references/knowledge/time-series/birdclef-2024.md:156 and 87 more
- No hidden or obfuscated text
- No instruction overrides
- 48 executable scriptsin 43 files: hooks/hooks.json:1 agent-identifier/scripts/validate-agent.sh:1 architecture-design/examples/augmentation_example.py:1 and 40 more
- 51 references to secretsin 18 files: mcp-integration/references/authentication.md:93 mcp-integration/references/server-types.md:30 mcp-integration/SKILL.md:131 and 15 more
- No requests to vote in Hot
Show all 1,053 signals by file
.claude-plugin/marketplace.json
- Network accessline 6
"metadata": { "description": "Semi-automated research assistant for academic research and software development", "homepage": "https://github.com/Galaxy-Dawn/claude-scholar" - Network accessline 7
"description": "Semi-automated research assistant for academic research and software development", "homepage": "https://github.com/Galaxy-Dawn/claude-scholar" }, - Network accessline 8
"homepage": "https://github.com/Galaxy-Dawn/claude-scholar"
.claude-plugin/plugin.json
- Network accessline 6
"name": "Galaxy-Dawn" }, "repository": "https://github.com/Galaxy-Dawn/claude-scholar", - Network accessline 7
}, "repository": "https://github.com/Galaxy-Dawn/claude-scholar", "homepage": "https://github.com/Galaxy-Dawn/claude-scholar", - Network accessline 8
"repository": "https://github.com/Galaxy-Dawn/claude-scholar", - Network accessline 9
"homepage": "https://github.com/Galaxy-Dawn/claude-scholar",
hooks/hooks.json
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
skills/agent-identifier/scripts/validate-agent.sh
- Executable scriptline 1
#!/bin/bash
skills/architecture-design/examples/augmentation_example.py
- Executable scriptline 1
Executable file
skills/architecture-design/examples/custom_dataset.py
- Executable scriptline 1
Executable file
skills/architecture-design/examples/custom_model.py
- Executable scriptline 1
Executable file
skills/architecture-design/examples/pipeline_example.sh
- Executable scriptline 1
#!/bin/bash
skills/bug-detective/SKILL.md
skills/bug-detective/examples/debugging-workflow.py
- Executable scriptline 1
Executable file
skills/bug-detective/examples/debugging-workflow.sh
skills/bug-detective/examples/error-handling-patterns.py
- Executable scriptline 1
Executable file
skills/bug-detective/references/common-patterns.md
- Network accessline 226
// ❌ 没有处理 Promise 错误 async function getData() { const response = await fetch(url); - Network accessline 227
async function getData() { const response = await fetch(url); return response.json(); // 如果失败会抛出异常 - Network accessline 228
const response = await fetch(url); - Network accessline 233
async function getData() { try { const response = await fetch(url); - Network accessline 234
try { const response = await fetch(url); return await response.json(); - Network accessline 235
const response = await fetch(url);
skills/citation-verification/references/api-usage.md
- Network accessline 25
GET https://api.semanticscholar.org/graph/v1/paper/{paper_id} - Network accessline 30
GET https://api.semanticscholar.org/graph/v1/paper/search?query={query} - Network accessline 106
GET http://export.arxiv.org/api/query?search_query={query}&start={start}&max_results={max} - Network accessline 182
GET https://api.crossref.org/works/{doi} - Network accessline 187
GET https://doi.org/{doi} - Network accessline 197
def get_crossref_metadata(doi): url = f"https://api.crossref.org/works/{doi}" response = requests.get(url) - Network accessline 198
url = f"https://api.crossref.org/works/{doi}" response = requests.get(url) if response.status_code == 200: - Network accessline 199
response = requests.get(url) - Network accessline 216
def doi_to_bibtex(doi): url = f"https://doi.org/{doi}" - Network accessline 217
url = f"https://doi.org/{doi}" headers = {"Accept": "application/x-bibtex"} response = requests.get(url, headers=headers) - Network accessline 218
headers = {"Accept": "application/x-bibtex"} response = requests.get(url, headers=headers) if response.status_code == 200: - Network accessline 219
response = requests.get(url, headers=headers)
skills/citation-verification/references/common-errors.md
skills/citation-verification/scripts/api-clients.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 72
API 文档: https://api.crossref.org/ - Network accessline 80
super().__init__(rate_limit) self.base_url = "https://api.crossref.org" - Network accessline 81
self.base_url = "https://api.crossref.org" - Network accessline 92
def request(): url = f"{self.base_url}/works/{doi}" response = requests.get(url, timeout=10) - Network accessline 93
url = f"{self.base_url}/works/{doi}" response = requests.get(url, timeout=10) response.raise_for_status() - Network accessline 94
response = requests.get(url, timeout=10) - Network accessline 164
def request(): url = f"https://doi.org/{doi}" - Network accessline 165
url = f"https://doi.org/{doi}" headers = {"Accept": "application/x-bibtex"} response = requests.get(url, headers=headers, timeout=10) - Network accessline 166
headers = {"Accept": "application/x-bibtex"} response = requests.get(url, headers=headers, timeout=10) response.raise_for_status() - Network accessline 167
response = requests.get(url, headers=headers, timeout=10) - Network accessline 183
API 文档: https://info.arxiv.org/help/api/ - Network accessline 307
API 文档: https://api.semanticscholar.org/api-docs/
skills/citation-verification/scripts/format-checker.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 316
field='doi', message=f"DOI 包含 URL 前缀: {doi}", suggestion="只保留 DOI 本身,移除 https://doi.org/ 前缀" - Network accessline 317
message=f"DOI 包含 URL 前缀: {doi}", suggestion="只保留 DOI 本身,移除 https://doi.org/ 前缀" )) - Network accessline 318
suggestion="只保留 DOI 本身,移除 https://doi.org/ 前缀"
skills/citation-verification/scripts/verify-citations.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 250
try: url = f"https://api.crossref.org/works/{doi}" response = requests.get(url, timeout=10) - Network accessline 251
url = f"https://api.crossref.org/works/{doi}" response = requests.get(url, timeout=10) if response.status_code == 200: - Network accessline 252
response = requests.get(url, timeout=10)
skills/code-review-excellence/SKILL.md
- Network accessline 301
// ❌ Not handling async errors async function fetchUser(id: string) { const response = await fetch(`/api/users/${id}`); - Network accessline 302
async function fetchUser(id: string) { const response = await fetch(`/api/users/${id}`); return response.json(); // What if network fails? - Network accessline 303
const response = await fetch(`/api/users/${id}`); - Network accessline 308
async function fetchUser(id: string): Promise<User> { try { const response = await fetch(`/api/users/${id}`); - Network accessline 309
try { const response = await fetch(`/api/users/${id}`); if (!response.ok) { - Network accessline 310
const response = await fetch(`/api/users/${id}`); - Dangerous shell operationline 411
- [ ] No eval() or similar dynamic execution?
skills/code-review-excellence/scripts/pr-analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/command-development/examples/plugin-commands.md
skills/command-development/references/advanced-workflows.md
skills/command-development/references/documentation-patterns.md
skills/command-development/references/marketplace-considerations.md
- Network accessline 96
INSTALLATION: - git: https://git-scm.com/downloads - jq: https://stedolan.github.io/jq/download/ - Network accessline 97
- git: https://git-scm.com/downloads - jq: https://stedolan.github.io/jq/download/ - node: https://nodejs.org/ - Network accessline 98
- jq: https://stedolan.github.io/jq/download/ - Network accessline 99
- node: https://nodejs.org/ - Network accessline 635
**Need Help?** - Documentation: https://docs.example.com - Network accessline 636
- Documentation: https://docs.example.com - Network accessline 638
- Community: https://community.example.com - Dangerous shell operationline 676
1. Remove flag: rm .claude/operation-completed.flag - Dangerous shell operationline 720
rm -rf $TEMP_DIR - Network accessline 872
Release notes: https://releases.example.com/v$LATEST_VERSION
skills/command-development/references/testing-strategies.md
- Dangerous shell operationline 243
rm /tmp/test-file*.txt /tmp/large-file.bin
skills/daily-paper-generator/example/daily paper example.md
- Network accessline 7
## arXiv 链接 https://arxiv.org/abs/2601.06134 - Network accessline 8
https://arxiv.org/abs/2601.06134 - Network accessline 37
| **第一作者单位** | Zhejiang University, College of Computer Science and Technology | | **发表日期** | 2026-01-05 | | **arXiv 链接** | https://arxiv.org/abs/2601.06134 | - Network accessline 38
| **发表日期** | 2026-01-05 | | **arXiv 链接** | https://arxiv.org/abs/2601.06134 | | **PDF 链接** | https://arxiv.org/pdf/2601.06134 | - Network accessline 39
| **arXiv 链接** | https://arxiv.org/abs/2601.06134 | | **PDF 链接** | https://arxiv.org/pdf/2601.06134 | | **分类** | cs.LG, q-bio.NC, eess.SP | - Network accessline 40
| **PDF 链接** | https://arxiv.org/pdf/2601.06134 | - Network accessline 51
https://arxiv.org/abs/2601.06134 - Network accessline 76
- [arXiv Abstract](https://arxiv.org/abs/2601.06134) - Network accessline 77
- [arXiv HTML](https://arxiv.org/html/2601.06134v1) - Network accessline 78
- [Paperverse Review](https://paperverse.io/paper/eabc5d58-8762-4dc9-aaf3-665057852cb7)
skills/daily-paper-generator/references/keywords.md
- Network accessline 45
`https://arxiv.org/search/?searchtype=all&query=<QUERY>&abstracts=show&order=-announced_date_first` - Network accessline 49
`https://export.arxiv.org/api/query?search_query=all:<QUERY>&start=0&max_results=50&sortBy=submittedDate&sortOrder=descending` - Network accessline 54
`https://api.biorxiv.org/details/biorxiv/<FROM_DATE>/<TO_DATE>/<CURSOR>` - Network accessline 58
`https://api.biorxiv.org/details/biorxiv/2026-01-01/2026-04-23/0`
skills/daily-paper-generator/scripts/arxiv_search.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 55
months: int = 3, ) -> List[Dict]: base_url = "https://export.arxiv.org/api/query?" - Network accessline 57
base_url = "https://export.arxiv.org/api/query?" - Network accessline 78
first_author = authors[0] if authors else "Unknown" arxiv_id = entry.id.split("/abs/")[-1] arxiv_link = f"https://arxiv.org/abs/{arxiv_id}" - Network accessline 79
arxiv_id = entry.id.split("/abs/")[-1] arxiv_link = f"https://arxiv.org/abs/{arxiv_id}" summary = re.sub(r"\s+", " ", entry.summary).strip() - Network accessline 80
arxiv_link = f"https://arxiv.org/abs/{arxiv_id}" - Network accessline 93
"link": arxiv_link, "arxiv_link": arxiv_link, "pdf_link": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 94
"arxiv_link": arxiv_link, "pdf_link": f"https://arxiv.org/pdf/{arxiv_id}.pdf", "categories": [tag.term for tag in getattr(entry, "tags", [])], - Network accessline 95
"pdf_link": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 117
probe_end = end_date - timedelta(days=shift_days) probe_url = ( "https://api.biorxiv.org/details/biorxiv/" - Network accessline 118
probe_url = ( "https://api.biorxiv.org/details/biorxiv/" f"{probe_start.isoformat()}/{probe_end.isoformat()}/0" - Network accessline 119
"https://api.biorxiv.org/details/biorxiv/" - Network accessline 142
window_end = end_date - timedelta(days=shift_days) url = ( "https://api.biorxiv.org/details/biorxiv/" - Network accessline 143
url = ( "https://api.biorxiv.org/details/biorxiv/" f"{window_start.isoformat()}/{window_end.isoformat()}/{cursor}" - Network accessline 144
"https://api.biorxiv.org/details/biorxiv/" - Network accessline 171
version = str(item.get("version", "1")).strip() or "1" if doi: link = f"https://www.biorxiv.org/content/{doi}v{version}" - Network accessline 172
if doi: link = f"https://www.biorxiv.org/content/{doi}v{version}" else: - Network accessline 173
link = f"https://www.biorxiv.org/content/{doi}v{version}"
skills/doc-coauthoring/SKILL.md
skills/frontend-design/LICENSE.txt
skills/git-workflow/SKILL.md
skills/git-workflow/examples/workflow-commands.sh
- Executable scriptline 1
#!/bin/bash
skills/git-workflow/references/advanced-usage.md
- Network accessline 79
# 浅克隆（只获取最近的提交） git clone --depth 1 https://github.com/repo/project.git - Network accessline 80
git clone --depth 1 https://github.com/repo/project.git - Network accessline 82
# 部分克隆（按需获取） git clone --filter=blob:none https://github.com/repo/project.git - Network accessline 83
git clone --filter=blob:none https://github.com/repo/project.git - Network accessline 85
# 稀疏检出（只检出需要的目录） git clone --filter=blob:none --sparse https://github.com/repo/project.git - Network accessline 86
git clone --filter=blob:none --sparse https://github.com/repo/project.git - Access to secretsline 127
[Credential-related source omitted] - Dangerous shell operationline 130
git filter-branch --force --index-filter 'git rm --cached --ignore-unmatch config/secrets.yml' - Dangerous shell operationline 131
'git rm --cached --ignore-unmatch config/secrets.yml' \ - Network accessline 168
git submodule add https://github.com/user/repo.git libs/repo - Network accessline 170
# 克隆包含子模块的项目 git clone --recurse-submodules https://github.com/user/project.git - Network accessline 171
git clone --recurse-submodules https://github.com/user/project.git - Dangerous shell operationline 201
rm -rf .git/modules/libs/repo - Dangerous shell operationline 204
git rm -f libs/repo
skills/git-workflow/references/gitignore-guide.md
skills/hook-development/SKILL.md
skills/hook-development/examples/load-context.sh
- Executable scriptline 1
#!/bin/bash
skills/hook-development/examples/validate-bash.sh
skills/hook-development/examples/validate-write.sh
- Executable scriptline 1
#!/bin/bash
skills/hook-development/references/advanced.md
- Access to secretsline 177
[Credential-related source omitted] - Network accessline 277
# Send notification to Slack curl -X POST "$SLACK_WEBHOOK" \ - Network accessline 278
curl -X POST "$SLACK_WEBHOOK" \ - Network accessline 307
# Send metrics to monitoring system echo "hook.pretooluse.${tool_name}:1|c" | nc -u -w1 statsd.local 8125 - Network accessline 308
echo "hook.pretooluse.${tool_name}:1|c" | nc -u -w1 statsd.local 8125 - Dangerous shell operationline 396
result=$(echo '{"tool_input": {"command": "rm -rf /"}}' | bash validate-bash.sh) - Dangerous shell operationline 426
rm -rf "$CLAUDE_PROJECT_DIR"
skills/hook-development/references/migration.md
- Dangerous shell operationline 42
if [[ "$command" == *"rm -rf"* ]]; then - Dangerous shell operationline 49
- Only checks for exact "rm -rf" pattern - Dangerous shell operationline 50
- Doesn't catch variations like `rm -fr` or `rm -r -f` - Dangerous shell operationline 66
"prompt": "Command: $TOOL_INPUT.command. Analyze for: 1) Destructive operations (rm -rf, dd, mkfs, etc) 2) Privilege escalation (sudo) 3) Network operations without user consent. Return 'approve' or 'deny' with explanation.",
skills/hook-development/references/patterns.md
skills/hook-development/scripts/hook-linter.sh
- Executable scriptline 1
#!/bin/bash
skills/hook-development/scripts/test-hook.sh
skills/hook-development/scripts/validate-hook-schema.sh
- Executable scriptline 1
#!/bin/bash
skills/kaggle-learner/references/knowledge/.archive/nlp.md
- Network accessline 112
### Eedi - Mining Misconceptions in Mathematics (2024) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/eedi-mining-misconceptions-in-mathematics) | [Lessons Learned](https://the-learning-agency.com/the-cutt - Network accessline 113
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/eedi-mining-misconceptions-in-mathematics) | [Lessons Learned](https://the-learning-agency.com/the-cutting-ed/article/lessons-learned-from-hosting-ai-competitions-in-edtec - Network accessline 273
### MAP - Charting Student Math Misunderstandings (2024) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/map-charting-student-math-misunderstandings) | [Case Study](https://the-learning-agency.com/the-cutti - Network accessline 274
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/map-charting-student-math-misunderstandings) | [Case Study](https://the-learning-agency.com/the-cutting-ed/article/case-study-math-misconceptions-competition/) | [MiRAGE P - Network accessline 459
