Not in the top 1,000 by GitHub stars
Kocoro-lab/Kocoro
A Mac-native AI agent with memory, local computer access, browser control, IM channels, and MCP-native integrations. Built on Shannon.
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
internal/migrate/claudecode/testdata/claude_home_basic/skills/dir-style/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/algorithmic-art/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/brand-guidelines/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/canvas-design/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/claude-api/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/doc-coauthoring/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/frontend-design/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/internal-comms/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/kocoro/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/kocoro-generative-ui/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/mcp-builder/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/pdf-reader/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/skill-creator/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/slack-gif-creator/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/theme-factory/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/web-artifacts-builder/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9afd8644076e → 9afd8644076e
internal/skills/bundled/skills/webapp-testing/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9afd8644076e → 9afd8644076e
View on GitHubAdd to my skills
Verified commit 9afd8644076e95f5fcb97e408c54de860a149614
git clone --filter=blob:none --no-checkout https://github.com/Kocoro-lab/Kocoro.git .hotskills/kocoro-lab-kocoro && git -C .hotskills/kocoro-lab-kocoro checkout --detach 9afd8644076e95f5fcb97e408c54de860a149614
# Copy each selected skill directory from .hotskills/kocoro-lab-kocoro into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/Kocoro-lab/Kocoro.git .hotskills/kocoro-lab-kocoro && git -C .hotskills/kocoro-lab-kocoro checkout --detach 9afd8644076e95f5fcb97e408c54de860a149614
# Copy each selected skill directory from .hotskills/kocoro-lab-kocoro into .agents/skills/<skill-name>/415GitHub stars
1star in 7 days
17skills in this repository
1commit in 30 days
Heat
2.6- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- dir-style
internal/migrate/claudecode/testdata/claude_home_basic/skills/dir-style - algorithmic-art
internal/skills/bundled/skills/algorithmic-art - brand-guidelines
internal/skills/bundled/skills/brand-guidelines - canvas-design
internal/skills/bundled/skills/canvas-design - claude-api
internal/skills/bundled/skills/claude-api - doc-coauthoring
internal/skills/bundled/skills/doc-coauthoring - frontend-design
internal/skills/bundled/skills/frontend-design - internal-comms
internal/skills/bundled/skills/internal-comms - kocoro
internal/skills/bundled/skills/kocoro - kocoro-generative-ui
internal/skills/bundled/skills/kocoro-generative-ui - mcp-builder
internal/skills/bundled/skills/mcp-builder - pdf-reader
internal/skills/bundled/skills/pdf-reader - skill-creator
internal/skills/bundled/skills/skill-creator - slack-gif-creator
internal/skills/bundled/skills/slack-gif-creator - theme-factory
internal/skills/bundled/skills/theme-factory - web-artifacts-builder
internal/skills/bundled/skills/web-artifacts-builder - webapp-testing
internal/skills/bundled/skills/webapp-testing
How it works
dir-style
When your agent uses it
dir layout
What it loads into context
Frontmatter
9 tokensAlways available to the agent
SKILL.md
14 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.mdcore53 bytes
algorithmic-art
When your agent uses it
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
4,151 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
- ALGORITHMIC PHILOSOPHY CREATION
- DEDUCING THE CONCEPTUAL SEED
- P5.JS IMPLEMENTATION
- INTERACTIVE ARTIFACT CREATION
- VARIATIONS & EXPLORATION
- THE CREATIVE PROCESS
- RESOURCES
Scripts executed separately
templates/generator_template.js
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore19,769 bytestemplates/generator_template.jsruns7,826 bytestemplates/viewer.htmlasset20,844 bytes
Read SKILL.md
Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms).
This happens in two steps:
1. Algorithmic Philosophy Creation (.md file)
2. Express by creating p5.js generative art (.html + .js files)
First, undertake this task:
## ALGORITHMIC PHILOSOPHY CREATION
To begin, create an ALGORITHMIC PHILOSOPHY (not static images or templates) that will be interpreted through:
- Computational processes, emergent behavior, mathematical beauty
- Seeded randomness, noise fields, organic systems
- Particles, flows, fields, forcesbrand-guidelines
When your agent uses it
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
518 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
- Brand Guidelines
- Features
- Technical Details
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore2,235 bytes
Read SKILL.md
# Anthropic Brand Styling
## Overview
To access Anthropic's official brand identity and style resources, use this skill.
**Keywords**: branding, corporate identity, visual identity, post-processing, styling, brand colors, typography, Anthropic brand, visual formatting, visual design
## Brand Guidelines
### Colors
**Main Colors:**
canvas-design
When your agent uses it
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
2,353 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 PHILOSOPHY CREATION
- DEDUCING THE SUBTLE REFERENCE
- CANVAS CREATION
- FINAL STEP
- MULTI-PAGE OPTION