### ARC Prize 2025 (2025) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/arc-prize-2025) | [Official Analysis](https://arcprize.org/blog/arc-prize-2025-results-analysis) - Network accessline 460
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/arc-prize-2025) | [Official Analysis](https://arcprize.org/blog/arc-prize-2025-results-analysis) - Network accessline 564
### AIMO-2 (2025) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2) | [Paper](https://arxiv.org/abs/2504.16891) - Network accessline 565
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2) | [Paper](https://arxiv.org/abs/2504.16891) - Network accessline 1011
基于论文: https://arxiv.org/html/2511.01182v1 - Network accessline 2732
4. 生成 CoT 和 TIR 格式 """ base_url = "https://artofproblemsolving.com" - Network accessline 2734
base_url = "https://artofproblemsolving.com" - Dangerous shell operationline 2906
exec(code, {}) - Network accessline 3497
| Source | Date | Tags | |--------|------|------| | [ARC Prize 2025](https://www.kaggle.com/competitions/arc-prize-2025) | 2025-01-22 | 抽象推理, Refinement Loops, 合成数据, Test-Time Training, TRM, SOAR, CompressARC | - Network accessline 3498
|--------|------|------| | [ARC Prize 2025](https://www.kaggle.com/competitions/arc-prize-2025) | 2025-01-22 | 抽象推理, Refinement Loops, 合成数据, Test-Time Training, TRM, SOAR, CompressARC | | [AI Mathematical Olympiad Progress Prize 2](https:// - Network accessline 3499
| [ARC Prize 2025](https://www.kaggle.com/competitions/arc-prize-2025) | 2025-01-22 | 抽象推理, Refinement Loops, 合成数据, Test-Time Training, TRM, SOAR, CompressARC | - Network accessline 3500
| [AI Mathematical Olympiad Progress Prize 2](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2) | 2025-01-22 | 数学推理, MARIO, 代码执行集成, OpenMathReasoning, GenSelect, 三阶段训练, AoPS | - Network accessline 3501
| [Eedi - Mining Misconceptions in Mathematics](https://www.kaggle.com/competitions/eedi-mining-misconceptions-in-mathematics) | 2024-09 | 教育 AI, 误解检测, 检索+重排, Qwen LLM, Distractor prediction,亲和度预测 | - Network accessline 3502
| [MAP - Charting Student Math Misunderstandings](https://www.kaggle.com/competitions/map-charting-student-math-misunderstandings) | 2025-01-22 | 教育 AI, 误解检测, MiRAGE, Shared-prefix attention, Soft labels, Multi-task learning, CoT distillati
skills/kaggle-learner/references/knowledge/.archive/tabular.md
- Network accessline 8
### CMI - Problematic Internet Use (2024) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/child-mind-institute-problematic-internet-use) - Network accessline 9
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/child-mind-institute-problematic-internet-use) - Network accessline 827
| Source | Date | Tags | |--------|------|------| | [Child Mind Institute - Problematic Internet Use](https://www.kaggle.com/competitions/child-mind-institute-problematic-internet-use) | 2025-01-22 | 表格数据, QWK, Pseudo Labeling, 多Seed平均, GBM - Network accessline 829
| [Child Mind Institute - Problematic Internet Use](https://www.kaggle.com/competitions/child-mind-institute-problematic-internet-use) | 2025-01-22 | 表格数据, QWK, Pseudo Labeling, 多Seed平均, GBM Ensemble, Tweedie Loss |
skills/kaggle-learner/references/knowledge/.archive/time-series.md
- Network accessline 804
**参考资料：** - [1st Place Writeup](https://www.kaggle.com/competitions/birdclef-2024/writeups/team-kefir-1st-place-solution) - Network accessline 805
- [1st Place Writeup](https://www.kaggle.com/competitions/birdclef-2024/writeups/team-kefir-1st-place-solution) - Network accessline 806
- [2nd Place Solution (Japanese)](https://zenn.dev/yuto_mo/articles/85eee84a753159) - Network accessline 807
- [3rd Place GitHub](https://github.com/TheoViel/kaggle_birdclef2024) - Network accessline 808
- [1st Place Explanation (Japanese)](https://zenn.dev/yuto_mo/articles/ad43c630729073) - Network accessline 1170
### HMS - Harmful Brain Activity Classification (2024) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) - Network accessline 1171
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) - Network accessline 1184
### Child Mind Institute - Detect Sleep States (2023) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states) - Network accessline 1185
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states) - Network accessline 1198
**Resources:** - [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/discussion/459715) - Network accessline 1199
- [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/discussion/459715) - Network accessline 1200
- [1st Place GitHub](https://github.com/sakami0000/child-mind-institute-detect-sleep-states-1st-place) - Network accessline 1201
- [Comprehensive Chinese Summary](https://zhuanlan.zhihu.com/p/675470807) - Network accessline 1202
- [Japanese Presentation](https://speakerdeck.com/unonao/shui-mian-konpe-1st-place-solution) - Network accessline 1204
### CMI - Detect Behavior with Sensor Data (2025) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data) - Network accessline 1205
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data) - Network accessline 1219
**Resources:** - [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data/writeups/cmi-1st-place-solution) - Network accessline 1220
- [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data/writeups/cmi-1st-place-solution) - Network accessline 1221
- [Japanese Summary](https://zenn.dev/ottantachinque/articles/2025-09-14_cmi-detect-behavior-with-sensor-data) - Network accessline 1222
- [Chinese EDA](https://zhuanlan.zhihu.com/p/1943779452640273827) - Network accessline 1224
### BirdCLEF 2024 - Bird Sound Identification (2024) - 2026-01-23 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/birdclef-2024) - Network accessline 1225
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/birdclef-2024) - Network accessline 1240
**Resources:** - [1st Place Writeup](https://www.kaggle.com/competitions/birdclef-2024/writeups/team-kefir-1st-place-solution) - Network accessline 1241
- [1st Place Writeup](https://www.kaggle.com/competitions/birdclef-2024/writeups/team-kefir-1st-place-solution) - Network accessline 1242
- [2nd Place Solution (Japanese)](https://zenn.dev/yuto_mo/articles/85eee84a753159) - Network accessline 1243
- [3rd Place GitHub](https://github.com/TheoViel/kaggle_birdclef2024) - Network accessline 1244
- [1st Place Explanation (Japanese)](https://zenn.dev/yuto_mo/articles/ad43c630729073) - Network accessline 1246
### BirdCLEF+ 2025 - Multi-Taxonomic Sound Identification (2025) - 2026-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/birdclef-2025) | [知乎 14个高分方案](https://zhuanlan.zhihu.com/p/1920582942931019095) - Network accessline 1247
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/birdclef-2025) | [知乎 14个高分方案](https://zhuanlan.zhihu.com/p/1920582942931019095) - Network accessline 1262
**Resources:** - [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/birdclef-2025/discussion/583577) - Network accessline 1263
- [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/birdclef-2025/discussion/583577) - Network accessline 1264
- [2nd Place Solution](https://www.kaggle.com/competitions/birdclef-2025/discussion/583699) - Network accessline 1265
- [5th Place Solution](https://www.kaggle.com/competitions/birdclef-2025/discussion/583312) - Network accessline 1266
- [Chinese Summary - 14 Solutions](https://zhuanlan.zhihu.com/p/1920582942931019095) - Network accessline 1514
# Superlet Transform - 比STFT更高的时间/频率分辨率 # 参考: https://github.com/antoninlff/superlet - Network accessline 1515
# 参考: https://github.com/antoninlff/superlet - Network accessline 7233
**代码仓库**：[GillesVandewiele/google-brain-ventilator](https://github.com/GillesVandewiele/google-brain-ventilator) - Network accessline 7286
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/ambrosm-2-solution-the-inverse-of-a-pid-controller) - Network accessline 7357
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/upstage-making-ai-beneficial-3rd-place-single-mode) - Network accessline 7410
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/jun-koda-4th-place-solution-hacking-the-pid-contro) - Network accessline 7473
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/0-0ggg-6th-place-solution-single-multi-task-lstm) - Network accessline 7509
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/pksha-no-pressure-14th-place-solution-multitask-ls) - Network accessline 7535
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/player2-has-flatlined-16th-place-journey-writeup-n) - Network accessline 7572
**参考文章**：[Blog Post](https://kozistr.tech/2021-11-03-ventilator-pressure-prediction/) - Network accessline 7574
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/hyeongchan-nikita-20th-place-solution-model-multi-) - Network accessline 8099
| Source | Date | Tags | |--------|------|------| | [HMS - Harmful Brain Activity Classification](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) | 2025-01-22 | EEG, 分类, CWT, Entmax, 2-Stage Training, KL-Diver - Network accessline 8100
|--------|------|------| | [HMS - Harmful Brain Activity Classification](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) | 2025-01-22 | EEG, 分类, CWT, Entmax, 2-Stage Training, KL-Divergence | | [Child Mind Ins - Network accessline 8101
| [HMS - Harmful Brain Activity Classification](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) | 2025-01-22 | EEG, 分类, CWT, Entmax, 2-Stage Training, KL-Divergence | - Network accessline 8102
| [Child Mind Institute - Detect Sleep States](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states) | 2025-01-22 | 睡眠检测, 事件检测, 两阶段建模, 后处理优化, 多tolerance AP | - Network accessline 8103
| [Child Mind Institute - Detect Behavior with Sensor Data](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data) | 2025-01-22 | 多模态时序, IMU+TOF+THM, 行为识别, 阶段感知Attention, 匈牙利算法 | - Network accessline 8104
| [BirdCLEF 2024](https://www.kaggle.com/competitions/birdclef-2024) | 2026-01-23 | 音频分类, 生物声学, Statistics T过滤, Google Classifier预标注, CE Loss, Sigmoid推理, Min Ensemble, Checkpoint Soup, 伪标签迭代, 120分钟推理限制 | - Network accessline 8105
| [BirdCLEF+ 2025](https://www.kaggle.com/competitions/birdclef-2025) | 2026-01-22 | 音频分类, 生物声学, Noisy Student, 自蒸馏, SED模型, 伪标签, Mel-Spectrogram, Soft AUC Loss, 90分钟推理限制 | - Network accessline 8106
| [Google Brain - Ventilator Pressure Prediction](https://www.kaggle.com/c/ventilator-pressure-prediction) | 2026-01-23 | 时序回归, PID逆向, 多任务学习, Delta Pressure, LSTM+Transformer, MAE, 2,605队伍 | - Network accessline 8107
| [Cornell Birdcall Identification (BirdCLEF 2020)](https://www.kaggle.com/competitions/birdsong-recognition) | 2026-01-23 | 音频分类, 生物声学, ResNeSt, Attention Pooling, Mel-Spectrogram, Weak Supervision, GAN伪标签, Ensemble, F1-Score, 1,390队伍 | - Network accessline 8108
| [BirdCLEF 2021 - Birdcall Identification](https://www.kaggle.com/competitions/birdclef-2021) | 2026-01-23 | 音频分类, 生物声学, PANNs, 弱监督, Mixup, SpecAugment, Attention Mechanism, F1-Score, 1,700队伍 | - Network accessline 8109
| [BirdCLEF 2022 - Endangered Bird Sounds](https://www.kaggle.com/competitions/birdclef-2022) | 2026-01-23 | 音频分类, 濒危物种, BirdNet, Perch, SED, 多尺度输入, AND规则, Framewise预测, F1-Score, 1,600队伍 | - Network accessline 8110
| [Rainforest Connection Species Audio Detection 2021](https://www.kaggle.com/competitions/rfcx-species-audio-detection) | 2026-01-23 | 音频检测, 生物声学, LWLRAP, Mel-Spectrogram as Image, ResNeSt, EfficientNet, ImageNet预训练, 2,200队伍 | - Network accessline 8111
| [AMP®-Parkinson's Disease Progression Prediction](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction) | 2026-01-23 | 表格时序回归, 蛋白质数据, Gradient Boosting, SMAPE, XGBoost/LightGBM, 2,500队伍 | - Network accessline 8927
""" 基于 PANNs CNN14 的模型 参考: https://github.com/qiuqiangkong/audioset_tagging_cnn - Network accessline 8928
基于 PANNs CNN14 的模型 参考: https://github.com/qiuqiangkong/audioset_tagging_cnn """ - Network accessline 8929
参考: https://github.com/qiuqiangkong/audioset_tagging_cnn - Network accessline 10223
实际使用时需要从官方仓库获取模型 参考: https://github.com/BirdVox/birdnet-library - Network accessline 10224
参考: https://github.com/BirdVox/birdnet-library
skills/kaggle-learner/references/knowledge/nlp/aimo-2-2025.md
- Network accessline 6
### AIMO-2 (2025) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2) | [Paper](https://arxiv.org/abs/2504.16891) - Network accessline 7
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2) | [Paper](https://arxiv.org/abs/2504.16891) - Network accessline 626
4. 生成 CoT 和 TIR 格式 """ base_url = "https://artofproblemsolving.com" - Network accessline 628
base_url = "https://artofproblemsolving.com" - Dangerous shell operationline 800
exec(code, {}) - Network accessline 1217
| Source | Date | Tags | |--------|------|------| | [ARC Prize 2025](https://www.kaggle.com/competitions/arc-prize-2025) | 2025-01-22 | 抽象推理, Refinement Loops, 合成数据, Test-Time Training, TRM, SOAR, CompressARC | - Network accessline 1218
|--------|------|------| | [ARC Prize 2025](https://www.kaggle.com/competitions/arc-prize-2025) | 2025-01-22 | 抽象推理, Refinement Loops, 合成数据, Test-Time Training, TRM, SOAR, CompressARC | | [AI Mathematical Olympiad Progress Prize 2](https:// - Network accessline 1219
| [ARC Prize 2025](https://www.kaggle.com/competitions/arc-prize-2025) | 2025-01-22 | 抽象推理, Refinement Loops, 合成数据, Test-Time Training, TRM, SOAR, CompressARC | - Network accessline 1220
| [AI Mathematical Olympiad Progress Prize 2](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2) | 2025-01-22 | 数学推理, MARIO, 代码执行集成, OpenMathReasoning, GenSelect, 三阶段训练, AoPS | - Network accessline 1221
| [Eedi - Mining Misconceptions in Mathematics](https://www.kaggle.com/competitions/eedi-mining-misconceptions-in-mathematics) | 2024-09 | 教育 AI, 误解检测, 检索+重排, Qwen LLM, Distractor prediction,亲和度预测 | - Network accessline 1222
| [MAP - Charting Student Math Misunderstandings](https://www.kaggle.com/competitions/map-charting-student-math-misunderstandings) | 2025-01-22 | 教育 AI, 误解检测, MiRAGE, Shared-prefix attention, Soft labels, Multi-task learning, CoT distillati
skills/kaggle-learner/references/knowledge/nlp/arc-prize-2025.md
- Network accessline 6
### ARC Prize 2025 (2025) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/arc-prize-2025) | [Official Analysis](https://arcprize.org/blog/arc-prize-2025-results-analysis) - Network accessline 7
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/arc-prize-2025) | [Official Analysis](https://arcprize.org/blog/arc-prize-2025-results-analysis) - Network accessline 182
基于论文: https://arxiv.org/html/2511.01182v1
skills/kaggle-learner/references/knowledge/nlp/eedi-2024.md
- Network accessline 55
### Eedi - Mining Misconceptions in Mathematics (2024) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/eedi-mining-misconceptions-in-mathematics) | [Lessons Learned](https://the-learning-agency.com/the-cutt - Network accessline 56
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/eedi-mining-misconceptions-in-mathematics) | [Lessons Learned](https://the-learning-agency.com/the-cutting-ed/article/lessons-learned-from-hosting-ai-competitions-in-edtec
skills/kaggle-learner/references/knowledge/nlp/konwinski-prize-2025-6th-place-study.md
- Network accessline 3
> 基于 quan16369 的开源解决方案 > GitHub: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - Network accessline 4
> GitHub: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - Network accessline 370
### GitHub 仓库 - **6th Place Solution**: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - Network accessline 371
- **6th Place Solution**: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - Network accessline 373
### Kaggle 竞赛 - **竞赛主页**: https://www.kaggle.com/competitions/konwinski-prize - Network accessline 374
- **竞赛主页**: https://www.kaggle.com/competitions/konwinski-prize - Network accessline 375
- **官方网站**: https://kprize.ai - Network accessline 377
### 策略指南 - **Strategy Guide**: https://github.com/raymyers/konwinski-prize-strategy-guide - Network accessline 378
- **Strategy Guide**: https://github.com/raymyers/konwinski-prize-strategy-guide - Network accessline 380
### 相关基准测试 - **SWE-bench**: https://www.swebench.com/ - Network accessline 381
- **SWE-bench**: https://www.swebench.com/
skills/kaggle-learner/references/knowledge/nlp/konwinski-prize-2025-comparison.md
- Network accessline 1333
**参考来源**: - Kaggle Konwinski Prize 竞赛页面 - 6th Place 开源代码: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - Network accessline 1334
- Kaggle Konwinski Prize 竞赛页面 - 6th Place 开源代码: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - 策略指南: https://github.com/raymyers/konwinski-prize-strategy-guide - Network accessline 1335
- 6th Place 开源代码: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - Network accessline 1336
- 策略指南: https://github.com/raymyers/konwinski-prize-strategy-guide - Network accessline 1337
- SWE-bench: https://www.swebench.com/
skills/kaggle-learner/references/knowledge/nlp/konwinski-prize-2025.md
- Network accessline 3
> **Competition URL**: https://www.kaggle.com/competitions/konwinski-prize - Network accessline 4
> > **Official Website**: https://kprize.ai > - Network accessline 5
> **Official Website**: https://kprize.ai - Network accessline 622
### Official Resources - **Competition Page**: https://www.kaggle.com/competitions/konwinski-prize - Network accessline 623
- **Competition Page**: https://www.kaggle.com/competitions/konwinski-prize - Network accessline 624
- **Official Website**: https://kprize.ai - Network accessline 625
- **Strategy Guide**: https://github.com/raymyers/konwinski-prize-strategy-guide - Network accessline 631
- **4th Place**: "Select-Patch-Verify-Test" - **5th Place**: Regex traceback analysis - **6th Place**: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - Network accessline 633
- **6th Place**: https://github.com/quan16369/Kaggle-Konwinski-Prize-6th-Place-Solution- - Network accessline 635
### Related Benchmarks - **SWE-bench**: https://www.swebench.com/ - Network accessline 636
- **SWE-bench**: https://www.swebench.com/ - Network accessline 637
- **SWE-bench Verified**: https://www.swebench.com/verified - Network accessline 638
- **SWE-agent**: https://github.com/princeton-nlp/SWE-agent
skills/kaggle-learner/references/knowledge/nlp/map-2024.md
- Network accessline 61
### MAP - Charting Student Math Misunderstandings (2024) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/map-charting-student-math-misunderstandings) | [Case Study](https://the-learning-agency.com/the-cutti - Network accessline 62
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/map-charting-student-math-misunderstandings) | [Case Study](https://the-learning-agency.com/the-cutting-ed/article/case-study-math-misconceptions-competition/) | [MiRAGE P
skills/kaggle-learner/references/knowledge/tabular/amp-parkinsons-2021.md
- Network accessline 570
### Official Writeups - [1st Place Solution - Connecting Dotts](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/connecting-dotts-1st-place-solution) - Network accessline 571
- [1st Place Solution - Connecting Dotts](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/connecting-dotts-1st-place-solution) - Network accessline 572
- [2nd Place Solution - No Luck, All Skill](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/no-luck-all-skill-2nd-place-solution) - Network accessline 573
- [3rd Place Solution - Hajime Tamura](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/hajime-tamura-3rd-place-solution) - Network accessline 574
- [5th Place Solution - Ambrosm](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/ambrosm-5-find-the-control-group) - Network accessline 575
- [9th Place Solution - Makotu](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/makotu-9th-place-solution) - Network accessline 576
- [13th Place Solution - FNOA](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/fnoa-13th-place-solution) - Network accessline 577
- [43rd Place Solution - Wojciech Victor Fulmyk](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/wojciech-victor-fulmyk-43rd-top-3-silver-medal-sol) - Network accessline 578
- [89th Place Solution - Giba (Non-Leaky)](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/writeups/giba-top-89-non-leaky-solution) - Network accessline 580
### External Resources - [H2O.ai Blog: Navigating the Parkinson's Disease Prediction Challenge with AI](https://h2o.ai/blog/2023/winners-insight-navigating-the-parkinsons-disease-prediction-challenge-with-ai/) - Network accessline 581
- [H2O.ai Blog: Navigating the Parkinson's Disease Prediction Challenge with AI](https://h2o.ai/blog/2023/winners-insight-navigating-the-parkinsons-disease-prediction-challenge-with-ai/) - Network accessline 582
- [中文复现: 小样本比赛也能有稳定区分度](https://zhuanlan.zhihu.com/p/669527953) - Network accessline 584
### Competition Pages - [Main Competition Page](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction) - Network accessline 585
- [Main Competition Page](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction) - Network accessline 586
- [Data Description](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction/data) - Network accessline 587
- [Discussion Forum](https://www.kaggle.com/c/amp-parkinsons-disease-progression-prediction/discussion) - Network accessline 589
### Code Notebooks - [LightGBM Starter with Added Features](https://www.kaggle.com/code/sijovm/lightgbm-starter-with-added-features) - Network accessline 590
- [LightGBM Starter with Added Features](https://www.kaggle.com/code/sijovm/lightgbm-starter-with-added-features) - Network accessline 591
- [XGB Baseline with Added Features](https://www.kaggle.com/code/sijovm/xgb-baseline-with-added-features) - Network accessline 592
- [AMP® - PDPP EDA + TF Model](https://www.kaggle.com/code/callmewenhao/amp-pdpp-eda-tf-model) - Network accessline 593
- [AMP® - PDPP EDA](https://www.kaggle.com/code/gunesevitan/amp-pdpp-eda)
skills/kaggle-learner/references/knowledge/time-series/birdclef-2023.md
- Network accessline 133
**代码仓库**： - GitHub: [VSydorskyy/BirdCLEF_2023_1st_place](https://github.com/VSydorskyy/BirdCLEF_2023_1st_place) - Network accessline 134
- GitHub: [VSydorskyy/BirdCLEF_2023_1st_place](https://github.com/VSydorskyy/BirdCLEF_2023_1st_place) - Network accessline 135
- Kaggle Writeup: [1st place solution: Correct Data is All You Need](https://www.kaggle.com/competitions/birdclef-2023/writeups/volodymyr-1st-place-solution-correct-data-is-all-y) - Network accessline 179
**代码仓库**： - GitHub: [LIHANG-HONG/birdclef2023-2nd-place-solution](https://github.com/LIHANG-HONG/birdclef2023-2nd-place-solution) - Network accessline 180
- GitHub: [LIHANG-HONG/birdclef2023-2nd-place-solution](https://github.com/LIHANG-HONG/birdclef2023-2nd-place-solution) - Network accessline 181
- Kaggle Writeup: [2nd place solution: SED + CNN with 7 models ensemble](https://www.kaggle.com/competitions/birdclef-2023/writeups/griffith-2nd-place-solution-sed-cnn-with-7-models-) - Network accessline 224
**代码仓库**： - Kaggle Writeup: [3rd place solution: SED with attention on Mel frequency bands](https://www.kaggle.com/competitions/birdclef-2023/writeups/adsr-3rd-place-solution-sed-with-attention-on-mel-) - Network accessline 225
- Kaggle Writeup: [3rd place solution: SED with attention on Mel frequency bands](https://www.kaggle.com/competitions/birdclef-2023/writeups/adsr-3rd-place-solution-sed-with-attention-on-mel-) - Network accessline 269
**代码仓库**： - GitHub: [AtsunoriFujita/BirdCLEF-2023-Identify-bird-calls-in-soundscapes](https://github.com/AtsunoriFujita/BirdCLEF-2023-Identify-bird-calls-in-soundscapes) - Network accessline 270
- GitHub: [AtsunoriFujita/BirdCLEF-2023-Identify-bird-calls-in-soundscapes](https://github.com/AtsunoriFujita/BirdCLEF-2023-Identify-bird-calls-in-soundscapes) - Network accessline 271
- Kaggle Writeup: [4th Place Solution: Knowledge Distillation Is All You Need](https://www.kaggle.com/competitions/birdclef-2023/writeups/atfujita-4th-place-solution-knowledge-distillation) - Network accessline 321
**代码仓库**： - GitHub: [yevmaslov](https://github.com/yevmaslov) - Network accessline 322
- GitHub: [yevmaslov](https://github.com/yevmaslov) - Network accessline 323
- Kaggle Writeup: [5th place solution](https://www.kaggle.com/competitions/birdclef-2023/writeups/yevhenii-maslov-5th-place-solution) - Network accessline 359
**代码仓库**： - Kaggle Writeup: [8th Place Solution: Implementing Multimodal Data Augmentation Methods](https://www.kaggle.com/competitions/birdclef-2023/writeups/furu-nag-8th-place-solution-implementing-multimoda) - Network accessline 360
- Kaggle Writeup: [8th Place Solution: Implementing Multimodal Data Augmentation Methods](https://www.kaggle.com/competitions/birdclef-2023/writeups/furu-nag-8th-place-solution-implementing-multimoda) - Network accessline 382
**代码仓库**： - Kaggle Writeup: [18th place solution: SED with attention](https://www.kaggle.com/competitions/birdclef-2023/writeups/18th-place-solution-sed-with-attention) - Network accessline 383
- Kaggle Writeup: [18th place solution: SED with attention](https://www.kaggle.com/competitions/birdclef-2023/writeups/18th-place-solution-sed-with-attention) - Network accessline 1806
1. **[1st place solution: Correct Data is All You Need](https://www.kaggle.com/competitions/birdclef-2023/writeups/volodymyr-1st-place-solution-correct-data-is-all-y)** - Volodymyr Sydorskyi - Network accessline 1807
2. **[2nd place solution: SED + CNN with 7 models ensemble](https://www.kaggle.com/competitions/birdclef-2023/writeups/griffith-2nd-place-solution-sed-cnn-with-7-models-)** - Griffith - Network accessline 1808
3. **[3rd place solution: SED with attention on Mel frequency bands](https://www.kaggle.com/competitions/birdclef-2023/writeups/adsr-3rd-place-solution-sed-with-attention-on-mel-)** - ADSR - Network accessline 1809
4. **[4th Place Solution: Knowledge Distillation Is All You Need](https://www.kaggle.com/competitions/birdclef-2023/writeups/atfujita-4th-place-solution-knowledge-distillation)** - ATFujita - Network accessline 1810
5. **[5th place solution](https://www.kaggle.com/competitions/birdclef-2023/writeups/yevhenii-maslov-5th-place-solution)** - Yevhenii Maslov - Network accessline 1811
6. **[8th Place Solution: Implementing Multimodal Data Augmentation Methods](https://www.kaggle.com/competitions/birdclef-2023/writeups/furu-nag-8th-place-solution-implementing-multimoda)** - FURU-NAG - Network accessline 1812
7. **[18th place solution: SED with attention](https://www.kaggle.com/competitions/birdclef-2023/writeups/18th-place-solution-sed-with-attention)** - Network accessline 1816
1. **[VSydorskyy/BirdCLEF_2023_1st_place](https://github.com/VSydorskyy/BirdCLEF_2023_1st_place)** - 1st Place 代码 - Network accessline 1817
2. **[LIHANG-HONG/birdclef2023-2nd-place-solution](https://github.com/LIHANG-HONG/birdclef2023-2nd-place-solution)** - 2nd Place 代码 - Network accessline 1818
3. **[AtsunoriFujita/BirdCLEF-2023-Identify-bird-calls-in-soundscapes](https://github.com/AtsunoriFujita/BirdCLEF-2023-Identify-bird-calls-in-soundscapes)** - 4th Place 代码 - Network accessline 1819
4. **[yevmaslov](https://github.com/yevmaslov)** - 5th Place 代码 - Network accessline 1823
1. **[Overview of BirdCLEF 2023: Automated Bird Species Identification in Eastern Africa](https://hal.science/hal-05182512/document)** - 竞赛概述 - Network accessline 1824
2. **[Acoustic Bird Species Recognition at BirdCLEF 2023](https://ceur-ws.org/Vol-3497/paper-172.pdf)** - 2nd Place 学术论文 - Network accessline 1825
3. **[Bird Species Recognition using Convolutional Neural Networks with Attention on Frequency Bands](https://www.researchgate.net/publication/389264675_Bird_Species_Recognition_using_Convolutional_Neural_Networks_with_Attention_on_Frequenc - Network accessline 1829
1. **[(Kaggle) BirdCLEF 2023 - 24th (top 2%) place solution](https://kozistr.tech/2023-05-26-birdcelf-2023/)** - 24th Place 详细方案 - Network accessline 1830
2. **[763rd Place Solution for the BirdCLEF 2023 Competition](https://www.kaggle.com/competitions/birdclef-2023/discussion/451041)** - 讨论帖 - Network accessline 1834
1. **[Leaderboard - BirdCLEF 2023](https://www.kaggle.com/competitions/birdclef-2023/leaderboard)** - 最终排行榜 - Network accessline 1835
2. **[BirdCLEF 2023 Competition Page](https://www.kaggle.com/competitions/birdclef-2023)** - 竞赛主页 - Network accessline 1836
3. **[Xeno-canto Extended Metadata for BirdCLEF2023](https://www.kaggle.com/datasets/mariotsaberlin/xeno-canto-extended-metadata-for-birdclef2023)** - Xeno-Canto 扩展数据集
skills/kaggle-learner/references/knowledge/time-series/birdclef-2024.md
- Network accessline 156
**参考资料：** - [1st Place Writeup](https://www.kaggle.com/competitions/birdclef-2024/writeups/team-kefir-1st-place-solution) - Network accessline 157
- [1st Place Writeup](https://www.kaggle.com/competitions/birdclef-2024/writeups/team-kefir-1st-place-solution) - Network accessline 158
- [2nd Place Solution (Japanese)](https://zenn.dev/yuto_mo/articles/85eee84a753159) - Network accessline 159
- [3rd Place GitHub](https://github.com/TheoViel/kaggle_birdclef2024) - Network accessline 160
- [1st Place Explanation (Japanese)](https://zenn.dev/yuto_mo/articles/ad43c630729073) - Network accessline 522
### BirdCLEF 2024 - Bird Sound Identification (2024) - 2026-01-23 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/birdclef-2024) - Network accessline 523
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/birdclef-2024) - Network accessline 538
**Resources:** - [1st Place Writeup](https://www.kaggle.com/competitions/birdclef-2024/writeups/team-kefir-1st-place-solution) - Network accessline 539
- [1st Place Writeup](https://www.kaggle.com/competitions/birdclef-2024/writeups/team-kefir-1st-place-solution) - Network accessline 540
- [2nd Place Solution (Japanese)](https://zenn.dev/yuto_mo/articles/85eee84a753159) - Network accessline 541
- [3rd Place GitHub](https://github.com/TheoViel/kaggle_birdclef2024) - Network accessline 542
- [1st Place Explanation (Japanese)](https://zenn.dev/yuto_mo/articles/ad43c630729073) - Network accessline 544
### BirdCLEF+ 2025 - Multi-Taxonomic Sound Identification (2025) - 2026-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/birdclef-2025) | [知乎 14个高分方案](https://zhuanlan.zhihu.com/p/1920582942931019095) - Network accessline 545
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/birdclef-2025) | [知乎 14个高分方案](https://zhuanlan.zhihu.com/p/1920582942931019095) - Network accessline 560
**Resources:** - [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/birdclef-2025/discussion/583577) - Network accessline 561
- [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/birdclef-2025/discussion/583577) - Network accessline 562
- [2nd Place Solution](https://www.kaggle.com/competitions/birdclef-2025/discussion/583699) - Network accessline 563
- [5th Place Solution](https://www.kaggle.com/competitions/birdclef-2025/discussion/583312) - Network accessline 564
- [Chinese Summary - 14 Solutions](https://zhuanlan.zhihu.com/p/1920582942931019095) - Network accessline 1653
**代码仓库**：[GillesVandewiele/google-brain-ventilator](https://github.com/GillesVandewiele/google-brain-ventilator) - Network accessline 1706
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/ambrosm-2-solution-the-inverse-of-a-pid-controller) - Network accessline 1777
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/upstage-making-ai-beneficial-3rd-place-single-mode) - Network accessline 1830
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/jun-koda-4th-place-solution-hacking-the-pid-contro) - Network accessline 1893
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/0-0ggg-6th-place-solution-single-multi-task-lstm) - Network accessline 1929
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/pksha-no-pressure-14th-place-solution-multitask-ls) - Network accessline 1955
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/player2-has-flatlined-16th-place-journey-writeup-n) - Network accessline 1992
**参考文章**：[Blog Post](https://kozistr.tech/2021-11-03-ventilator-pressure-prediction/) - Network accessline 1994
**Writeup**：[Kaggle Writeup](https://www.kaggle.com/competitions/ventilator-pressure-prediction/writeups/hyeongchan-nikita-20th-place-solution-model-multi-) - Network accessline 2519
| Source | Date | Tags | |--------|------|------| | [HMS - Harmful Brain Activity Classification](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) | 2025-01-22 | EEG, 分类, CWT, Entmax, 2-Stage Training, KL-Diver - Network accessline 2520
|--------|------|------| | [HMS - Harmful Brain Activity Classification](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) | 2025-01-22 | EEG, 分类, CWT, Entmax, 2-Stage Training, KL-Divergence | | [Child Mind Ins - Network accessline 2521
| [HMS - Harmful Brain Activity Classification](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) | 2025-01-22 | EEG, 分类, CWT, Entmax, 2-Stage Training, KL-Divergence | - Network accessline 2522