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore11,939 bytescanvas-fonts/ArsenalSC-OFL.txtdoc4,373 bytescanvas-fonts/ArsenalSC-Regular.ttfasset165,848 bytescanvas-fonts/BigShoulders-Bold.ttfasset94,528 bytescanvas-fonts/BigShoulders-OFL.txtdoc4,397 bytescanvas-fonts/BigShoulders-Regular.ttfasset94,396 bytescanvas-fonts/Boldonse-OFL.txtdoc4,390 bytescanvas-fonts/Boldonse-Regular.ttfasset77,168 bytescanvas-fonts/BricolageGrotesque-Bold.ttfasset90,952 bytescanvas-fonts/BricolageGrotesque-OFL.txtdoc4,403 bytescanvas-fonts/BricolageGrotesque-Regular.ttfasset90,920 bytescanvas-fonts/CrimsonPro-Bold.ttfasset107,352 bytescanvas-fonts/CrimsonPro-Italic.ttfasset108,828 bytescanvas-fonts/CrimsonPro-OFL.txtdoc4,394 bytescanvas-fonts/CrimsonPro-Regular.ttfasset106,696 bytescanvas-fonts/DMMono-OFL.txtdoc4,392 bytescanvas-fonts/DMMono-Regular.ttfasset48,852 bytescanvas-fonts/EricaOne-OFL.txtdoc4,410 bytescanvas-fonts/EricaOne-Regular.ttfasset24,872 bytescanvas-fonts/GeistMono-Bold.ttfasset78,304 bytescanvas-fonts/GeistMono-OFL.txtdoc4,388 bytescanvas-fonts/GeistMono-Regular.ttfasset78,232 bytescanvas-fonts/Gloock-OFL.txtdoc4,381 bytescanvas-fonts/Gloock-Regular.ttfasset95,156 bytescanvas-fonts/IBMPlexMono-Bold.ttfasset136,008 bytescanvas-fonts/IBMPlexMono-OFL.txtdoc4,363 bytescanvas-fonts/IBMPlexMono-Regular.ttfasset133,796 bytescanvas-fonts/IBMPlexSerif-Bold.ttfasset161,000 bytescanvas-fonts/IBMPlexSerif-BoldItalic.ttfasset169,840 bytescanvas-fonts/IBMPlexSerif-Italic.ttfasset170,004 bytescanvas-fonts/IBMPlexSerif-Regular.ttfasset160,380 bytescanvas-fonts/InstrumentSans-Bold.ttfasset68,084 bytescanvas-fonts/InstrumentSans-BoldItalic.ttfasset70,004 bytescanvas-fonts/InstrumentSans-Italic.ttfasset69,900 bytescanvas-fonts/InstrumentSans-OFL.txtdoc4,403 bytescanvas-fonts/InstrumentSans-Regular.ttfasset68,028 bytescanvas-fonts/InstrumentSerif-Italic.ttfasset70,868 bytescanvas-fonts/InstrumentSerif-Regular.ttfasset69,312 bytescanvas-fonts/Italiana-OFL.txtdoc4,394 bytescanvas-fonts/Italiana-Regular.ttfasset27,184 bytescanvas-fonts/JetBrainsMono-Bold.ttfasset114,828 bytescanvas-fonts/JetBrainsMono-OFL.txtdoc4,399 bytescanvas-fonts/JetBrainsMono-Regular.ttfasset114,904 bytescanvas-fonts/Jura-Light.ttfasset154,308 bytescanvas-fonts/Jura-Medium.ttfasset154,488 bytescanvas-fonts/Jura-OFL.txtdoc4,380 bytescanvas-fonts/LibreBaskerville-OFL.txtdoc4,449 bytescanvas-fonts/LibreBaskerville-Regular.ttfasset147,584 bytescanvas-fonts/Lora-Bold.ttfasset133,828 bytescanvas-fonts/Lora-BoldItalic.ttfasset140,332 bytescanvas-fonts/Lora-Italic.ttfasset139,328 bytescanvas-fonts/Lora-OFL.txtdoc4,423 bytescanvas-fonts/Lora-Regular.ttfasset133,888 bytescanvas-fonts/NationalPark-Bold.ttfasset79,208 bytescanvas-fonts/NationalPark-OFL.txtdoc4,399 bytescanvas-fonts/NationalPark-Regular.ttfasset76,424 bytescanvas-fonts/NothingYouCouldDo-OFL.txtdoc4,363 bytescanvas-fonts/NothingYouCouldDo-Regular.ttfasset32,020 bytescanvas-fonts/Outfit-Bold.ttfasset55,392 bytescanvas-fonts/Outfit-OFL.txtdoc4,389 bytescanvas-fonts/Outfit-Regular.ttfasset54,912 bytescanvas-fonts/PixelifySans-Medium.ttfasset51,072 bytescanvas-fonts/PixelifySans-OFL.txtdoc4,395 bytescanvas-fonts/PoiretOne-OFL.txtdoc4,366 bytescanvas-fonts/PoiretOne-Regular.ttfasset45,244 bytescanvas-fonts/RedHatMono-Bold.ttfasset34,420 bytescanvas-fonts/RedHatMono-OFL.txtdoc4,394 bytescanvas-fonts/RedHatMono-Regular.ttfasset34,488 bytescanvas-fonts/Silkscreen-OFL.txtdoc4,394 bytescanvas-fonts/Silkscreen-Regular.ttfasset31,960 bytescanvas-fonts/SmoochSans-Medium.ttfasset59,704 bytescanvas-fonts/SmoochSans-OFL.txtdoc4,396 bytescanvas-fonts/Tektur-Medium.ttfasset76,248 bytescanvas-fonts/Tektur-OFL.txtdoc4,385 bytescanvas-fonts/Tektur-Regular.ttfasset75,604 bytescanvas-fonts/WorkSans-Bold.ttfasset191,304 bytescanvas-fonts/WorkSans-BoldItalic.ttfasset175,772 bytescanvas-fonts/WorkSans-Italic.ttfasset174,280 bytescanvas-fonts/WorkSans-OFL.txtdoc4,397 bytescanvas-fonts/WorkSans-Regular.ttfasset188,916 bytescanvas-fonts/YoungSerif-OFL.txtdoc4,398 bytescanvas-fonts/YoungSerif-Regular.ttfasset105,136 bytes
Read SKILL.md
These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.
Complete this in two steps:
1. Design Philosophy Creation (.md file)
2. Express by creating it on a canvas (.pdf file or .png file)
First, undertake this task:
## DESIGN PHILOSOPHY CREATION
To begin, create a VISUAL PHILOSOPHY (not layouts or templates) that will be interpreted through:
- Form, space, color, composition
- Images, graphics, shapes, patterns
- Minimal text as visual accentclaude-api
When your agent uses it
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
4,382 tokensWhen the skill is activated
Reference documents
36,582 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Defaults
- Language Detection
- Which Surface Should I Use?
- Architecture
- Current Models (cached: 2026-02-17)
- Thinking & Effort (Quick Reference)
- Compaction (Quick Reference)
- Reading Guide
- When to Use WebFetch
- Common Pitfalls
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore18,276 bytesSKILL.mdcore18,276 bytescsharp/claude-api.mddoc1,758 bytescurl/examples.mddoc4,475 bytesgo/claude-api.mddoc3,980 bytesjava/claude-api.mddoc3,941 bytesphp/claude-api.mddoc1,568 bytespython/agent-sdk/README.mddoc9,869 bytespython/agent-sdk/patterns.mddoc8,208 bytespython/claude-api/README.mddoc10,942 bytespython/claude-api/batches.mddoc4,948 bytespython/claude-api/files-api.mddoc3,881 bytespython/claude-api/streaming.mddoc5,217 bytespython/claude-api/tool-use.mddoc16,730 bytesruby/claude-api.mddoc1,816 bytesshared/error-codes.mddoc7,050 bytesshared/live-sources.mddoc10,727 bytesshared/models.mddoc4,625 bytesshared/tool-use-concepts.mddoc14,761 bytestypescript/agent-sdk/README.mddoc7,839 bytestypescript/agent-sdk/patterns.mddoc3,274 bytestypescript/claude-api/README.mddoc8,627 bytestypescript/claude-api/batches.mddoc2,594 bytestypescript/claude-api/files-api.mddoc2,260 bytestypescript/claude-api/streaming.mddoc5,582 bytestypescript/claude-api/tool-use.mddoc12,821 bytes
Read SKILL.md
# Building LLM-Powered Applications with Claude
This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.
## Defaults
Unless the user requests otherwise:
For the Claude model version, please use Claude Opus 4.6, which you can access via the exact model string `claude-opus-4-6`. Please default to using adaptive thinking (`thinking: {type: "adaptive"}`) for anything remotely complicated. And finally, please default to streaming for any request that may involve long input, long output, or high `max_tokens` — it prevents hitting request timeouts. Use the SDK's `.get_final_message()` / `.finalMessage()` helper to get the complete response if you don't need to handle individual stream events
---
## Language Detection
doc-coauthoring
When your agent uses it
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
3,254 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 Offer This Workflow
- Stage 1: Context Gathering
- Stage 2: Refinement & Structure
- Stage 3: Reader Testing
- Final Review
- Tips for Effective Guidance
Files
SKILL.mdcore15,815 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.