| [Child Mind Institute - Detect Sleep States](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states) | 2025-01-22 | 睡眠检测, 事件检测, 两阶段建模, 后处理优化, 多tolerance AP | - Network accessline 2523
| [Child Mind Institute - Detect Behavior with Sensor Data](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data) | 2025-01-22 | 多模态时序, IMU+TOF+THM, 行为识别, 阶段感知Attention, 匈牙利算法 | - Network accessline 2524
| [BirdCLEF 2024](https://www.kaggle.com/competitions/birdclef-2024) | 2026-01-23 | 音频分类, 生物声学, Statistics T过滤, Google Classifier预标注, CE Loss, Sigmoid推理, Min Ensemble, Checkpoint Soup, 伪标签迭代, 120分钟推理限制 | - Network accessline 2525
| [BirdCLEF+ 2025](https://www.kaggle.com/competitions/birdclef-2025) | 2026-01-22 | 音频分类, 生物声学, Noisy Student, 自蒸馏, SED模型, 伪标签, Mel-Spectrogram, Soft AUC Loss, 90分钟推理限制 | - Network accessline 2526
| [Google Brain - Ventilator Pressure Prediction](https://www.kaggle.com/c/ventilator-pressure-prediction) | 2026-01-23 | 时序回归, PID逆向, 多任务学习, Delta Pressure, LSTM+Transformer, MAE, 2,605队伍 | - Network accessline 2527
| [Cornell Birdcall Identification (BirdCLEF 2020)](https://www.kaggle.com/competitions/birdsong-recognition) | 2026-01-23 | 音频分类, 生物声学, ResNeSt, Attention Pooling, Mel-Spectrogram, Weak Supervision, GAN伪标签, Ensemble, F1-Score, 1,390队伍 | - Network accessline 2528
| [BirdCLEF 2021 - Birdcall Identification](https://www.kaggle.com/competitions/birdclef-2021) | 2026-01-23 | 音频分类, 生物声学, PANNs, 弱监督, Mixup, SpecAugment, Attention Mechanism, F1-Score, 1,700队伍 | - Network accessline 2529
| [BirdCLEF 2022 - Endangered Bird Sounds](https://www.kaggle.com/competitions/birdclef-2022) | 2026-01-23 | 音频分类, 濒危物种, BirdNet, Perch, SED, 多尺度输入, AND规则, Framewise预测, F1-Score, 1,600队伍 | - Network accessline 2530
| [Rainforest Connection Species Audio Detection 2021](https://www.kaggle.com/competitions/rfcx-species-audio-detection) | 2026-01-23 | 音频检测, 生物声学, LWLRAP, Mel-Spectrogram as Image, ResNeSt, EfficientNet, ImageNet预训练, 2,200队伍 | - Network accessline 2531
| [AMP®-Parkinson's Disease Progression Prediction](https://www.kaggle.com/competitions/amp-parkinsons-disease-progression-prediction) | 2026-01-23 | 表格时序回归, 蛋白质数据, Gradient Boosting, SMAPE, XGBoost/LightGBM, 2,500队伍 | - Network accessline 3347
""" 基于 PANNs CNN14 的模型 参考: https://github.com/qiuqiangkong/audioset_tagging_cnn - Network accessline 3348
基于 PANNs CNN14 的模型 参考: https://github.com/qiuqiangkong/audioset_tagging_cnn """ - Network accessline 3349
参考: https://github.com/qiuqiangkong/audioset_tagging_cnn - Network accessline 4643
实际使用时需要从官方仓库获取模型 参考: https://github.com/BirdVox/birdnet-library - Network accessline 4644
参考: https://github.com/BirdVox/birdnet-library
skills/kaggle-learner/references/knowledge/time-series/detect-behavior-sensor-2025.md
- Network accessline 230
### CMI - Detect Behavior with Sensor Data (2025) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data) - Network accessline 231
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data) - Network accessline 245
**Resources:** - [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data/writeups/cmi-1st-place-solution) - Network accessline 246
- [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/cmi-detect-behavior-with-sensor-data/writeups/cmi-1st-place-solution) - Network accessline 247
- [Japanese Summary](https://zenn.dev/ottantachinque/articles/2025-09-14_cmi-detect-behavior-with-sensor-data) - Network accessline 248
- [Chinese EDA](https://zhuanlan.zhihu.com/p/1943779452640273827)
skills/kaggle-learner/references/knowledge/time-series/detect-sleep-states-2023.md
- Network accessline 214
### Child Mind Institute - Detect Sleep States (2023) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states) - Network accessline 215
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states) - Network accessline 228
**Resources:** - [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/discussion/459715) - Network accessline 229
- [1st Place Solution (Kaggle)](https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/discussion/459715) - Network accessline 230
- [1st Place GitHub](https://github.com/sakami0000/child-mind-institute-detect-sleep-states-1st-place) - Network accessline 231
- [Comprehensive Chinese Summary](https://zhuanlan.zhihu.com/p/675470807) - Network accessline 232
- [Japanese Presentation](https://speakerdeck.com/unonao/shui-mian-konpe-1st-place-solution)
skills/kaggle-learner/references/knowledge/time-series/hms-2024.md
- Network accessline 218
### HMS - Harmful Brain Activity Classification (2024) - 2025-01-22 **Source:** [Kaggle Competition](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) - Network accessline 219
**Source:** [Kaggle Competition](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification) - Network accessline 474
# Superlet Transform - 比STFT更高的时间/频率分辨率 # 参考: https://github.com/antoninlff/superlet - Network accessline 475
# 参考: https://github.com/antoninlff/superlet
skills/latex-conference-template-organizer/SKILL.md
skills/mcp-integration/SKILL.md
- Network accessline 102
"asana": { "type": "sse", "url": "https://mcp.asana.com/sse" - Network accessline 103
"type": "sse", "url": "https://mcp.asana.com/sse" } - Network accessline 104
"url": "https://mcp.asana.com/sse" - Network accessline 127
"api-service": { "type": "http", "url": "https://api.example.com/mcp", - Network accessline 128
"type": "http", "url": "https://api.example.com/mcp", "headers": { - Network accessline 129
"url": "https://api.example.com/mcp", - Access to secretsline 131
[Credential-related source omitted] - Access to secretsline 182
[Credential-related source omitted] - Network accessline 248
{ "type": "sse", "url": "https://mcp.example.com/sse" - Network accessline 249
"type": "sse", "url": "https://mcp.example.com/sse" } - Network accessline 250
"url": "https://mcp.example.com/sse" - Network accessline 261
{ "type": "http", "url": "https://api.example.com", - Network accessline 262
"type": "http", "url": "https://api.example.com", "headers": { - Network accessline 263
"url": "https://api.example.com", - Access to secretsline 265
[Credential-related source omitted] - Access to secretsline 282
[Credential-related source omitted] - Network accessline 329
"github": { "type": "sse", "url": "https://mcp.github.com/sse" - Network accessline 330
"type": "sse", "url": "https://mcp.github.com/sse" }, - Network accessline 331
"url": "https://mcp.github.com/sse" - Network accessline 333
"jira": { "type": "sse", "url": "https://mcp.jira.com/sse" - Network accessline 334
"type": "sse", "url": "https://mcp.jira.com/sse" } - Network accessline 335
"url": "https://mcp.jira.com/sse" - Network accessline 349
✅ "url": "https://mcp.example.com/sse" - Network accessline 350
❌ "url": "http://mcp.example.com/sse" - Network accessline 535
- **Official MCP Docs**: https://modelcontextprotocol.io/ - Network accessline 536
- **Claude Code MCP Docs**: https://docs.claude.com/en/docs/claude-code/mcp
skills/mcp-integration/examples/http-server.json
- Network accessline 3
"rest-api": { "type": "http", "url": "https://api.example.com/mcp", - Network accessline 4
"type": "http", "url": "https://api.example.com/mcp", "headers": { - Network accessline 5
"url": "https://api.example.com/mcp", - Access to secretsline 7
[Credential-related source omitted] - Network accessline 12
"internal-service": { "type": "http", "url": "https://api.example.com/mcp", - Network accessline 13
"type": "http", "url": "https://api.example.com/mcp", "headers": { - Network accessline 14
"url": "https://api.example.com/mcp", - Access to secretsline 16
[Credential-related source omitted]
skills/mcp-integration/examples/sse-server.json
- Network accessline 3
"asana": { "type": "sse", "url": "https://mcp.asana.com/sse" - Network accessline 4
"type": "sse", "url": "https://mcp.asana.com/sse" }, - Network accessline 5
"url": "https://mcp.asana.com/sse" - Network accessline 7
"github": { "type": "sse", "url": "https://mcp.github.com/sse" - Network accessline 8
"type": "sse", "url": "https://mcp.github.com/sse" }, - Network accessline 9
"url": "https://mcp.github.com/sse" - Network accessline 11
"custom-service": { "type": "sse", "url": "https://mcp.example.com/sse", - Network accessline 12
"type": "sse", "url": "https://mcp.example.com/sse", "headers": { - Network accessline 13
"url": "https://mcp.example.com/sse",
skills/mcp-integration/examples/stdio-server.json
- Access to secretsline 22
[Credential-related source omitted]
skills/mcp-integration/references/authentication.md
- Network accessline 26
"service": { "type": "sse", "url": "https://mcp.example.com/sse" - Network accessline 27
"type": "sse", "url": "https://mcp.example.com/sse" } - Network accessline 28
"url": "https://mcp.example.com/sse" - Network accessline 37
**Known OAuth-enabled MCP servers:** - Asana: `https://mcp.asana.com/sse` - Network accessline 38
- Asana: `https://mcp.asana.com/sse` - Network accessline 89
"api": { "type": "http", "url": "https://api.example.com/mcp", - Network accessline 90
"type": "http", "url": "https://api.example.com/mcp", "headers": { - Network accessline 91
"url": "https://api.example.com/mcp", - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 101
[Credential-related source omitted] - Network accessline 111
"api": { "type": "http", "url": "https://api.example.com/mcp", - Network accessline 112
"type": "http", "url": "https://api.example.com/mcp", "headers": { - Network accessline 113
"url": "https://api.example.com/mcp", - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Network accessline 129
"service": { "type": "sse", "url": "https://mcp.example.com/sse", - Network accessline 130
"type": "sse", "url": "https://mcp.example.com/sse", "headers": { - Network accessline 131
"url": "https://mcp.example.com/sse", - Access to secretsline 133
[Credential-related source omitted] - Access to secretsline 153
[Credential-related source omitted] - Access to secretsline 154
[Credential-related source omitted] - Network accessline 159
1. Visit https://api.example.com/tokens - Access to secretsline 223
[Credential-related source omitted] - Network accessline 235
"api": { "type": "sse", "url": "https://api.example.com", - Network accessline 236
"type": "sse", "url": "https://api.example.com", "headersHelper": "${CLAUDE_PLUGIN_ROOT}/scripts/get-headers.sh" - Network accessline 237
"url": "https://api.example.com", - Access to secretsline 275
[Credential-related source omitted] - Network accessline 318
"api": { "type": "http", "url": "https://api.example.com/mcp", - Network accessline 319
"type": "http", "url": "https://api.example.com/mcp", "headers": { - Network accessline 320
"url": "https://api.example.com/mcp", - Access to secretsline 322
[Credential-related source omitted] - Network accessline 332
"api": { "type": "http", "url": "https://${TENANT_ID}.api.example.com/mcp" - Network accessline 333
"type": "http", "url": "https://${TENANT_ID}.api.example.com/mcp" } - Network accessline 334
"url": "https://${TENANT_ID}.api.example.com/mcp" - Access to secretsline 367
[Credential-related source omitted] - Access to secretsline 370
[Credential-related source omitted] - Network accessline 397
[Credential-related source omitted] - Network accessline 398
[Credential-related source omitted] - Access to secretsline 398
[Credential-related source omitted] - Network accessline 399
https://api.example.com/mcp/health - Access to secretsline 421
[Credential-related source omitted] - Network accessline 446
{ "type": "sse", "url": "https://mcp.example.com/sse" - Network accessline 447
"type": "sse", "url": "https://mcp.example.com/sse" } - Network accessline 448
"url": "https://mcp.example.com/sse" - Network accessline 472
[Credential-related source omitted] - Access to secretsline 472
[Credential-related source omitted] - Network accessline 473
"env": { "API_URL": "https://secure.example.com" } - Network accessline 474
"API_URL": "https://secure.example.com" - Access to secretsline 509
[Credential-related source omitted] - Access to secretsline 515
[Credential-related source omitted] - Access to secretsline 538
[Credential-related source omitted]
skills/mcp-integration/references/server-types.md
- Access to secretsline 30
[Credential-related source omitted] - Network accessline 112
"hosted-service": { "type": "sse", "url": "https://mcp.example.com/sse" - Network accessline 113
"type": "sse", "url": "https://mcp.example.com/sse" } - Network accessline 114
"url": "https://mcp.example.com/sse" - Network accessline 122
"service": { "type": "sse", "url": "https://mcp.example.com/sse", - Network accessline 123
"type": "sse", "url": "https://mcp.example.com/sse", "headers": { - Network accessline 124
"url": "https://mcp.example.com/sse", - Network accessline 146
"asana": { "type": "sse", "url": "https://mcp.asana.com/sse" - Network accessline 147
"type": "sse", "url": "https://mcp.asana.com/sse" } - Network accessline 148
"url": "https://mcp.asana.com/sse" - Network accessline 162
"service": { "type": "sse", "url": "https://mcp.example.com/sse", - Network accessline 163
"type": "sse", "url": "https://mcp.example.com/sse", "headers": { - Network accessline 164
"url": "https://mcp.example.com/sse", - Access to secretsline 166
[Credential-related source omitted] - Network accessline 174
**Official Services:** - Asana: `https://mcp.asana.com/sse` - Network accessline 175
- Asana: `https://mcp.asana.com/sse` - Network accessline 176
- GitHub: `https://mcp.github.com/sse` - Network accessline 215
"api": { "type": "http", "url": "https://api.example.com/mcp" - Network accessline 216
"type": "http", "url": "https://api.example.com/mcp" } - Network accessline 217
"url": "https://api.example.com/mcp" - Network accessline 225
"api": { "type": "http", "url": "https://api.example.com/mcp", - Network accessline 226
"type": "http", "url": "https://api.example.com/mcp", "headers": { - Network accessline 227
"url": "https://api.example.com/mcp", - Access to secretsline 229
[Credential-related source omitted] - Access to secretsline 250
[Credential-related source omitted] - Access to secretsline 259
[Credential-related source omitted] - Access to secretsline 268
[Credential-related source omitted] - Network accessline 427
"hosted-server": { "type": "sse", "url": "https://mcp.example.com/sse" - Network accessline 428
"type": "sse", "url": "https://mcp.example.com/sse" } - Network accessline 429
"url": "https://mcp.example.com/sse" - Network accessline 439
"api": { "type": "http", "url": "https://api.example.com/mcp" - Network accessline 440
"type": "http", "url": "https://api.example.com/mcp" } - Network accessline 441
"url": "https://api.example.com/mcp" - Network accessline 470
"cloud-api": { "type": "sse", "url": "https://mcp.example.com/sse" - Network accessline 471
"type": "sse", "url": "https://mcp.example.com/sse" }, - Network accessline 472
"url": "https://mcp.example.com/sse" - Network accessline 474
"internal-service": { "type": "http", "url": "https://api.example.com/mcp", - Network accessline 475
"type": "http", "url": "https://api.example.com/mcp", "headers": { - Network accessline 476
"url": "https://api.example.com/mcp", - Access to secretsline 478
[Credential-related source omitted] - Access to secretsline 494
[Credential-related source omitted] - Network accessline 500
Set different values for dev/prod: - Dev: `API_URL=http://localhost:8080/mcp` - Network accessline 501
- Dev: `API_URL=http://localhost:8080/mcp` - Network accessline 502
- Prod: `API_URL=https://api.production.com/mcp`
skills/ml-paper-writing/SKILL.md
- Network accessline 85
claude mcp add exa -- npx -y mcp-remote "https://mcp.exa.ai/mcp" - Network accessline 92
"exa": { "type": "http", "url": "https://mcp.exa.ai/mcp" - Network accessline 93
"type": "http", "url": "https://mcp.exa.ai/mcp" } - Network accessline 94
"url": "https://mcp.exa.ai/mcp" - Network accessline 242
URL Pattern: https://arxiv.org/search/?searchtype=all&query=KEYWORDS&abstracts=show&order=-announced_date_first - Network accessline 243
https://arxiv.org/search/?searchtype=all&query=KEYWORDS&abstracts=show&order=-announced_date_first - Network accessline 245
Example Searches: - https://arxiv.org/search/?searchtype=all&query=graph+neural+networks&abstracts=show&order=-announced_date_first - Network accessline 246
- https://arxiv.org/search/?searchtype=all&query=graph+neural+networks&abstracts=show&order=-announced_date_first - Network accessline 247