## When to Offer This Workflow
**Trigger conditions:**
- User mentions writing documentation: "write a doc", "draft a proposal", "create a spec", "write up"
- User mentions specific doc types: "PRD", "design doc", "decision doc", "RFC"
- User seems to be starting a substantial writing task
**Initial offer:**
Offer the user a structured workflow for co-authoring the document. Explain the three stages:
frontend-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
88 tokensAlways available to the agent
SKILL.md
857 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.mdcore4,440 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.
internal-comms
When your agent uses it
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
321 tokensWhen the skill is activated
Reference documents
2,082 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- How to use this skill
- Keywords
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore1,511 bytesexamples/3p-updates.mddoc3,274 bytesexamples/company-newsletter.mddoc3,295 bytesexamples/faq-answers.mddoc2,366 bytesexamples/general-comms.mddoc602 bytes
Read SKILL.md
## When to use this skill
To write internal communications, use this skill for:
- 3P updates (Progress, Plans, Problems)
- Company newsletters
- FAQ responses
- Status reports
- Leadership updates
- Project updates
- Incident reports
## How to use this skill
To write any internal communication:
kocoro
When your agent uses it
Inspect AND manage Kocoro platform state — agents, skills, MCP servers, schedules, permissions, config, rules. 中:列出/查看/查询/创建/修改/删除/配置/安装 agent/skill/MCP/计划/权限/规则。 日:一覧/表示/確認/検索/作成/更新/削除/設定/インストール エージェント/スキル/MCPサーバー/スケジュール/権限/ルール。 Use for explicit operations on Kocoro-managed platform state under ~/.shannon/, including configured agents, skills, MCP servers, schedules, permissions, rules, and config. Route only that platform-state portion through the daemon API; mixed requests may and should continue with file, shell, web, and integration tools as appropriate. Do not use this platform-management skill merely to fill a task-time capability gap when discover_installable_skills is available.
What it loads into context
Frontmatter
325 tokensAlways available to the agent
SKILL.md
2,410 tokensWhen the skill is activated
Reference documents
65,886 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Task-time capability gaps
- Common Operations
- Security
- Style
Files
SKILL.mdcore10,308 bytesSKILL.mdcore10,308 bytesSKILL.mdcore10,308 bytesSKILL.mdcore10,308 bytesreferences/agents.mddoc36,790 bytesreferences/auth.mddoc10,290 bytesreferences/calendar.mddoc11,250 bytesreferences/cancel.mddoc5,893 bytesreferences/computer-use.mddoc26,015 bytesreferences/config.mddoc27,250 bytesreferences/desktop-rpc.mddoc7,383 bytesreferences/events.mddoc28,588 bytesreferences/feishu.mddoc11,153 bytesreferences/instructions.mddoc5,122 bytesreferences/mcp.mddoc14,186 bytesreferences/memory.mddoc7,442 bytesreferences/permissions.mddoc10,637 bytesreferences/project-init.mddoc3,441 bytesreferences/queue.mddoc4,414 bytesreferences/recipes.mddoc18,550 bytesreferences/rewind.mddoc2,955 bytesreferences/schedules.mddoc13,357 bytesreferences/session-sync.mddoc3,151 bytesreferences/skills.mddoc29,611 bytes
Read SKILL.md
# Kocoro — Platform Configuration Assistant
You help users set up and manage their Kocoro platform.
Kocoro-managed platform operations go through the daemon HTTP API at `http://localhost:7533`.
Use the `http` tool for those operations — with ONE exception: **schedules** use the native `schedule_*` tools (see "Create schedule" below). Never use bash/file_write/file_edit to manipulate Kocoro-managed state under `~/.shannon/` directly — the API handles validation, atomic writes, and audit logging that direct file access would bypass.
This routing rule is scoped. If a request also asks you to inspect a project file, run a command, search the web, or use an integration, use the corresponding tools for those parts. Activating this skill never means “HTTP only” for the whole run.
## Task-time capability gaps
When `discover_installable_skills` is available and the current task needs a
capability that is not in the visible installed skills, call it first. Do not
guess a `use_skill` name, call `/skills/downloadable` orkocoro-generative-ui
When your agent uses it
Generate interactive, inline HTML/SVG widgets (charts, diagrams, forms, dashboards, illustrations) that render in sandboxed iframes inside Kocoro Desktop chat. Use when the user asks to "visualize", "chart", "diagram", "explain visually", "show me", or when data is denser than a paragraph of prose.
What it loads into context
Frontmatter
211 tokensAlways available to the agent
SKILL.md
2,640 tokensWhen the skill is activated
Reference documents
16,028 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Output Contract
- Streaming Safety
- CDN allowlist (CSP-enforced)
- Design system
- Color palette (9 ramps × 7 stops)
- Use case router
- Scope
- Forbidden
- Accessibility
- Output discipline
- Sharing externally (optional)
Files
SKILL.mdcore10,205 bytesSKILL.mdcore10,205 bytesreferences/charts.mddoc3,104 bytesreferences/diagrams.mddoc38,101 bytesreferences/maps.mddoc2,205 bytesreferences/svg-setup.mddoc9,389 bytesreferences/ui-components.mddoc6,943 bytes
Read SKILL.md
# Kocoro Generative UI
You produce rich visual content — SVG diagrams and HTML interactive widgets —
that renders inline in the Kocoro Desktop conversation, token-by-token, in a
WKWebView sandbox.
> **Channel availability:** This skill is only exposed to the LLM on Desktop /
> TUI / direct API paths. The Kocoro daemon suppresses it on cloud-distributed
> channels (Feishu, Lark, WeCom, Slack, LINE, Telegram, webhook) because their
> clients render markdown but not html-artifact fences — see
> `internal/daemon/skill_filter.go` (`desktopOnlySkills`).
## Output Contract
mcp-builder
When your agent uses it
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,938 tokensWhen the skill is activated
Reference documents
18,723 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- 🚀 High-Level Workflow
- 📚 Documentation Library
Scripts executed separately
scripts/connections.pyscripts/evaluation.py
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore9,092 bytesreference/evaluation.mddoc21,663 bytesreference/mcp_best_practices.mddoc7,330 bytesreference/node_mcp_server.mddoc28,550 bytesreference/python_mcp_server.mddoc25,099 bytesscripts/connections.pyruns4,875 bytesscripts/evaluation.pyruns12,579 bytesscripts/example_evaluation.xmlasset1,194 bytesscripts/requirements.txtdoc29 bytes
Read SKILL.md
# MCP Server Development Guide
## Overview
Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.
---
# Process
## 🚀 High-Level Workflow
Creating a high-quality MCP server involves four main phases:
pdf-reader
When your agent uses it
Analyze PDF files attached by the user. Activates automatically when user uploads a PDF. Handles both text-based and scanned/image-based PDFs using file_read's built-in PDF rendering.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
473 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
- How file_read handles PDFs
- Workflow
- Tips
Files
SKILL.mdcore1,930 bytesSKILL.mdcore1,930 bytesSKILL.mdcore1,930 bytesSKILL.mdcore1,930 bytesSKILL.mdcore1,930 bytes
Read SKILL.md
# PDF Reader
Analyze PDF files using the `file_read` tool which natively supports PDF rendering.
## How file_read handles PDFs
- `file_read` with a `.pdf` path renders pages as images for vision analysis
- Parameters: `offset` = start page (0-based), `limit` = max pages (default 5)
- Each page is rendered at 144 DPI, resized to 1568px max dimension
- Returns image blocks that you can analyze with vision
## Workflow
1. **Read the PDF**: Call `file_read` with the PDF path. It will render pages as images automatically.skill-creator
When your agent uses it
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
7,241 tokensWhen the skill is activated
Reference documents
9,476 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Communicating with the user
- Creating a skill
- Running and evaluating test cases
- Improving the skill
- Advanced: Blind comparison
- Description Optimization
- Claude.ai-specific instructions
- Cowork-Specific Instructions
- Reference files
Scripts executed separately
eval-viewer/generate_review.pyscripts/__init__.pyscripts/aggregate_benchmark.pyscripts/generate_report.pyscripts/improve_description.pyscripts/package_skill.pyscripts/quick_validate.pyscripts/run_eval.pyscripts/run_loop.pyscripts/utils.py
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore33,168 bytesSKILL.mdcore33,168 bytesSKILL.mdcore33,168 bytesSKILL.mdcore33,168 bytesSKILL.mdcore33,168 bytesSKILL.mdcore33,168 bytesagents/analyzer.mddoc10,376 bytesagents/comparator.mddoc7,287 bytesagents/grader.mddoc9,049 bytesassets/eval_review.htmlasset7,058 byteseval-viewer/generate_review.pyruns16,365 byteseval-viewer/viewer.htmlasset44,998 bytesreferences/schemas.mddoc12,061 bytesscripts/__init__.pyruns0 bytesscripts/aggregate_benchmark.pyruns14,386 bytesscripts/generate_report.pyruns12,847 bytesscripts/improve_description.pyruns11,116 bytesscripts/package_skill.pyruns4,234 bytesscripts/quick_validate.pyruns4,013 bytesscripts/run_eval.pyruns11,464 bytesscripts/run_loop.pyruns13,605 bytesscripts/utils.pyruns1,661 bytes
Read SKILL.md
# Skill Creator
A skill for creating new skills and iteratively improving them.
At a high level, the process of creating a skill goes like this:
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and run claude-with-access-to-the-skill on them
- Help the user evaluate the results both qualitatively and quantitatively
- While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
- Use the `eval-viewer/generate_review.py` script to show the user the results for them to look at, and also let them look at the quantitative metrics
- Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
- Repeat until you're satisfiedslack-gif-creator
When your agent uses it
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
1,983 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
- Slack Requirements
- Core Workflow
- Drawing Graphics
- Available Utilities
- Animation Concepts
- Optimization Strategies
- Philosophy
- Dependencies
Scripts executed separately
core/easing.pycore/frame_composer.pycore/gif_builder.pycore/validators.py
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytesSKILL.mdcore7,841 bytescore/easing.pyruns6,265 bytescore/frame_composer.pyruns4,548 bytescore/gif_builder.pyruns9,847 bytescore/validators.pyruns3,785 bytesrequirements.txtdoc66 bytes
Read SKILL.md
# Slack GIF Creator
A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack.
## Slack Requirements
**Dimensions:**
- Emoji GIFs: 128x128 (recommended)
- Message GIFs: 480x480
**Parameters:**
- FPS: 10-30 (lower is smaller file size)
- Colors: 48-128 (fewer = smaller file size)
- Duration: Keep under 3 seconds for emoji GIFstheme-factory
When your agent uses it
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
659 tokensWhen the skill is activated
Reference documents
1,429 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Usage Instructions
- Themes Available
- Theme Details
- Application Process
- Create your Own Theme
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore3,124 bytestheme-showcase.pdfasset124,310 bytesthemes/arctic-frost.mddoc544 bytesthemes/botanical-garden.mddoc519 bytesthemes/desert-rose.mddoc496 bytesthemes/forest-canopy.mddoc506 bytesthemes/golden-hour.mddoc528 bytesthemes/midnight-galaxy.mddoc513 bytesthemes/modern-minimalist.mddoc549 bytesthemes/ocean-depths.mddoc555 bytesthemes/sunset-boulevard.mddoc558 bytesthemes/tech-innovation.mddoc547 bytes
Read SKILL.md
# Theme Factory Skill
This skill provides a curated collection of professional font and color themes themes, each with carefully selected color palettes and font pairings. Once a theme is chosen, it can be applied to any artifact.
## Purpose
To apply consistent, professional styling to presentation slide decks, use this skill. Each theme includes:
- A cohesive color palette with hex codes
- Complementary font pairings for headers and body text
- A distinct visual identity suitable for different contexts and audiences
## Usage Instructions
web-artifacts-builder
When your agent uses it
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
699 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 & Style Guidelines
- Quick Start
- Reference
Scripts executed separately
scripts/bundle-artifact.shscripts/init-artifact.sh
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore3,087 bytesSKILL.mdcore3,087 bytesSKILL.mdcore3,087 bytesSKILL.mdcore3,087 bytesscripts/bundle-artifact.shruns1,517 bytesscripts/init-artifact.shruns9,924 bytesscripts/shadcn-components.tar.gzasset19,955 bytes
Read SKILL.md
# Web Artifacts Builder
To build powerful frontend claude.ai artifacts, follow these steps:
1. Initialize the frontend repo using `scripts/init-artifact.sh`
2. Develop your artifact by editing the generated code
3. Bundle all code into a single HTML file using `scripts/bundle-artifact.sh`
4. Display artifact to user
5. (Optional) Test the artifact
**Stack**: React 18 + TypeScript + Vite + Parcel (bundling) + Tailwind CSS + shadcn/ui
## Design & Style Guidelines
VERY IMPORTANT: To avoid what is often referred to as "AI slop", avoid using excessive centered layouts, purple gradients, uniform rounded corners, and Inter font.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
46 tokensAlways available to the agent
SKILL.md
884 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.mdcore3,913 bytesSKILL.mdcore3,913 bytesSKILL.mdcore3,913 bytesSKILL.mdcore3,913 bytesSKILL.mdcore3,913 bytesSKILL.mdcore3,913 bytesSKILL.mdcore3,913 bytesSKILL.mdcore3,913 bytesSKILL.mdcore3,913 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 selectorsSkills included
- dir-style
- algorithmic-art
- brand-guidelines
- canvas-design
- claude-api
- doc-coauthoring
- frontend-design
- internal-comms
- kocoro
- kocoro-generative-ui
- mcp-builder
- pdf-reader
- skill-creator
- slack-gif-creator
- theme-factory
- web-artifacts-builder
- webapp-testing
Repository facts
- License
- MIT
- Created
- Feb 23, 2026
- Last pushed
- Oct 14, 2026
- Forks
- 133
- Open issues
- 18
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 35 notes
internal/skills/bundled/skills/claude-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/kocoro/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/kocoro/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/kocoro/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/kocoro/references/computer-use.md:28Analysis incomplete: physical or joined line exceeds character limitinternal/skills/bundled/skills/kocoro-generative-ui/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/pdf-reader/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/pdf-reader/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/pdf-reader/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/pdf-reader/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/skill-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/skill-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/skill-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/skill-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/skill-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/slack-gif-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/slack-gif-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/slack-gif-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/slack-gif-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedinternal/skills/bundled/skills/slack-gif-creator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 1 broad permissionin 1 file: pdf-reader/SKILL.md:1