- https://arxiv.org/search/?cat:cs.LG+AND+all:transformer&abstracts=show&order=-announced_date_first - Network accessline 565
| Source | Key Contribution | Link | |--------|-----------------|------| | **Neel Nanda** (Google DeepMind) | The Narrative Principle, What/Why/So What framework | [How to Write ML Papers](https://www.alignmentforum.org/posts/eJGptPbbFPZGLp - Network accessline 566
|--------|-----------------|------| | **Neel Nanda** (Google DeepMind) | The Narrative Principle, What/Why/So What framework | [How to Write ML Papers](https://www.alignmentforum.org/posts/eJGptPbbFPZGLpjsp/highly-opinionated-advice-on-how- - Network accessline 567
| **Neel Nanda** (Google DeepMind) | The Narrative Principle, What/Why/So What framework | [How to Write ML Papers](https://www.alignmentforum.org/posts/eJGptPbbFPZGLpjsp/highly-opinionated-advice-on-how-to-write-ml-papers) | - Network accessline 568
| **Sebastian Farquhar** (DeepMind) | 5-sentence abstract formula | [How to Write ML Papers](https://sebastianfarquhar.com/on-research/2024/11/04/how_to_write_ml_papers/) | - Network accessline 569
| **Gopen & Swan** | 7 principles of reader expectations | [Science of Scientific Writing](https://cseweb.ucsd.edu/~swanson/papers/science-of-writing.pdf) | - Network accessline 570
| **Zachary Lipton** | Word choice, eliminating hedging | [Heuristics for Scientific Writing](https://www.approximatelycorrect.com/2018/01/29/heuristics-technical-scientific-writing-machine-learning-perspective/) | - Network accessline 571
| **Jacob Steinhardt** (UC Berkeley) | Precision, consistent terminology | [Writing Tips](https://bounded-regret.ghost.io/) | - Network accessline 572
| **Ethan Perez** (Anthropic) | Micro-level clarity tips | [Easy Paper Writing Tips](https://ethanperez.net/easy-paper-writing-tips/) | - Network accessline 1106
- **VS Code/Cursor**: Install LaTeX Workshop extension + TeX Live → Save to auto-compile - **Command line**: `latexmk -pdf main.tex` or `pdflatex` + `bibtex` workflow - **Online**: Upload to [Overleaf](https://overleaf.com) - Network accessline 1108
- **Online**: Upload to [Overleaf](https://overleaf.com) - Network accessline 1114
**Writing Philosophy:** - [Neel Nanda: How to Write ML Papers](https://www.alignmentforum.org/posts/eJGptPbbFPZGLpjsp/highly-opinionated-advice-on-how-to-write-ml-papers) - Narrative, "What/Why/So What" - Network accessline 1115
- [Neel Nanda: How to Write ML Papers](https://www.alignmentforum.org/posts/eJGptPbbFPZGLpjsp/highly-opinionated-advice-on-how-to-write-ml-papers) - Narrative, "What/Why/So What" - Network accessline 1116
- [Farquhar: How to Write ML Papers](https://sebastianfarquhar.com/on-research/2024/11/04/how_to_write_ml_papers/) - 5-sentence abstract - Network accessline 1117
- [Gopen & Swan: Science of Scientific Writing](https://cseweb.ucsd.edu/~swanson/papers/science-of-writing.pdf) - 7 reader expectation principles - Network accessline 1118
- [Lipton: Heuristics for Scientific Writing](https://www.approximatelycorrect.com/2018/01/29/heuristics-technical-scientific-writing-machine-learning-perspective/) - Word choice - Network accessline 1119
- [Perez: Easy Paper Writing Tips](https://ethanperez.net/easy-paper-writing-tips/) - Micro-level clarity - Network accessline 1121
**APIs:** [Semantic Scholar](https://api.semanticscholar.org/api-docs/) | [CrossRef](https://www.crossref.org/documentation/retrieve-metadata/rest-api/) | [arXiv](https://info.arxiv.org/help/api/basics.html) - Network accessline 1123
**Venues:** [NeurIPS](https://neurips.cc/Conferences/2025/PaperInformation/StyleFiles) | [ICML](https://icml.cc/Conferences/2025/AuthorInstructions) | [ICLR](https://iclr.cc/Conferences/2026/AuthorGuide) | [ACL](https://github.com/acl-org/a
skills/ml-paper-writing/references/citation-workflow.md
- Network accessline 124
# Check CrossRef (via DOI) if doi: resp = requests.get(f"https://api.crossref.org/works/{doi}") - Network accessline 125
if doi: resp = requests.get(f"https://api.crossref.org/works/{doi}") if resp.status_code == 200: - Network accessline 126
resp = requests.get(f"https://api.crossref.org/works/{doi}") - Network accessline 130
# Check arXiv if arxiv_id: resp = requests.get( - Network accessline 131
if arxiv_id: resp = requests.get( f"http://export.arxiv.org/api/query?id_list={arxiv_id}" - Network accessline 132
resp = requests.get( - Network accessline 133
f"http://export.arxiv.org/api/query?id_list={arxiv_id}" - Network accessline 148
def doi_to_bibtex(doi: str) -> str: """Get verified BibTeX from DOI via CrossRef content negotiation.""" response = requests.get( - Network accessline 149
"""Get verified BibTeX from DOI via CrossRef content negotiation.""" response = requests.get( f"https://doi.org/{doi}", - Network accessline 150
response = requests.get( - Network accessline 151
f"https://doi.org/{doi}", - Access to secretsline 248
[Credential-related source omitted] - Access to secretsline 249
[Credential-related source omitted] - Network accessline 283
if paper.doi: try: resp = requests.get( - Network accessline 284
try: resp = requests.get( f"https://api.crossref.org/works/{paper.doi}", - Network accessline 285
resp = requests.get( - Network accessline 286
f"https://api.crossref.org/works/{paper.doi}", - Network accessline 295
if paper.arxiv_id: try: resp = requests.get( - Network accessline 296
try: resp = requests.get( f"http://export.arxiv.org/api/query?id_list={paper.arxiv_id}", - Network accessline 297
resp = requests.get( - Network accessline 298
f"http://export.arxiv.org/api/query?id_list={paper.arxiv_id}", - Network accessline 310
if paper.doi: try: resp = requests.get( - Network accessline 311
try: resp = requests.get( f"https://doi.org/{paper.doi}", - Network accessline 312
resp = requests.get( - Network accessline 313
f"https://doi.org/{paper.doi}", - Network accessline 549
**APIs:** - Semantic Scholar: https://api.semanticscholar.org/api-docs/ - Network accessline 550
- Semantic Scholar: https://api.semanticscholar.org/api-docs/ - Network accessline 551
- CrossRef: https://www.crossref.org/documentation/retrieve-metadata/rest-api/ - Network accessline 552
- arXiv: https://info.arxiv.org/help/api/basics.html - Network accessline 553
- OpenAlex: https://docs.openalex.org/ - Network accessline 555
**Python Libraries:** - `semanticscholar`: https://pypi.org/project/semanticscholar/ - Network accessline 556
- `semanticscholar`: https://pypi.org/project/semanticscholar/ - Network accessline 557
- `arxiv`: https://pypi.org/project/arxiv/ - Network accessline 558
- `habanero` (CrossRef): https://github.com/sckott/habanero - Network accessline 560
**Verification Tools:** - Citely: https://citely.ai/citation-checker - Network accessline 561
- Citely: https://citely.ai/citation-checker - Network accessline 562
- ReciteWorks: https://reciteworks.com/
skills/ml-paper-writing/references/knowledge/rethinking-papers-kaiming-he.md
- Network accessline 1003
**Code**: https://github.com/LTH14/mar
skills/ml-paper-writing/references/literature-research/arxiv-search-guide.md
- Network accessline 15
https://arxiv.org/search/?searchtype=all&query=KEYWORDS&abstracts=show&order=-announced_date_first - Network accessline 41
https://arxiv.org/search/?cat:cs.LG+OR+cat:cs.AI+AND+all:transformer&abstracts=show&order=-announced_date_first - Network accessline 130
**From arXiv Abstract Page (`https://arxiv.org/abs/ARXIV_ID`):** - Network accessline 195
- **arXiv**: https://arxiv.org/ - Network accessline 196
- **Semantic Scholar**: https://www.semanticscholar.org/ - Network accessline 197
- **Papers With Code**: https://paperswithcode.com/ - Network accessline 198
- **Connected Papers**: https://www.connectedpapers.com/ - Network accessline 199
- **arXiv API**: http://export.arxiv.org/api_help/
skills/ml-paper-writing/references/sources.md
- Network accessline 11
| Source | Author | URL | Key Contribution | |--------|--------|-----|------------------| | **Highly Opinionated Advice on How to Write ML Papers** | Neel Nanda | [Alignment Forum](https://www.alignmentforum.org/posts/eJGptPbbFPZGLpjsp/high - Network accessline 12
|--------|--------|-----|------------------| | **Highly Opinionated Advice on How to Write ML Papers** | Neel Nanda | [Alignment Forum](https://www.alignmentforum.org/posts/eJGptPbbFPZGLpjsp/highly-opinionated-advice-on-how-to-write-ml-pape - Network accessline 13
| **Highly Opinionated Advice on How to Write ML Papers** | Neel Nanda | [Alignment Forum](https://www.alignmentforum.org/posts/eJGptPbbFPZGLpjsp/highly-opinionated-advice-on-how-to-write-ml-papers) | Narrative framework, "What/Why/So What" - Network accessline 14
| **How to Write ML Papers** | Sebastian Farquhar (DeepMind) | [Blog](https://sebastianfarquhar.com/on-research/2024/11/04/how_to_write_ml_papers/) | 5-sentence abstract formula, structure templates | - Network accessline 15
| **A Survival Guide to a PhD** | Andrej Karpathy | [Blog](http://karpathy.github.io/2016/09/07/phd/) | Paper structure recipe, contribution framing | - Network accessline 16
| **Heuristics for Scientific Writing** | Zachary Lipton (CMU) | [Blog](https://www.approximatelycorrect.com/2018/01/29/heuristics-technical-scientific-writing-machine-learning-perspective/) | Word choice, section balance, intensifier warni - Network accessline 17
| **Advice for Authors** | Jacob Steinhardt (UC Berkeley) | [Blog](https://jsteinhardt.stat.berkeley.edu/blog/advice-for-authors) | Precision over brevity, consistent terminology | - Network accessline 18
| **Easy Paper Writing Tips** | Ethan Perez (Anthropic) | [Blog](https://ethanperez.net/easy-paper-writing-tips/) | Micro-level tips, apostrophe unfolding, clarity tricks | - Network accessline 22
| Source | Author | URL | Key Contribution | |--------|--------|-----|------------------| | **The Science of Scientific Writing** | Gopen & Swan | [PDF](https://cseweb.ucsd.edu/~swanson/papers/science-of-writing.pdf) | Topic/stress position - Network accessline 23
|--------|--------|-----|------------------| | **The Science of Scientific Writing** | Gopen & Swan | [PDF](https://cseweb.ucsd.edu/~swanson/papers/science-of-writing.pdf) | Topic/stress positions, old-before-new, 7 principles | | **Summary - Network accessline 24
| **The Science of Scientific Writing** | Gopen & Swan | [PDF](https://cseweb.ucsd.edu/~swanson/papers/science-of-writing.pdf) | Topic/stress positions, old-before-new, 7 principles | - Network accessline 25
| **Summary of Science of Scientific Writing** | Lawrence Crowl | [Summary](https://www.crowl.org/Lawrence/writing/GopenSwan90.html) | Condensed version of Gopen & Swan | - Network accessline 29
| Source | URL | Key Contribution | |--------|-----|------------------| | How To Write A Research Paper In ML | [Blog](https://grigorisg9gr.github.io/machine%20learning/research%20paper/how-to-write-a-research-paper-in-machine-learning/) | - Network accessline 30
|--------|-----|------------------| | How To Write A Research Paper In ML | [Blog](https://grigorisg9gr.github.io/machine%20learning/research%20paper/how-to-write-a-research-paper-in-machine-learning/) | Practical walkthrough, LaTeX tips | - Network accessline 31
| How To Write A Research Paper In ML | [Blog](https://grigorisg9gr.github.io/machine%20learning/research%20paper/how-to-write-a-research-paper-in-machine-learning/) | Practical walkthrough, LaTeX tips | - Network accessline 32
| A Recipe for Training Neural Networks | [Karpathy Blog](http://karpathy.github.io/2019/04/25/recipe/) | Debugging methodology that translates to paper structure | - Network accessline 33
| ICML Paper Writing Best Practices | [ICML](https://icml.cc/Conferences/2022/BestPractices) | Official venue guidance | - Network accessline 34
| Bill Freeman's Writing Slides | [MIT](https://billf.mit.edu/sites/default/files/documents/cvprPapers.pdf) | Visual guide to paper structure | - Network accessline 42
| Document | URL | Purpose | |----------|-----|---------| | Paper Checklist Guidelines | [NeurIPS](https://neurips.cc/public/guides/PaperChecklist) | 16-item mandatory checklist | - Network accessline 43
|----------|-----|---------| | Paper Checklist Guidelines | [NeurIPS](https://neurips.cc/public/guides/PaperChecklist) | 16-item mandatory checklist | | Reviewer Guidelines 2025 | [NeurIPS](https://neurips.cc/Conferences/2025/ReviewerGuidel - Network accessline 44
| Paper Checklist Guidelines | [NeurIPS](https://neurips.cc/public/guides/PaperChecklist) | 16-item mandatory checklist | - Network accessline 45
| Reviewer Guidelines 2025 | [NeurIPS](https://neurips.cc/Conferences/2025/ReviewerGuidelines) | Evaluation criteria, scoring | - Network accessline 46
| Style Files | [NeurIPS](https://neurips.cc/Conferences/2025/PaperInformation/StyleFiles) | LaTeX templates | - Network accessline 50
| Document | URL | Purpose | |----------|-----|---------| | Paper Guidelines | [ICML](https://icml.cc/Conferences/2024/PaperGuidelines) | Submission requirements | - Network accessline 51
|----------|-----|---------| | Paper Guidelines | [ICML](https://icml.cc/Conferences/2024/PaperGuidelines) | Submission requirements | | Reviewer Instructions 2025 | [ICML](https://icml.cc/Conferences/2025/ReviewerInstructions) | Review for - Network accessline 52
| Paper Guidelines | [ICML](https://icml.cc/Conferences/2024/PaperGuidelines) | Submission requirements | - Network accessline 53
| Reviewer Instructions 2025 | [ICML](https://icml.cc/Conferences/2025/ReviewerInstructions) | Review form, evaluation | - Network accessline 54
| Style & Author Instructions | [ICML](https://icml.cc/Conferences/2022/StyleAuthorInstructions) | Formatting specifications | - Network accessline 58
| Document | URL | Purpose | |----------|-----|---------| | Author Guide 2026 | [ICLR](https://iclr.cc/Conferences/2026/AuthorGuide) | Submission requirements, LLM disclosure | - Network accessline 59
|----------|-----|---------| | Author Guide 2026 | [ICLR](https://iclr.cc/Conferences/2026/AuthorGuide) | Submission requirements, LLM disclosure | | Reviewer Guide 2025 | [ICLR](https://iclr.cc/Conferences/2025/ReviewerGuide) | Review proc - Network accessline 60
| Author Guide 2026 | [ICLR](https://iclr.cc/Conferences/2026/AuthorGuide) | Submission requirements, LLM disclosure | - Network accessline 61
| Reviewer Guide 2025 | [ICLR](https://iclr.cc/Conferences/2025/ReviewerGuide) | Review process, evaluation | - Network accessline 65
| Document | URL | Purpose | |----------|-----|---------| | ACL Style Files | [GitHub](https://github.com/acl-org/acl-style-files) | LaTeX templates | - Network accessline 66
|----------|-----|---------| | ACL Style Files | [GitHub](https://github.com/acl-org/acl-style-files) | LaTeX templates | | ACL Rolling Review | [ARR](https://aclrollingreview.org/) | Submission process | - Network accessline 67
| ACL Style Files | [GitHub](https://github.com/acl-org/acl-style-files) | LaTeX templates | - Network accessline 68
| ACL Rolling Review | [ARR](https://aclrollingreview.org/) | Submission process | - Network accessline 72
| Document | URL | Purpose | |----------|-----|---------| | Author Kit 2026 | [AAAI](https://aaai.org/authorkit26/) | Templates and guidelines | - Network accessline 74
| Author Kit 2026 | [AAAI](https://aaai.org/authorkit26/) | Templates and guidelines | - Network accessline 78
| Document | URL | Purpose | |----------|-----|---------| | Template | [GitHub](https://github.com/COLM-org/Template) | LaTeX templates | - Network accessline 80
| Template | [GitHub](https://github.com/COLM-org/Template) | LaTeX templates | - Network accessline 88
| API | Documentation | Best For | |-----|---------------|----------| | **Semantic Scholar** | [Docs](https://api.semanticscholar.org/api-docs/) | ML/AI papers, citation graphs | - Network accessline 89
|-----|---------------|----------| | **Semantic Scholar** | [Docs](https://api.semanticscholar.org/api-docs/) | ML/AI papers, citation graphs | | **CrossRef** | [Docs](https://www.crossref.org/documentation/retrieve-metadata/rest-api/) | DO - Network accessline 90
| **Semantic Scholar** | [Docs](https://api.semanticscholar.org/api-docs/) | ML/AI papers, citation graphs | - Network accessline 91
| **CrossRef** | [Docs](https://www.crossref.org/documentation/retrieve-metadata/rest-api/) | DOI lookup, BibTeX retrieval | - Network accessline 92