- 13 dangerous shell commandsin 5 files: kocoro/references/permissions.md:8 kocoro/references/agents.md:77 kocoro/references/config.md:86 and 2 more
- 395 network referencesin 78 files: claude-api/shared/live-sources.md:16 kocoro/references/feishu.md:33 kocoro/references/recipes.md:11 and 75 more
- No hidden or obfuscated text
- 8 instruction override signalsin 2 files: claude-api/typescript/agent-sdk/README.md:65 kocoro/references/config.md:79
- 23 executable scriptsin 23 files: algorithmic-art/templates/generator_template.js:1 mcp-builder/scripts/connections.py:1 mcp-builder/scripts/evaluation.py:1 and 20 more
- 83 references to secretsin 24 files: kocoro/references/auth.md:5 claude-api/curl/examples.md:8 kocoro/references/skills.md:139 and 21 more
- No requests to vote in Hot
Show all 523 signals by file
internal/skills/bundled/skills/algorithmic-art/LICENSE.txt
internal/skills/bundled/skills/algorithmic-art/SKILL.md
- Network accessline 278
<head> <!-- p5.js from CDN - always available --> <script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js"></script> - Network accessline 279
<!-- p5.js from CDN - always available --> <script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js"></script> <style> - Network accessline 280
<script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js"></script>
internal/skills/bundled/skills/algorithmic-art/templates/generator_template.js
- Executable scriptline 1
Executable file
internal/skills/bundled/skills/algorithmic-art/templates/viewer.html
- Network accessline 21
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Generative Art Viewer</title> <script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js"></script> - Network accessline 22
<title>Generative Art Viewer</title> <script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js"></script> <link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 23
<script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js"></script> - Network accessline 24
<link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 25
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 26
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@400;500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
internal/skills/bundled/skills/brand-guidelines/LICENSE.txt
internal/skills/bundled/skills/canvas-design/LICENSE.txt
internal/skills/bundled/skills/canvas-design/canvas-fonts/ArsenalSC-OFL.txt
internal/skills/bundled/skills/canvas-design/canvas-fonts/BigShoulders-OFL.txt
- Network accessline 1
Copyright 2019 The Big Shoulders Project Authors (https://github.com/xotypeco/big_shoulders) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/Boldonse-OFL.txt
- Network accessline 1
Copyright 2024 The Boldonse Project Authors (https://github.com/googlefonts/boldonse) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/BricolageGrotesque-OFL.txt
- Network accessline 1
Copyright 2022 The Bricolage Grotesque Project Authors (https://github.com/ateliertriay/bricolage) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/CrimsonPro-OFL.txt
- Network accessline 1
Copyright 2018 The Crimson Pro Project Authors (https://github.com/Fonthausen/CrimsonPro) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/DMMono-OFL.txt
- Network accessline 1
Copyright 2020 The DM Mono Project Authors (https://www.github.com/googlefonts/dm-mono) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/EricaOne-OFL.txt
internal/skills/bundled/skills/canvas-design/canvas-fonts/GeistMono-OFL.txt
- Network accessline 1
Copyright 2024 The Geist Project Authors (https://github.com/vercel/geist-font.git) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/Gloock-OFL.txt
- Network accessline 1
Copyright 2022 The Gloock Project Authors (https://github.com/duartp/gloock) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/IBMPlexMono-OFL.txt
internal/skills/bundled/skills/canvas-design/canvas-fonts/InstrumentSans-OFL.txt
- Network accessline 1
Copyright 2022 The Instrument Sans Project Authors (https://github.com/Instrument/instrument-sans) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/Italiana-OFL.txt
internal/skills/bundled/skills/canvas-design/canvas-fonts/JetBrainsMono-OFL.txt
- Network accessline 1
Copyright 2020 The JetBrains Mono Project Authors (https://github.com/JetBrains/JetBrainsMono) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/Jura-OFL.txt
- Network accessline 1
Copyright 2019 The Jura Project Authors (https://github.com/ossobuffo/jura) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/LibreBaskerville-OFL.txt
- Network accessline 1
Copyright 2012 The Libre Baskerville Project Authors (https://github.com/impallari/Libre-Baskerville) with Reserved Font Name Libre Baskerville. - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/Lora-OFL.txt
- Network accessline 1
Copyright 2011 The Lora Project Authors (https://github.com/cyrealtype/Lora-Cyrillic), with Reserved Font Name "Lora". - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/NationalPark-OFL.txt
- Network accessline 1
Copyright 2025 The National Park Project Authors (https://github.com/benhoepner/National-Park) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/NothingYouCouldDo-OFL.txt
internal/skills/bundled/skills/canvas-design/canvas-fonts/Outfit-OFL.txt
- Network accessline 1
Copyright 2021 The Outfit Project Authors (https://github.com/Outfitio/Outfit-Fonts) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/PixelifySans-OFL.txt
- Network accessline 1
Copyright 2021 The Pixelify Sans Project Authors (https://github.com/eifetx/Pixelify-Sans) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/PoiretOne-OFL.txt
internal/skills/bundled/skills/canvas-design/canvas-fonts/RedHatMono-OFL.txt
- Network accessline 1
Copyright 2024 The Red Hat Project Authors (https://github.com/RedHatOfficial/RedHatFont) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/Silkscreen-OFL.txt
- Network accessline 1
Copyright 2001 The Silkscreen Project Authors (https://github.com/googlefonts/silkscreen) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/SmoochSans-OFL.txt
- Network accessline 1
Copyright 2016 The Smooch Sans Project Authors (https://github.com/googlefonts/smooch-sans) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/Tektur-OFL.txt
- Network accessline 1
Copyright 2023 The Tektur Project Authors (https://www.github.com/hyvyys/Tektur) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/WorkSans-OFL.txt
- Network accessline 1
Copyright 2019 The Work Sans Project Authors (https://github.com/weiweihuanghuang/Work-Sans) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/canvas-design/canvas-fonts/YoungSerif-OFL.txt
- Network accessline 1
Copyright 2023 The Young Serif Project Authors (https://github.com/noirblancrouge/YoungSerif) - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
internal/skills/bundled/skills/claude-api/LICENSE.txt
internal/skills/bundled/skills/claude-api/SKILL.md
- Network accessline 60
| Go | Yes (beta) | No | `BetaToolRunner` in `toolrunner` pkg | | Ruby | Yes (beta) | No | `BaseTool` + `tool_runner` in beta | | cURL | N/A | N/A | Raw HTTP, no SDK features - Network accessline 61
| Ruby | Yes (beta) | No | `BaseTool` + `tool_runner` in beta | | cURL | N/A | N/A | Raw HTTP, no SDK features | | C# | No | No | Official SDK - Network accessline 62
| cURL | N/A | N/A | Raw HTTP, no SDK features | - Network accessline 211
> **Note:** For Java, Go, Ruby, C#, PHP, and cURL — these have a single file each covering all basics. Read that file plus `shared/tool-use-concepts.md` and `shared/error-codes.md` as needed.
internal/skills/bundled/skills/claude-api/csharp/claude-api.md
internal/skills/bundled/skills/claude-api/curl/examples.md
- Network accessline 1
# Claude API — cURL / Raw HTTP - Access to secretsline 8
[Credential-related source omitted] - Network accessline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 18
[Credential-related source omitted] - Network accessline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Network accessline 73
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Network accessline 98
[Credential-related source omitted] - Access to secretsline 98
[Credential-related source omitted] - Access to secretsline 100
[Credential-related source omitted] - Network accessline 137
# Opus 4.6: adaptive thinking (recommended) curl https://api.anthropic.com/v1/messages \ - Network accessline 138
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Access to secretsline 140
[Credential-related source omitted]
internal/skills/bundled/skills/claude-api/go/claude-api.md
- Access to secretsline 19
[Credential-related source omitted]
internal/skills/bundled/skills/claude-api/java/claude-api.md
- Access to secretsline 29
[Credential-related source omitted]
internal/skills/bundled/skills/claude-api/php/claude-api.md
internal/skills/bundled/skills/claude-api/python/agent-sdk/patterns.md
- Access to secretsline 164
[Credential-related source omitted]
internal/skills/bundled/skills/claude-api/python/claude-api/README.md
- Access to secretsline 14
[Credential-related source omitted] - Access to secretsline 18
[Credential-related source omitted] - Network accessline 95
"source": { "type": "url", "url": "https://example.com/image.png" - Network accessline 96
"type": "url", "url": "https://example.com/image.png" } - Network accessline 97
"url": "https://example.com/image.png"
internal/skills/bundled/skills/claude-api/python/claude-api/tool-use.md
- Network accessline 54
**Beta.** Convert [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) tools, prompts, and resources to Anthropic API types for use with the tool runner. Requires `pip install anthropic[mcp]` (Python 3.10+). - Network accessline 456
- `https://github.com/anthropics/anthropic-sdk-python/blob/main/examples/memory/basic.py`
internal/skills/bundled/skills/claude-api/ruby/claude-api.md
internal/skills/bundled/skills/claude-api/shared/error-codes.md
internal/skills/bundled/skills/claude-api/shared/live-sources.md
- Network accessline 16
| Topic | URL | Extraction Prompt | | --------------- | ---------------------------------------------- - Network accessline 17
| --------------- | --------------------------------------------------------------------- | ------------------------------------------------------------------------------- | | Models Overview | `https://platform.claude.com/docs/en/about-cla - Network accessline 18
| Models Overview | `https://platform.claude.com/docs/en/about-claude/models/overview.md` | "Extract current model IDs, context windows, and pricing for all Claude models" | - Network accessline 19
| Pricing | `https://platform.claude.com/docs/en/pricing.md` | "Extract current pricing per million tokens for input and output" | - Network accessline 23
| Topic | URL | Extraction Prompt | | ----------------- | ---------------------------- - Network accessline 24
| ----------------- | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | | Extended Thinking | `https://platform.claude.com - Network accessline 25
| Extended Thinking | `https://platform.claude.com/docs/en/build-with-claude/extended-thinking.md` | "Extract extended thinking parameters, budget_tokens requirements, and usage examples" | - Network accessline 26
| Adaptive Thinking | `https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking.md` | "Extract adaptive thinking setup, effort levels, and Claude Opus 4.6 usage examples" | - Network accessline 27
| Effort Parameter | `https://platform.claude.com/docs/en/build-with-claude/effort.md` | "Extract effort levels, cost-quality tradeoffs, and interaction with thinking" | - Network accessline 28
| Tool Use | `https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview.md` | "Extract tool definition schema, tool_choice options, and handling tool results" | - Network accessline 29
| Streaming | `https://platform.claude.com/docs/en/build-with-claude/streaming.md` | "Extract streaming event types, SDK examples, and best practices" | - Network accessline 30
| Prompt Caching | `https://platform.claude.com/docs/en/build-with-claude/prompt-caching.md` | "Extract cache_control usage, pricing benefits, and implementation examples" | - Network accessline 34
| Topic | URL | Extraction Prompt | | ----------- | ------------------------------------------------------------------- - Network accessline 35
| ----------- | ---------------------------------------------------------------------- | ----------------------------------------------------------------- | | Vision | `https://platform.claude.com/docs/en/build-with-claude/vision.md` - Network accessline 36
| Vision | `https://platform.claude.com/docs/en/build-with-claude/vision.md` | "Extract supported image formats, size limits, and code examples" | - Network accessline 37
| PDF Support | `https://platform.claude.com/docs/en/build-with-claude/pdf-support.md` | "Extract PDF handling capabilities, limits, and examples" | - Network accessline 41
| Topic | URL | Extraction Prompt | | ---------------- | -------------- - Network accessline 42
| ---------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- | | Batch Processing | `https://platf - Network accessline 43
| Batch Processing | `https://platform.claude.com/docs/en/build-with-claude/batch-processing.md` | "Extract batch API endpoints, request format, and polling for results" | | Files API | `https://platf - Network accessline 44
| Files API | `https://platform.claude.com/docs/en/build-with-claude/files.md` | "Extract file upload, download, and referencing in messages, including supported types and beta header" | - Network accessline 45
| Token Counting | `https://platform.claude.com/docs/en/build-with-claude/token-counting.md` | "Extract token counting API usage and examples" | - Network accessline 46
| Rate Limits | `https://platform.claude.com/docs/en/api/rate-limits.md` | "Extract current rate limits by tier and model" | - Network accessline 47
| Errors | `https://platform.claude.com/docs/en/api/errors.md` | "Extract HTTP error codes, meanings, and retry guidance" | - Network accessline 51
| Topic | URL | Extraction Prompt | | -------------- | ---------------------- - Network accessline 52
| -------------- | -------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | | Code Execution | `https://platform.clau - Network accessline 53
| Code Execution | `https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool.md` | "Extract code execution tool setup, file upload, container reuse, and response handling" | - Network accessline 54
| Computer Use | `https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use.md` | "Extract computer use tool setup, capabilities, and implementation examples" | - Network accessline 58
| Topic | URL | Extraction Prompt | | ------------------ | ------------------------------------------------------------ - Network accessline 59
| ------------------ | ----------------------------------------------------------------------------- | --------------------------------------------------- | | Structured Outputs | `https://platform.claude.com/docs/en/build-with-claude/struc - Network accessline 60
| Structured Outputs | `https://platform.claude.com/docs/en/build-with-claude/structured-outputs.md` | "Extract output_config.format usage and schema enforcement" | - Network accessline 61
| Compaction | `https://platform.claude.com/docs/en/build-with-claude/compaction.md` | "Extract compaction setup, trigger config, and streaming with compaction" | - Network accessline 62
| Citations | `https://platform.claude.com/docs/en/build-with-claude/citations.md` | "Extract citation format and implementation" | - Network accessline 63
| Context Windows | `https://platform.claude.com/docs/en/build-with-claude/context-windows.md` | "Extract context window sizes and token management" | - Network accessline 69
| SDK | URL | Description | | ---------- | --------------------------------------------------------- | ------------------------------ | | Python | `https:// - Network accessline 70
| ---------- | --------------------------------------------------------- | ------------------------------ | | Python | `https://github.com/anthropics/anthropic-sdk-python` | `anthropic` pip package source | | TypeScript | `https://g - Network accessline 71
| Python | `https://github.com/anthropics/anthropic-sdk-python` | `anthropic` pip package source | - Network accessline 72