| **arXiv** | [Docs](https://info.arxiv.org/help/api/basics.html) | Preprints, PDF access | - Network accessline 93
| **OpenAlex** | [Docs](https://docs.openalex.org/) | Open alternative, bulk access | - Network accessline 105
| Tool | URL | Purpose | |------|-----|---------| | Citely | [citely.ai](https://citely.ai/citation-checker) | Batch verification | - Network accessline 106
|------|-----|---------| | Citely | [citely.ai](https://citely.ai/citation-checker) | Batch verification | | ReciteWorks | [reciteworks.com](https://reciteworks.com/) | In-text citation checking | - Network accessline 107
| Citely | [citely.ai](https://citely.ai/citation-checker) | Batch verification | - Network accessline 108
| ReciteWorks | [reciteworks.com](https://reciteworks.com/) | In-text citation checking | - Network accessline 116
| Tool | URL | Purpose | |------|-----|---------| | PlotNeuralNet | [GitHub](https://github.com/HarisIqbal88/PlotNeuralNet) | TikZ neural network diagrams | - Network accessline 117
|------|-----|---------| | PlotNeuralNet | [GitHub](https://github.com/HarisIqbal88/PlotNeuralNet) | TikZ neural network diagrams | | SciencePlots | [GitHub](https://github.com/garrettj403/SciencePlots) | Publication-ready matplotlib | - Network accessline 118
| PlotNeuralNet | [GitHub](https://github.com/HarisIqbal88/PlotNeuralNet) | TikZ neural network diagrams | - Network accessline 119
| SciencePlots | [GitHub](https://github.com/garrettj403/SciencePlots) | Publication-ready matplotlib | - Network accessline 120
| Okabe-Ito Palette | [Reference](https://jfly.uni-koeln.de/color/) | Colorblind-safe colors | - Network accessline 124
| Resource | URL | Purpose | |----------|-----|---------| | Overleaf Templates | [Overleaf](https://www.overleaf.com/latex/templates) | Online LaTeX editor | - Network accessline 125
|----------|-----|---------| | Overleaf Templates | [Overleaf](https://www.overleaf.com/latex/templates) | Online LaTeX editor | | BibLaTeX Guide | [CTAN](https://ctan.org/pkg/biblatex) | Modern citation management | - Network accessline 126
| Overleaf Templates | [Overleaf](https://www.overleaf.com/latex/templates) | Online LaTeX editor | - Network accessline 127
| BibLaTeX Guide | [CTAN](https://ctan.org/pkg/biblatex) | Modern citation management | - Network accessline 133
| Source | URL | Key Finding | |--------|-----|-------------| | AI Hallucinations in Citations | [Enago](https://www.enago.com/academy/ai-hallucinations-research-citations/) | ~40% error rate | - Network accessline 134
|--------|-----|-------------| | AI Hallucinations in Citations | [Enago](https://www.enago.com/academy/ai-hallucinations-research-citations/) | ~40% error rate | | Hallucination in AI Writing | [PMC](https://pmc.ncbi.nlm.nih.gov/articles/P - Network accessline 135
| AI Hallucinations in Citations | [Enago](https://www.enago.com/academy/ai-hallucinations-research-citations/) | ~40% error rate | - Network accessline 136
| Hallucination in AI Writing | [PMC](https://pmc.ncbi.nlm.nih.gov/articles/PMC10726751/) | Types of citation errors | - Network accessline 137
| NeurIPS 2025 AI Report | [ByteIota](https://byteiota.com/neurips-2025-100-ai-hallucinations-slip-through-review/) | 100+ hallucinated citations |
skills/ml-paper-writing/templates/README.md
- Network accessline 11
**Setup:** 1. Install [TeX Live](https://www.tug.org/texlive/) (full distribution recommended) - Network accessline 12
1. Install [TeX Live](https://www.tug.org/texlive/) (full distribution recommended) - Network accessline 13
- macOS: `brew install --cask mactex` - Ubuntu: `sudo apt install texlive-full` - Windows: Download from [tug.org/texlive](https://www.tug.org/texlive/) - Dangerous shell operationline 14
- Ubuntu: `sudo apt install texlive-full` - Network accessline 15
- Windows: Download from [tug.org/texlive](https://www.tug.org/texlive/) - Network accessline 62
1. Go to [overleaf.com](https://www.overleaf.com) - Network accessline 108
| Conference | Directory | Year | Source | |------------|-----------|------|--------| | ICML | `icml2026/` | 2026 | [Official ICML](https://icml.cc/Conferences/2026/AuthorInstructions) | - Network accessline 109
|------------|-----------|------|--------| | ICML | `icml2026/` | 2026 | [Official ICML](https://icml.cc/Conferences/2026/AuthorInstructions) | | ICLR | `iclr2026/` | 2026 | [Official GitHub](https://github.com/ICLR/Master-Template) | - Network accessline 110
| ICML | `icml2026/` | 2026 | [Official ICML](https://icml.cc/Conferences/2026/AuthorInstructions) | - Network accessline 111
| ICLR | `iclr2026/` | 2026 | [Official GitHub](https://github.com/ICLR/Master-Template) | - Network accessline 112
| NeurIPS | `neurips2025/` | 2025 | Community template | | ACL | `acl/` | 2025+ | [Official ACL](https://github.com/acl-org/acl-style-files) | | AAAI | `aaai2026/` | 2026 | [AAAI Author Kit](https://aaai.org/authorkit26/) | - Network accessline 113
| ACL | `acl/` | 2025+ | [Official ACL](https://github.com/acl-org/acl-style-files) | - Network accessline 114
| AAAI | `aaai2026/` | 2026 | [AAAI Author Kit](https://aaai.org/authorkit26/) | - Network accessline 115
| COLM | `colm2025/` | 2025 | [Official COLM](https://github.com/COLM-org/Template) | - Network accessline 246
- ICML: https://icml.cc/ - Network accessline 247
- ICLR: https://iclr.cc/ - Network accessline 248
- NeurIPS: https://neurips.cc/ - Network accessline 249
- ACL: https://github.com/acl-org/acl-style-files - Network accessline 250
- AAAI: https://aaai.org/ - Network accessline 251
- COLM: https://colmweb.org/
skills/ml-paper-writing/templates/aaai2026/README.md
skills/ml-paper-writing/templates/aaai2026/aaai2026-unified-supp.tex
skills/ml-paper-writing/templates/aaai2026/aaai2026-unified-template.tex
- Dangerous shell operationline 121
Written by AAAI Press Staff\textsuperscript{\rm 1}\thanks{With help from the AAAI Publications Committee.}\\ - Dangerous shell operationline 132
\textsuperscript{\rm 1}Association for the Advancement of Artificial Intelligence\\ - Dangerous shell operationline 137
% Sunil Issar\textsuperscript{\rm 2}, - Dangerous shell operationline 138
% J. Scott Penberthy\textsuperscript{\rm 3}, - Dangerous shell operationline 139
% George Ferguson\textsuperscript{\rm 4}, - Dangerous shell operationline 140
% Hans Guesgen\textsuperscript{\rm 5} - Dangerous shell operationline 169
First Author Name\textsuperscript{\rm 1}, - Dangerous shell operationline 170
Second Author Name\textsuperscript{\rm 2}, - Dangerous shell operationline 171
Third Author Name\textsuperscript{\rm 1} - Dangerous shell operationline 175
\textsuperscript{\rm 1}Affiliation 1\\ - Dangerous shell operationline 176
\textsuperscript{\rm 2}Affiliation 2\\ - Network accessline 198
% NOTE: For anonymous submissions, do not include links that could reveal your identity % \begin{links} % \link{Code}{https://aaai.org/example/code} - Network accessline 199
% \begin{links} % \link{Code}{https://aaai.org/example/code} % \link{Datasets}{https://aaai.org/example/datasets} - Network accessline 200
% \link{Code}{https://aaai.org/example/code} - Network accessline 201
% \link{Datasets}{https://aaai.org/example/datasets} - Network accessline 202
% \link{Extended version}{https://aaai.org/example/extended-version} - Network accessline 206
% You must keep this block between (not within) the abstract and the main body of the paper. \begin{links} \link{Code}{https://aaai.org/example/code} - Network accessline 207
\begin{links} \link{Code}{https://aaai.org/example/code} \link{Datasets}{https://aaai.org/example/datasets} - Network accessline 208
\link{Code}{https://aaai.org/example/code} - Network accessline 209
\link{Datasets}{https://aaai.org/example/datasets} - Network accessline 210
\link{Extended version}{https://aaai.org/example/extended-version} - Network accessline 405
\begin{scriptsize}\begin{verbatim} \begin{links} \link{Code}{https://aaai.org/example/guidelines} - Network accessline 406
\begin{links} \link{Code}{https://aaai.org/example/guidelines} \link{Datasets}{https://aaai.org/example/datasets} - Network accessline 407
\link{Code}{https://aaai.org/example/guidelines} - Network accessline 408
\link{Datasets}{https://aaai.org/example/datasets} - Network accessline 409
\link{Extended version}{https://aaai.org/example} - Network accessline 525
\subsubsection{Obtaining Type 1 Computer Modern for \LaTeX{}.} If you use Computer Modern for the mathematics in your paper (you cannot use it for the text) you may need to download type 1 Computer fonts. They are available without charge f - Network accessline 527
http://www.ams.org/tex/type1-fonts.html. - Network accessline 532
\subsection{Title and Authors} Your title must appear centered over both text columns in sixteen-point bold type (twenty-four point leading). The title must be written in Title Case capitalization rules (not sentence case). The rules are a - Network accessline 533
Your title must appear centered over both text columns in sixteen-point bold type (twenty-four point leading). The title must be written in Title Case capitalization rules (not sentence case). The rules are a bit involved, but in general ve - Dangerous shell operationline 551
\noindent For authors from different institutions, use \textbackslash textsuperscript \{\textbackslash rm x \} to match authors and affiliations. Notice that there should not be any spaces between the author name (or comma following it) and - Dangerous shell operationline 555
AuthorOne\equalcontrib\textsuperscript{\rm 1,\rm 2}, - Dangerous shell operationline 556
AuthorTwo\equalcontrib\textsuperscript{\rm 2}, - Dangerous shell operationline 557
AuthorThree\textsuperscript{\rm 3},\\ - Dangerous shell operationline 558
AuthorFour\textsuperscript{\rm 4}, - Dangerous shell operationline 559
AuthorFive \textsuperscript{\rm 5}} - Dangerous shell operationline 562
\textsuperscript{\rm 1}AffiliationOne,\\ - Dangerous shell operationline 563
\textsuperscript{\rm 2}AffiliationTwo,\\ - Dangerous shell operationline 564
\textsuperscript{\rm 3}AffiliationThree,\\ - Dangerous shell operationline 565
\textsuperscript{\rm 4}AffiliationFour,\\ - Dangerous shell operationline 566
\textsuperscript{\rm 5}AffiliationFive\\ - Network accessline 849
@misc(key, [...] howpublished="\url{http://...}", - Network accessline 850
[...] howpublished="\url{http://...}", note="Accessed: YYYY-mm-dd", - Network accessline 851
howpublished="\url{http://...}", - Network accessline 859
\vspace{.2em} For the most up to date version of the AAAI reference style, please consult the \textit{AI Magazine} Author Guidelines at \url{https://aaai.org/ojs/index.php/aimagazine/about/submissions#authorGuidelines} - Network accessline 860
For the most up to date version of the AAAI reference style, please consult the \textit{AI Magazine} Author Guidelines at \url{https://aaai.org/ojs/index.php/aimagazine/about/submissions#authorGuidelines}
skills/ml-paper-writing/templates/aaai2026/aaai2026.bib
- Network accessline 38
publisher = {American Association for the Advancement of Science}, issn = {0036-8075}, URL = {https://science.sciencemag.org/content/208/4447/1019}, - Network accessline 39
issn = {0036-8075}, URL = {https://science.sciencemag.org/content/208/4447/1019}, eprint = {https://science.sciencemag.org/content/208/4447/1019.full.pdf}, - Network accessline 40
URL = {https://science.sciencemag.org/content/208/4447/1019}, - Network accessline 41
eprint = {https://science.sciencemag.org/content/208/4447/1019.full.pdf}, - Network accessline 58
year = {1984}, issn = {0020-7373}, doi = {https://doi.org/10.1016/S0020-7373(84)80003-6}, - Network accessline 59
issn = {0020-7373}, doi = {https://doi.org/10.1016/S0020-7373(84)80003-6}, url = {https://www.sciencedirect.com/science/article/pii/S0020737384800036}, - Network accessline 60
doi = {https://doi.org/10.1016/S0020-7373(84)80003-6}, - Network accessline 61
url = {https://www.sciencedirect.com/science/article/pii/S0020737384800036}, - Network accessline 106
title = "Pluto: The 'Other' Red Planet", author = "{NASA}", howpublished = "\url{https://www.nasa.gov/nh/pluto-the-other-red-planet}", - Network accessline 107
author = "{NASA}", howpublished = "\url{https://www.nasa.gov/nh/pluto-the-other-red-planet}", year = 2015, - Network accessline 108
howpublished = "\url{https://www.nasa.gov/nh/pluto-the-other-red-planet}",
skills/ml-paper-writing/templates/aaai2026/aaai2026.sty
- Network accessline 241
\@ifpackageloaded{bbm}% {% \PackageError{aaai}{You must not use bbm package in AAAI papers because it introduces Type 3 fonts which are forbidden.}{See https://tex.stackexchange.com/questions/479160/a-replacement-to-mathbbm1-with- - Network accessline 242
{% \PackageError{aaai}{You must not use bbm package in AAAI papers because it introduces Type 3 fonts which are forbidden.}{See https://tex.stackexchange.com/questions/479160/a-replacement-to-mathbbm1-with-type-1-fonts for possible al - Network accessline 243
\PackageError{aaai}{You must not use bbm package in AAAI papers because it introduces Type 3 fonts which are forbidden.}{See https://tex.stackexchange.com/questions/479160/a-replacement-to-mathbbm1-with-type-1-fonts for possible alternative
skills/ml-paper-writing/templates/acl/README.md
- Network accessline 12
- as an [Overleaf template](https://www.overleaf.com/latex/templates/association-for-computational-linguistics-acl-conference/jvxskxpnznfj) - Network accessline 14
- as a [.zip file](https://github.com/acl-org/acl-style-files/archive/refs/heads/master.zip) - Network accessline 16
Please see [`acl_latex.tex`](https://github.com/acl-org/acl-style-files/blob/master/acl_latex.tex) for an example. - Network accessline 21
- [Paper formatting guidelines](https://acl-org.github.io/ACLPUB/formatting.html) - Network accessline 46
- git pull from github to a local repository - then, git push from your local repository to overleaf project - Overleaf project is https://www.overleaf.com/project/5f64f1fb97c4c50001b60549 - Network accessline 47
- then, git push from your local repository to overleaf project - Overleaf project is https://www.overleaf.com/project/5f64f1fb97c4c50001b60549 - Overleaf git url is https://git.overleaf.com/5f64f1fb97c4c50001b60549 - Network accessline 48
- Overleaf project is https://www.overleaf.com/project/5f64f1fb97c4c50001b60549 - Network accessline 49
- Overleaf git url is https://git.overleaf.com/5f64f1fb97c4c50001b60549
skills/ml-paper-writing/templates/acl/acl.sty
- Network accessline 2
% The official sources can be found at % % https://github.com/acl-org/acl-style-files/ - Network accessline 3
% % https://github.com/acl-org/acl-style-files/ % - Network accessline 4
% https://github.com/acl-org/acl-style-files/ - Network accessline 35
\ifacl@linenumbers % Add draft line numbering via the lineno package % https://texblog.org/2012/02/08/adding-line-numbers-to-documents/ - Network accessline 36
% Add draft line numbering via the lineno package % https://texblog.org/2012/02/08/adding-line-numbers-to-documents/ \usepackage[switch,mathlines]{lineno} - Network accessline 37
% https://texblog.org/2012/02/08/adding-line-numbers-to-documents/ - Network accessline 61
% Patch amsmath commands so that the previous line and the equation itself % are numbered. Bug: multline has an extra line number. % https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align - Network accessline 62
% are numbered. Bug: multline has an extra line number. % https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align \usepackage{etoolbox} %% <- for \pretocmd, \apptocmd and \patchcmd - Network accessline 63
% https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align
skills/ml-paper-writing/templates/acl/acl_latex.tex
- Network accessline 13
% For Vietnamese characters % \usepackage[T5]{fontenc} % See https://www.latex-project.org/help/documentation/encguide.pdf for other character sets - Network accessline 15
% See https://www.latex-project.org/help/documentation/encguide.pdf for other character sets - Network accessline 117
These instructions are for authors submitting papers to *ACL conferences using \LaTeX. They are not self-contained. All authors must follow the general instructions for *ACL proceedings,\footnote{\url{http://acl-org.github.io/ACLPUB/formatt - Network accessline 298
You can obtain the complete ACL Anthology as a Bib\TeX{} file from \url{https://aclweb.org/anthology/anthology.bib.gz}.