| TypeScript | `https://github.com/anthropics/anthropic-sdk-typescript` | `@anthropic-ai/sdk` npm source | - Network accessline 73
| Java | `https://github.com/anthropics/anthropic-sdk-java` | `anthropic-java` Maven source | - Network accessline 74
| Go | `https://github.com/anthropics/anthropic-sdk-go` | Go module source | - Network accessline 75
| Ruby | `https://github.com/anthropics/anthropic-sdk-ruby` | `anthropic` gem source | - Network accessline 76
| C# | `https://github.com/anthropics/anthropic-sdk-csharp` | NuGet package source | - Network accessline 77
| PHP | `https://github.com/anthropics/anthropic-sdk-php` | Composer package source | - Network accessline 85
| Topic | URL | Extraction Prompt | | -------------------- | ----------------------------------------------------------- | - Network accessline 86
| -------------------- | ----------------------------------------------------------- | --------------------------------------------------------------- | | Agent SDK Overview | `https://platform.claude.com/docs/en/agent-sdk.md` | - Network accessline 87
| Agent SDK Overview | `https://platform.claude.com/docs/en/agent-sdk.md` | "Extract the Agent SDK overview, key features, and use cases" | - Network accessline 88
| Agent SDK Python | `https://github.com/anthropics/claude-agent-sdk-python` | "Extract Python SDK installation, imports, and basic usage" | - Network accessline 89
| Agent SDK TypeScript | `https://github.com/anthropics/claude-agent-sdk-typescript` | "Extract TypeScript SDK installation, imports, and basic usage" | - Network accessline 93
| Topic | URL | Extraction Prompt | | -------------- | ----------------------------------------------- - Network accessline 94
| -------------- | ----------------------------------------------------------------------------------------- | ------------------------------------------------------------ | | Python SDK | `https://raw.githubusercontent.com/anthropics/c - Network accessline 95
| Python SDK | `https://raw.githubusercontent.com/anthropics/claude-agent-sdk-python/main/README.md` | "Extract Python SDK API reference, classes, and methods" | - Network accessline 96
| TypeScript SDK | `https://raw.githubusercontent.com/anthropics/claude-agent-sdk-typescript/main/README.md` | "Extract TypeScript SDK API reference, types, and functions" | - Network accessline 100
| Package | URL | Description | | ----------------------------------- | -------------------------------------------------------------- | -- - Network accessline 101
| ----------------------------------- | -------------------------------------------------------------- | ------------------------- | | claude-agent-sdk (Python) | `https://pypi.org/project/claude-agent-sdk/` | Py - Network accessline 102
| claude-agent-sdk (Python) | `https://pypi.org/project/claude-agent-sdk/` | Python package on PyPI | - Network accessline 103
| @anthropic-ai/claude-agent-sdk (TS) | `https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk` | TypeScript package on npm | - Network accessline 107
| Resource | URL | Description | | -------------- | ----------------------------------------------------------- | ----------------------------------- | | - Network accessline 108
| -------------- | ----------------------------------------------------------- | ----------------------------------- | | Python SDK | `https://github.com/anthropics/claude-agent-sdk-python` | Python package source | | - Network accessline 109
| Python SDK | `https://github.com/anthropics/claude-agent-sdk-python` | Python package source | - Network accessline 110
| TypeScript SDK | `https://github.com/anthropics/claude-agent-sdk-typescript` | TypeScript/Node.js package source | - Network accessline 111
| MCP Servers | `https://github.com/modelcontextprotocol` | Official MCP server implementations |
internal/skills/bundled/skills/claude-api/shared/tool-use-concepts.md
- Network accessline 81
Set a `max_continuations` limit (e.g., 5) to prevent infinite loops. For the full guide, see: `https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons` - Network accessline 199
- URL: `https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling` - Network accessline 209
- URL: `https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool` - Network accessline 219
- URL: `https://platform.claude.com/docs/en/agents-and-tools/tool-use/implement-tool-use` - Network accessline 229
- URL: `https://platform.claude.com/docs/en/agents-and-tools/computer-use/overview` - Network accessline 248
- Docs: `https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool.md` - Network accessline 305
- URL: `https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview`
internal/skills/bundled/skills/claude-api/typescript/agent-sdk/README.md
- Instruction override signalline 65
- `"acceptEdits"`: Auto-accept file edits - `"dontAsk"`: Don't prompt (useful for CI/CD) - `"bypassPermissions"`: Skip all prompts (requires `allowDangerouslySkipPermissions: true` in options) - Instruction override signalline 67
- `"bypassPermissions"`: Skip all prompts (requires `allowDangerouslySkipPermissions: true` in options) - Instruction override signalline 157
| `disallowedTools` | array | Tools to explicitly disallow | | `permissionMode` | string | How to handle permission prompts - Instruction override signalline 158
| `permissionMode` | string | How to handle permission prompts | | `allowDangerouslySkipPermissions` | bool | Must be `true` to use `permissionMode: "bypassPermissions"` - Instruction override signalline 159
| `allowDangerouslySkipPermissions` | bool | Must be `true` to use `permissionMode: "bypassPermissions"` |
internal/skills/bundled/skills/claude-api/typescript/claude-api/README.md
- Access to secretsline 14
[Credential-related source omitted] - Network accessline 62
{ type: "image", source: { type: "url", url: "https://example.com/image.png" }, - Network accessline 63
type: "image", source: { type: "url", url: "https://example.com/image.png" }, }, - Network accessline 64
source: { type: "url", url: "https://example.com/image.png" },
internal/skills/bundled/skills/claude-api/typescript/claude-api/tool-use.md
- Network accessline 403
- `https://github.com/anthropics/anthropic-sdk-typescript/blob/main/examples/tools-helpers-memory.ts`
internal/skills/bundled/skills/doc-coauthoring/SKILL.md
internal/skills/bundled/skills/frontend-design/LICENSE.txt
internal/skills/bundled/skills/internal-comms/LICENSE.txt
internal/skills/bundled/skills/kocoro-generative-ui/SKILL.md
- Network accessline 40
<h2 class="sr-only">Bar chart of Q1 revenue across three regions</h2> <div style="position:relative;height:240px"><canvas id="c1"></canvas></div> <script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.js"></scr - Network accessline 41
<div style="position:relative;height:240px"><canvas id="c1"></canvas></div> <script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.js"></script> <script> - Network accessline 42
<script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.js"></script> - Network accessline 84
call arbitrary external APIs, your own backend, `raw.githubusercontent.com`, or anything else — only static assets from these four CDNs. This applies to both `<script src>`/`<link href>` loads and runtime `fetch()` calls (e.g. D3 - Network accessline 85
or anything else — only static assets from these four CDNs. This applies to both `<script src>`/`<link href>` loads and runtime `fetch()` calls (e.g. D3 topology JSON from jsdelivr is fine; fetching a weather API is not). - Network accessline 86
both `<script src>`/`<link href>` loads and runtime `fetch()` calls (e.g. D3
internal/skills/bundled/skills/kocoro-generative-ui/references/charts.md
- Network accessline 5
<canvas id="myChart"></canvas> </div> <script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.js"></script> - Network accessline 6
</div> <script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.js"></script> <script> - Network accessline 7
<script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.js"></script> - Network accessline 20
- **Canvas sizing**: set height ONLY on the wrapper div, never on the canvas element itself. Use position: relative on the wrapper and responsive: true, maintainAspectRatio: false in Chart.js options. Never set CSS height directly on canvas - Network accessline 21
- For horizontal bar charts: wrapper div height should be at least (number_of_bars * 40) + 80 pixels. - Load UMD build via `<script src="https://cdnjs.cloudflare.com/ajax/libs/...">` — sets `window.Chart` global. Follow with plain `<script> - Network accessline 22
- Load UMD build via `<script src="https://cdnjs.cloudflare.com/ajax/libs/...">` — sets `window.Chart` global. Follow with plain `<script>` (no `type="module"`).