skills/ml-paper-writing/templates/acl/acl_natbib.bst
- Network accessline 1
%%% Modification of BibTeX style file acl_natbib_nourl.bst %%% ... by urlbst, version 0.9.1 (marked with "% urlbst") %%% See <https://purl.org/nxg/dist/urlbst> and repository <https://heptapod.host/nxg/urlbst> - Network accessline 2
%%% ... by urlbst, version 0.9.1 (marked with "% urlbst") %%% See <https://purl.org/nxg/dist/urlbst> and repository <https://heptapod.host/nxg/urlbst> %%% Modifications Copyright 2002–23, Norman Gray, - Network accessline 3
%%% See <https://purl.org/nxg/dist/urlbst> and repository <https://heptapod.host/nxg/urlbst> - Network accessline 125
"online" 'onlinestring := % label that a resource is online "[link]" 'linktextstring := % anonymous link text "http://www.ncbi.nlm.nih.gov/pubmed/" 'pubmedurl := % prefix to make URL from PUBMED - Network accessline 126
"[link]" 'linktextstring := % anonymous link text "http://www.ncbi.nlm.nih.gov/pubmed/" 'pubmedurl := % prefix to make URL from PUBMED "https://doi.org/" 'doiurl := % prefix to make URL from DOI - Network accessline 127
"http://www.ncbi.nlm.nih.gov/pubmed/" 'pubmedurl := % prefix to make URL from PUBMED - Network accessline 128
"https://doi.org/" 'doiurl := % prefix to make URL from DOI - Network accessline 129
"doi:" 'doiprefix := % printed text to introduce DOI "https://arxiv.org/abs/" 'eprinturl := % prefix to make URL from eprint ref "cited " 'citedstring := % label in "lastchecked" remark - Network accessline 130
"https://arxiv.org/abs/" 'eprinturl := % prefix to make URL from eprint ref - Network accessline 1191
{ doi empty$ { "" } { doi parse.doi % leaves "https://doi.org/DOI" DOI on the stack - Network accessline 1192
{ "" } { doi parse.doi % leaves "https://doi.org/DOI" DOI on the stack 's := 't := - Network accessline 1193
{ doi parse.doi % leaves "https://doi.org/DOI" DOI on the stack - Network accessline 1231
% then don't print the URL (thanks to Joseph Wright % for (the original version of) this code, % at http://tex.stackexchange.com/questions/5660) - Network accessline 1232
% for (the original version of) this code, % at http://tex.stackexchange.com/questions/5660) adddoi - Network accessline 1233
% at http://tex.stackexchange.com/questions/5660) - Network accessline 1287
% author, note, year, month, and lastchecked fields optional % See references % ISO 690-2 http://www.nlc-bnc.ca/iso/tc46sc9/standard/690-2e.htm - Network accessline 1288
% See references % ISO 690-2 http://www.nlc-bnc.ca/iso/tc46sc9/standard/690-2e.htm % http://www.classroom.net/classroom/CitingNetResources.html - Network accessline 1289
% ISO 690-2 http://www.nlc-bnc.ca/iso/tc46sc9/standard/690-2e.htm - Network accessline 1290
% http://www.classroom.net/classroom/CitingNetResources.html - Network accessline 1291
% http://neal.ctstateu.edu/history/cite.html - Network accessline 1292
% http://www.cas.usf.edu/english/walker/mla.html
skills/ml-paper-writing/templates/acl/anthology.bib.txt
- Network accessline 10
For example, https://aclanthology.org/N04-1035 can be cited as \cite{galley-etal-2004-whats}. - Network accessline 12
The consolidated file can be downloaded from here: - https://aclanthology.org/anthology.bib - Network accessline 13
- https://aclanthology.org/anthology.bib - Network accessline 19
There are currently (2025) two files: - https://aclanthology.org/anthology-1.bib - Network accessline 20
- https://aclanthology.org/anthology-1.bib - Network accessline 21
- https://aclanthology.org/anthology-2.bib
skills/ml-paper-writing/templates/acl/custom.bib
skills/ml-paper-writing/templates/acl/formatting.md
- Network accessline 10
> https://acl-org.github.io/ACLPUB/ - Network accessline 132
Long titles should be typed on two lines without a blank line intervening. Put the title 2.5 cm from the top of the page. Write the title in [title case](https://apastyle.apa.org/style-grammar-guidelines/capitalization/title-case); do not w - Network accessline 134
Write the title in [title case](https://apastyle.apa.org/style-grammar-guidelines/capitalization/title-case); do not write the title in all capital letters, except for acronyms (e.g., "BLEU") or proper nouns ("English") that are normally up - Network accessline 252
Provide as complete a citation as possible, using a consistent format, such as the [one for Computational Linguistics](http://cljournal.org/style_guide_refs.html) or the one in the [Publication Manual of the American Psychological Associati - Network accessline 258
All references are required to contain DOIs of all cited works when possible, or, as a second resort, links to ACL Anthology pages. Appropriate records should be found for most materials in the current [ACL Anthology](https://aclweb.org/ant - Network accessline 259
Appropriate records should be found for most materials in the current [ACL Anthology](https://aclweb.org/anthology/). - Network accessline 263
> Rie Kubota Ando and Tong Zhang. 2005. [A framework for learning predictive structures from multiple tasks and unlabeled data](https://www.jmlr.org/papers/v6/ando05a.html). *Journal of Machine Learning Research*, 6:1817–1853. - Network accessline 267
> Galen Andrew and Jianfeng Gao. 2007. [Scalable training of L1-regularized log-linear models](https://doi.org/10.1145/1273496.1273501). In *Proceedings of the 24th International Conference on Machine Learning*, pages 33–40. - Network accessline 271
> James Goodman, Andreas Vlachos, and Jason Naradowsky. 2016. [Noise reduction and targeted exploration in imitation learning for Abstract Meaning Representation parsing](http://dx.doi.org/10.18653/v1/P16-1001). In *Proceedings of the 54th - Network accessline 275
> Benjamin Börschinger and Mark Johnson. 2011. [A particle filter algorithm for Bayesian word segmentation](https://www.aclweb.org/anthology/U11-1004/). In *Proceedings of the Australasian Language Technology Association Workshop 2011*, pag - Network accessline 279
> Mohammad Sadegh Rasooli and Joel R. Tetreault. 2015. [Yara parser: A fast and accurate dependency parser](http://arxiv.org/abs/1503.06733). *Computing Research Repository*, arXiv:1503.06733. Version 2.
skills/ml-paper-writing/templates/colm2025/colm2025_conference.bib
- Network accessline 5
publisher = {Curran Associates, Inc.}, title = {Attention is All you Need}, url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf}, - Network accessline 6
title = {Attention is All you Need}, url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf}, volume = {30}, - Network accessline 7
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf},
skills/ml-paper-writing/templates/colm2025/colm2025_conference.tex
- Network accessline 71
COLM requires electronic submissions, processed by \url{https://openreview.net/}. See COLM's website for more instructions. - Network accessline 72
\url{https://openreview.net/}. See COLM's website for more instructions. - Network accessline 102
The style files for COLM and other conference information are available online at: \begin{center} \url{http://www.colmweb.org/} - Network accessline 103
\begin{center} \url{http://www.colmweb.org/} \end{center} - Network accessline 104
\url{http://www.colmweb.org/} - Network accessline 143
We strongly recommend following arXiv's guidelines for making your paper friendly for HTML conversion: \url{https://info.arxiv.org/help/submit_latex_best_practices.html}. - Network accessline 277
\end{verbatim} for .pdf graphics. See section~4.4 in the graphics bundle documentation (\url{http://www.ctan.org/tex-archive/macros/latex/required/graphics/grfguide.ps}) - Network accessline 279
See section~4.4 in the graphics bundle documentation (\url{http://www.ctan.org/tex-archive/macros/latex/required/graphics/grfguide.ps})
skills/ml-paper-writing/templates/colm2025/math_commands.tex
- Dangerous shell operationline 82
% rm is already a command, just don't name any random variables m
skills/ml-paper-writing/templates/iclr2026/iclr2026_conference.tex
- Network accessline 5
% Optional math commands from https://github.com/goodfeli/dlbook_notation. - Network accessline 65
ICLR requires electronic submissions, processed by \url{https://openreview.net/}. See ICLR's website for more instructions. - Network accessline 66
\url{https://openreview.net/}. See ICLR's website for more instructions. - Network accessline 93
The style files for ICLR and other conference information are available online at: \begin{center} \url{http://www.iclr.cc/} - Network accessline 94
\begin{center} \url{http://www.iclr.cc/} \end{center} - Network accessline 95
\url{http://www.iclr.cc/} - Network accessline 230
notation file from the textbook, \textit{Deep Learning} \cite{goodfellow2016deep} available at \url{https://github.com/goodfeli/dlbook_notation/}. Use of this style - Network accessline 231
\cite{goodfellow2016deep} available at \url{https://github.com/goodfeli/dlbook_notation/}. Use of this style is not required and can be disabled by commenting out - Network accessline 232
\url{https://github.com/goodfeli/dlbook_notation/}. Use of this style - Network accessline 390
\end{verbatim} for .pdf graphics. See section~4.4 in the graphics bundle documentation (\url{http://www.ctan.org/tex-archive/macros/latex/required/graphics/grfguide.ps}) - Network accessline 392
See section~4.4 in the graphics bundle documentation (\url{http://www.ctan.org/tex-archive/macros/latex/required/graphics/grfguide.ps})
skills/ml-paper-writing/templates/iclr2026/math_commands.tex
- Dangerous shell operationline 82
% rm is already a command, just don't name any random variables m
skills/ml-paper-writing/templates/icml2026/example_paper.tex
- Network accessline 136
are available on the conference web site at: \begin{center} \texttt{http://icml.cc/} - Network accessline 137
\begin{center} \texttt{http://icml.cc/} \end{center} - Network accessline 138
\texttt{http://icml.cc/} - Network accessline 572
for everyone including people with disabilities and sensory or neurological differences. Tips of how to achieve this and what to pay attention to will be provided on the conference website \url{http://icml.cc/}. - Network accessline 574
provided on the conference website \url{http://icml.cc/}.
skills/ml-paper-writing/templates/icml2026/fancyhdr.sty
skills/ml-paper-writing/templates/neurips2025/Makefile
skills/nature-data/references/source-basis.md
- Network accessline 26
- Springer Nature, Research data policy: <https://www.springernature.com/gp/journal-policies/15369670> - Network accessline 27
<https://www.springernature.com/gp/journal-policies/15369670> - Network accessline 28
- Springer Nature, Data availability statements: <https://www.springernature.com/gp/authors/research-data-policy/data-availability-statements> - Springer Nature, Data repository guidance: - Network accessline 29
<https://www.springernature.com/gp/authors/research-data-policy/data-availability-statements> - Network accessline 30
- Springer Nature, Data repository guidance: <https://www.springernature.com/gp/authors/research-data-policy/recommended-repositories> - Springer Nature, Sensitive data: - Network accessline 31
<https://www.springernature.com/gp/authors/research-data-policy/recommended-repositories> - Network accessline 32
- Springer Nature, Sensitive data: <https://www.springernature.com/gp/authors/research-data-policy/sensitive-data> - Nature Portfolio, Reporting standards and availability of data, materials, code and protocols: - Network accessline 33
<https://www.springernature.com/gp/authors/research-data-policy/sensitive-data> - Network accessline 34
- Nature Portfolio, Reporting standards and availability of data, materials, code and protocols: <https://www.nature.com/nature-portfolio/editorial-policies/reporting-standards> - Example Nature Portfolio journal reporting standards page: - Network accessline 35
<https://www.nature.com/nature-portfolio/editorial-policies/reporting-standards> - Network accessline 36
- Example Nature Portfolio journal reporting standards page: <https://www.nature.com/npj2dmaterials/editorial-policies/reporting-standards> - Nature Research, Data availability statements and data citations policy FAQ: - Network accessline 37
<https://www.nature.com/npj2dmaterials/editorial-policies/reporting-standards> - Network accessline 38
- Nature Research, Data availability statements and data citations policy FAQ: <https://www.nature.com/documents/nr-data-availability-statements-data-citations-faqs.pdf> - Scientific Data, Data policies: - Network accessline 39
<https://www.nature.com/documents/nr-data-availability-statements-data-citations-faqs.pdf> - Network accessline 40
- Scientific Data, Data policies: <https://www.nature.com/sdata/policies/data-policies> - Wilkinson et al. 2016, The FAIR Guiding Principles for scientific data management and stewardship: - Network accessline 41
<https://www.nature.com/sdata/policies/data-policies> - Network accessline 42
- Wilkinson et al. 2016, The FAIR Guiding Principles for scientific data management and stewardship: <https://www.nature.com/articles/sdata201618> - DataCite Metadata Schema: - Network accessline 43
<https://www.nature.com/articles/sdata201618> - Network accessline 45
<https://schema.datacite.org/>
skills/nature-response/references/source-basis.md
- Network accessline 18
| Source | URL | Source type | Local rule summary | |---|---|---|---| | Nature editorial criteria and processes | https://www.nature.com/nature/for-authors/editorial-criteria-and-processes | Formal journal process | Revised papers that need - Network accessline 19
|---|---|---|---| | Nature editorial criteria and processes | https://www.nature.com/nature/for-authors/editorial-criteria-and-processes | Formal journal process | Revised papers that need technical work should be accompanied by a point-by- - Network accessline 20
| Nature editorial criteria and processes | https://www.nature.com/nature/for-authors/editorial-criteria-and-processes | Formal journal process | Revised papers that need technical work should be accompanied by a point-by-point response to - Network accessline 21
| Nature transparent peer review information | https://www.nature.com/nature/for-authors/editorial-criteria-and-processes | Formal journal process | For some published original research articles, reviewer comments and author rebuttal materi - Network accessline 22
| Nature Electronics editorial process | https://www.nature.com/natelectron/submission-guidelines/editorial-process | Journal instruction | A revision package commonly includes the revised manuscript, a response to each reviewer, and a cove - Network accessline 23
| Springer Nature rebuttal guidance | https://communities.springernature.com/posts/how-to-write-a-rebuttal-letter | Editorial advice | Preserve reviewer comments, respond immediately after each concern, number or clearly separate replies, s - Network accessline 24
| Scientific Reviews peer-review policies | https://www.nature.com/scirev/journal-policies/peer-review | Journal policy | Revisions should include point-by-point responses explaining manuscript changes. Appeals and revision responses follow
skills/nature-writing/README.md
skills/obsidian-literature-workflow/scripts/build_literature_canvas.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/obsidian-literature-workflow/scripts/build_literature_graph.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/obsidian-project-kb-core/scripts/kb_canvas_check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/obsidian-project-kb-core/scripts/kb_common.py
skills/obsidian-project-kb-core/scripts/kb_index_check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/obsidian-project-kb-core/scripts/kb_link_check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/obsidian-project-kb-core/scripts/kb_lint.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/obsidian-project-kb-core/scripts/kb_registry_check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/obsidian-project-kb-core/scripts/kb_scaffold.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/obsidian-project-kb-core/scripts/project_kb.py
skills/planning-with-files/reference.md
skills/plugin-structure/SKILL.md
- Network accessline 72
"name": "Author Name", "email": "author@example.com", "url": "https://example.com" - Network accessline 73
"email": "author@example.com", "url": "https://example.com" }, - Network accessline 74
"url": "https://example.com" - Network accessline 75
}, "homepage": "https://docs.example.com", "repository": "https://github.com/user/plugin-name", - Network accessline 76
"homepage": "https://docs.example.com", - Network accessline 77
"repository": "https://github.com/user/plugin-name", - Access to secretsline 247
[Credential-related source omitted]
skills/plugin-structure/examples/advanced-plugin.md
- Network accessline 111
"name": "DevOps Platform Team", "email": "devops-platform@company.com", "url": "https://company.com/teams/devops" - Network accessline 112
"email": "devops-platform@company.com", "url": "https://company.com/teams/devops" }, - Network accessline 113
"url": "https://company.com/teams/devops" - Network accessline 114
}, "homepage": "https://docs.company.com/plugins/devops", "repository": { - Network accessline 115
"homepage": "https://docs.company.com/plugins/devops", - Network accessline 116
"repository": { "type": "git", "url": "https://github.com/company/devops-plugin.git" - Network accessline 117
"type": "git", "url": "https://github.com/company/devops-plugin.git" }, - Network accessline 118
"url": "https://github.com/company/devops-plugin.git" - Access to secretsline 170
[Credential-related source omitted]
skills/plugin-structure/examples/standard-plugin.md
- Network accessline 48
"email": "quality@example.com" }, "homepage": "https://docs.example.com/plugins/code-quality", - Network accessline 49
}, "homepage": "https://docs.example.com/plugins/code-quality", "repository": "https://github.com/example/code-quality-plugin", - Network accessline 50
"homepage": "https://docs.example.com/plugins/code-quality", - Network accessline 51
"repository": "https://github.com/example/code-quality-plugin",
skills/plugin-structure/references/manifest-reference.md
- Network accessline 95
"name": "Jane Developer", "email": "jane@example.com", "url": "https://janedeveloper.com" - Network accessline 96
"email": "jane@example.com", "url": "https://janedeveloper.com" } - Network accessline 97
"url": "https://janedeveloper.com" - Network accessline 104
{ "author": "Jane Developer <jane@example.com> (https://janedeveloper.com)" - Network accessline 105
"author": "Jane Developer <jane@example.com> (https://janedeveloper.com)" - Network accessline 117
**Type**: String (URL) **Example**: `"https://docs.example.com/plugins/my-plugin"` - Network accessline 118
**Example**: `"https://docs.example.com/plugins/my-plugin"` - Network accessline 135
**Type**: String (URL) or Object **Example**: `"https://github.com/user/plugin-name"` - Network accessline 136
**Example**: `"https://github.com/user/plugin-name"` - Network accessline 142
{ "repository": "https://github.com/user/plugin-name" - Network accessline 143
"repository": "https://github.com/user/plugin-name" - Network accessline 150
"repository": { "type": "git", "url": "https://github.com/user/plugin-name.git", - Network accessline 151
"type": "git", "url": "https://github.com/user/plugin-name.git", "directory": "packages/plugin-name" - Network accessline 152
"url": "https://github.com/user/plugin-name.git", - Network accessline 180
**Full list**: https://spdx.org/licenses/ - Access to secretsline 320
[Credential-related source omitted] - Network accessline 474
"email": "jane@example.com" }, "homepage": "https://docs.example.com/code-review", - Network accessline 475
}, "homepage": "https://docs.example.com/code-review", "repository": "https://github.com/janedev/code-review-assistant", - Network accessline 476
"homepage": "https://docs.example.com/code-review", - Network accessline 477
"repository": "https://github.com/janedev/code-review-assistant", - Network accessline 493
"name": "DevOps Team", "email": "devops@company.com", "url": "https://company.com/devops" - Network accessline 494
"email": "devops@company.com", "url": "https://company.com/devops" }, - Network accessline 495
"url": "https://company.com/devops" - Network accessline 496
}, "homepage": "https://docs.company.com/plugins/devops", "repository": { - Network accessline 497
"homepage": "https://docs.company.com/plugins/devops", - Network accessline 498
"repository": { "type": "git", "url": "https://github.com/company/devops-plugin.git" - Network accessline 499
"type": "git", "url": "https://github.com/company/devops-plugin.git" }, - Network accessline 500
"url": "https://github.com/company/devops-plugin.git"
skills/post-acceptance/references/xquik-promotion.md
skills/publication-chart-skill/scripts/ensure_publication_tooling.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/research-ideation/references/literature-search-strategies.md
- Network accessline 161
**URL 中的 DOI**： - `https://doi.org/10.xxxx/xxxxx` - 直接 DOI 链接 - Network accessline 162
- `https://doi.org/10.xxxx/xxxxx` - 直接 DOI 链接 - Network accessline 163
- `https://dl.acm.org/doi/10.xxxx/xxxxx` - ACM Digital Library - Network accessline 164
- `https://ieeexplore.ieee.org/document/xxxxx` - IEEE（需从页面提取） - Network accessline 165
- `https://arxiv.org/abs/xxxx.xxxxx` - arXiv（DOI 格式：`10.48550/arXiv.xxxx.xxxxx`）
skills/research-ideation/references/zotero-integration-guide.md
- Network accessline 101
**从搜索结果 URL 中识别 DOI**： - `https://doi.org/10.xxxx/xxxxx` — 直接 DOI 链接 - Network accessline 102
- `https://doi.org/10.xxxx/xxxxx` — 直接 DOI 链接 - Network accessline 103
- `https://dl.acm.org/doi/10.xxxx/xxxxx` — ACM Digital Library - Network accessline 104
- `https://arxiv.org/abs/xxxx.xxxxx` — arXiv（DOI：`10.48550/arXiv.xxxx.xxxxx`）
skills/results-analysis/references/statistical-methods.md
- Network accessline 546
- [Nature Statistics Checklist](https://www.nature.com/documents/nr-reporting-summary-flat.pdf) - Network accessline 547
- [ASA Statement on P-Values](https://www.amstat.org/asa/files/pdfs/p-valuestatement.pdf) - Network accessline 548
- [Reporting Statistics in Psychology](https://apastyle.apa.org/instructional-aids/numbers-statistics-guide.pdf)
skills/results-analysis/references/visualization-best-practices.md
- Network accessline 255
- [Ten Simple Rules for Better Figures](https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1003833) - Network accessline 256
- [Okabe-Ito Color Palette](https://jfly.uni-koeln.de/color/) - Network accessline 257
- [Paul Tol's Notes on Colour](https://personal.sron.nl/~pault/)
skills/skill-improver/scripts/backup-skill.sh
- Executable scriptline 1
#!/bin/bash
skills/skill-improver/scripts/verify-update.sh
- Executable scriptline 1
#!/bin/bash
skills/skill-quality-reviewer/scripts/extract-yaml.sh
- Executable scriptline 1
#!/bin/bash
skills/skill-quality-reviewer/scripts/skill-audit.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ui-ux-pro-max/scripts/search.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/uv-package-manager/SKILL.md
- Network accessline 55
# macOS/Linux curl -LsSf https://astral.sh/uv/install.sh | sh - Dangerous shell operationline 56
curl -LsSf https://astral.sh/uv/install.sh | sh - Network accessline 56
curl -LsSf https://astral.sh/uv/install.sh | sh - Network accessline 58
# Windows (PowerShell) powershell -c "irm https://astral.sh/uv/install.ps1 | iex" - Network accessline 59
powershell -c "irm https://astral.sh/uv/install.ps1 | iex" - Network accessline 67
# Using cargo (if you have Rust) cargo install --git https://github.com/astral-sh/uv uv - Network accessline 68
cargo install --git https://github.com/astral-sh/uv uv - Network accessline 188
# Add from git uv add git+https://github.com/user/repo.git - Network accessline 189
uv add git+https://github.com/user/repo.git - Network accessline 191
# Add from git with specific ref uv add git+https://github.com/user/repo.git@v1.0.0 - Network accessline 192
uv add git+https://github.com/user/repo.git@v1.0.0 - Network accessline 321
[tool.uv.sources] # Custom package sources my-package = { git = "https://github.com/user/repo.git" } - Network accessline 323
my-package = { git = "https://github.com/user/repo.git" } - Network accessline 601
# Clone repository git clone https://github.com/user/project.git - Network accessline 602
git clone https://github.com/user/project.git - Network accessline 815
- **Official documentation**: https://docs.astral.sh/uv/ - Network accessline 816
- **GitHub repository**: https://github.com/astral-sh/uv - Network accessline 817
- **Astral blog**: https://astral.sh/blog - Network accessline 818
- **Migration guides**: https://docs.astral.sh/uv/guides/ - Network accessline 819
- **Comparison with other tools**: https://docs.astral.sh/uv/pip/compatibility/
skills/verification-loop/SKILL.md
skills/web-design-reviewer/SKILL.md
- Network accessline 23
1. **Target website must be running** - Local development server (e.g., `http://localhost:3000`) - Network accessline 24
- Local development server (e.g., `http://localhost:3000`) - Network accessline 56
> Please provide the URL of the website to review (e.g., `http://localhost:3000`) - Network accessline 292
[Playwright MCP](https://github.com/microsoft/playwright-mcp) is recommended as the reference implementation for this skill.
skills/web-design-reviewer/references/framework-fixes.md
skills/webapp-testing/LICENSE.txt
skills/webapp-testing/SKILL.md
- Network accessline 58
browser = p.chromium.launch(headless=True) # Always launch chromium in headless mode page = browser.new_page() page.goto('http://localhost:5173') # Server already running and ready - Network accessline 59
page = browser.new_page() page.goto('http://localhost:5173') # Server already running and ready page.wait_for_load_state('networkidle') # CRITICAL: Wait for JS to execute - Network accessline 60
page.goto('http://localhost:5173') # Server already running and ready
skills/webapp-testing/examples/console_logging.py
skills/webapp-testing/examples/element_discovery.py
skills/webapp-testing/examples/static_html_automation.py
- Executable scriptline 1
Executable file
skills/webapp-testing/scripts/with_server.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 26
while time.time() - start_time < timeout: try: with socket.create_connection(('localhost', port), timeout=1): - Network accessline 27
try: with socket.create_connection(('localhost', port), timeout=1): return True - Network accessline 28
with socket.create_connection(('localhost', port), timeout=1):
skills/writing-anti-ai/SKILL.md
- Network accessline 23
This skill identifies and eliminates predictable AI writing patterns from prose, based on [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. - Network accessline 236
Based on [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia/Signs_of_AI_writing), maintained by WikiProject AI Cleanup. Merges content from `humanizer`, `humanizer-zh`, and `stop-slop` skills.
skills/writing-anti-ai/references/patterns-chinese.md
- Network accessline 242
[基于维基百科：AI 写作特征](https://en.wikipedia.org/wiki/Wikipedia/Signs_of_AI_writing)
skills/writing-anti-ai/references/patterns-english.md
- Network accessline 242
[Based on Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia/Signs_of_AI_writing)
skills/zotero-obsidian-bridge/references/PAPER-NOTE-SCHEMA.md
skills/zotero-obsidian-bridge/scripts/verify_paper_notes.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 4 facts
- Contacts doi.org, which SKILL.md, the README and the plugin manifest do not mentioncitation-verification/scripts/api-clients.py:165High confidence
- Contacts doi.org, which SKILL.md, the README and the plugin manifest do not mentioncitation-verification/scripts/format-checker.py:318High confidence
- Contacts api.biorxiv.org, which SKILL.md, the README and the plugin manifest do not mentiondaily-paper-generator/scripts/arxiv_search.py:119High confidence
- Contacts www.biorxiv.org, which SKILL.md, the README and the plugin manifest do not mentiondaily-paper-generator/scripts/arxiv_search.py:173High confidence
Signal confidence: 496 facts
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:6High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:7High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:8High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:6High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:7High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:8High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:9High confidence
- Executable script in code of the plugin configurationhooks/hooks.json:1High confidence
- Executable script in code of the plugin configurationhooks/hooks.json:1High confidence
- Executable script in code of the plugin configurationhooks/hooks.json:1High confidence
- Executable script in code of the plugin configurationhooks/hooks.json:1High confidence
- Executable script in code of the plugin configurationhooks/hooks.json:1High confidence
- Executable script in code of the plugin configurationhooks/hooks.json:1High confidence
- Executable script in code of a file that runsagent-identifier/scripts/validate-agent.sh:1High confidence
- Executable script in prose of a file that runsarchitecture-design/examples/augmentation_example.py:1Low confidence
- Executable script in prose of a file that runsarchitecture-design/examples/custom_dataset.py:1Low confidence
- Executable script in prose of a file that runsarchitecture-design/examples/custom_model.py:1Low confidence
- Executable script in code of a file that runsarchitecture-design/examples/pipeline_example.sh:1High confidence
- Dangerous shell operation in code of the SKILL.mdbug-detective/SKILL.md:158High confidence
- Dangerous shell operation in code of the SKILL.mdbug-detective/SKILL.md:161High confidence
- Dangerous shell operation in code of the SKILL.mdbug-detective/SKILL.md:216High confidence
- Dangerous shell operation in code of the SKILL.mdbug-detective/SKILL.md:221High confidence
- Executable script in prose of a file that runsbug-detective/examples/debugging-workflow.py:1Low confidence
- Executable script in code of a file that runsbug-detective/examples/debugging-workflow.sh:1High confidence
- Dangerous shell operation in a comment of a file that runsbug-detective/examples/debugging-workflow.sh:76Low confidence
- Dangerous shell operation in code of a file that runsbug-detective/examples/debugging-workflow.sh:288High confidence
- Network access in code of a file that runsbug-detective/examples/debugging-workflow.sh:339High confidence
- Executable script in prose of a file that runsbug-detective/examples/error-handling-patterns.py:1Low confidence
- Network access in code of documentationbug-detective/references/common-patterns.md:226Low confidence
- Network access in code of documentationbug-detective/references/common-patterns.md:227Low confidence
- Network access in code of documentationbug-detective/references/common-patterns.md:228Low confidence
- Network access in code of documentationbug-detective/references/common-patterns.md:233Low confidence
- Network access in code of documentationbug-detective/references/common-patterns.md:234Low confidence
- Network access in code of documentationbug-detective/references/common-patterns.md:235Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:25Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:30Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:106Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:182Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:187Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:197Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:198Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:199Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:216Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:217Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:218Low confidence
- Network access in code of documentationcitation-verification/references/api-usage.md:219Low confidence
- Network access in code of documentationcitation-verification/references/common-errors.md:49Low confidence
- Network access in code of documentationcitation-verification/references/common-errors.md:50Low confidence
- Executable script in code of a file that runscitation-verification/scripts/api-clients.py:1High confidence
- Network access in prose of a file that runscitation-verification/scripts/api-clients.py:72Low confidence
and 446 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/agent-identifier/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/agent-identifier/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/agent-identifier/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/agent-identifier/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/agent-identifier/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/galaxy-dawn-claude-scholar/)