internal/skills/bundled/skills/kocoro-generative-ui/references/diagrams.md
- Network accessline 192
<div id="erd"></div> <script type="module"> import mermaid from 'https://esm.sh/mermaid@11/dist/mermaid.esm.min.mjs'; - Network accessline 193
<script type="module"> import mermaid from 'https://esm.sh/mermaid@11/dist/mermaid.esm.min.mjs'; const dark = matchMedia('(prefers-color-scheme: dark)').matches; - Network accessline 194
import mermaid from 'https://esm.sh/mermaid@11/dist/mermaid.esm.min.mjs'; - Network accessline 223
const x = Math.min(...xs), y = Math.min(...ys); const w = Math.max(...xs) - x, h = Math.max(...ys) - y; const rect = document.createElementNS('http://www.w3.org/2000/svg', 'rect'); - Network accessline 224
const w = Math.max(...xs) - x, h = Math.max(...ys) - y; const rect = document.createElementNS('http://www.w3.org/2000/svg', 'rect'); rect.setAttribute('x', x); rect.setAttribute('y', y); - Network accessline 225
const rect = document.createElementNS('http://www.w3.org/2000/svg', 'rect');
internal/skills/bundled/skills/kocoro-generative-ui/references/maps.md
- Network accessline 6
Three topology sources on jsdelivr. CSP only allows `cdnjs.cloudflare.com`, `esm.sh`, `cdn.jsdelivr.net`, `unpkg.com` — do NOT try `raw.githubusercontent.com` or other hosts, the fetch will silently fail. Other package names like `uk-atlas` - Network accessline 7
- US states: `https://cdn.jsdelivr.net/npm/us-atlas@3/states-10m.json` → `d3.geoAlbersUsa()`, object key `.states` - Network accessline 8
- World countries: `https://cdn.jsdelivr.net/npm/world-atlas@2/countries-110m.json` → `d3.geoNaturalEarth1()`, object key `.countries` - Network accessline 9
- Per-country subdivisions: `https://cdn.jsdelivr.net/npm/datamaps@0.5.10/src/js/data/{iso3}.topo.json` (lowercase alpha-3: `deu`, `jpn`, `gbr`...), object key `.{iso3}` - Network accessline 14
<div id="map" style="width: 100%;"></div> <script src="https://cdnjs.cloudflare.com/ajax/libs/d3/7.8.5/d3.min.js"></script> - Network accessline 15
<script src="https://cdnjs.cloudflare.com/ajax/libs/d3/7.8.5/d3.min.js"></script> - Network accessline 16
<script src="https://cdnjs.cloudflare.com/ajax/libs/topojson/3.0.2/topojson.min.js"></script> - Network accessline 21
const svg = d3.select('#map').append('svg').attr('viewBox', '0 0 900 560').attr('width', '100%'); const path = d3.geoPath(d3.geoAlbersUsa().scale(1100).translate([450, 280])); d3.json('https://cdn.jsdelivr.net/npm/us-atlas@3/states-10m.json - Network accessline 22
const path = d3.geoPath(d3.geoAlbersUsa().scale(1100).translate([450, 280])); d3.json('https://cdn.jsdelivr.net/npm/us-atlas@3/states-10m.json').then(us => { svg.selectAll('path').data(topojson.feature(us, us.objects.states).features).joi - Network accessline 23
d3.json('https://cdn.jsdelivr.net/npm/us-atlas@3/states-10m.json').then(us => {
internal/skills/bundled/skills/kocoro/SKILL.md
- Network accessline 28
Kocoro-managed platform operations go through the daemon HTTP API at `http://localhost:7533`. - Network accessline 53
http POST http://localhost:7533/agents - Network accessline 58
**List agents:** `http GET http://localhost:7533/agents` - Network accessline 60
**Update agent prompt:** `http PUT http://localhost:7533/agents/{name}` body: `{"prompt": "..."}` - Network accessline 62
**Delete agent:** `http DELETE http://localhost:7533/agents/{name}?confirm=true` (explain consequences first) - Network accessline 64
**Agent config (model, tools):** `http PUT http://localhost:7533/agents/{name}/config` body: `{"agent": {"model": "..."}, "tools": {"allow": [...]}}` - Network accessline 66
**List globally installed skills:** `http GET http://localhost:7533/skills` - Network accessline 68
**List skills enabled for a named agent:** `http GET http://localhost:7533/agents/{name}` and inspect `skills` - Network accessline 70
**List bundled skills available to install (explicit administration):** `http GET http://localhost:7533/skills/downloadable` - Network accessline 74
**Install a named skill directly (explicit administration only, outside a capability-dependent task):** `http POST http://localhost:7533/skills/install/{name}` - Network accessline 76
**Attach skill to agent:** `http PUT http://localhost:7533/agents/{name}/skills/{skill}` - Network accessline 78
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Network accessline 80
**Update settings:** `http PATCH http://localhost:7533/config` body: `{"agent": {"temperature": 0.7}}`, then `http POST http://localhost:7533/config/reload` and verify with `GET /config` - Network accessline 82
**Create rule:** `http PUT http://localhost:7533/rules/{name}` body: `{"content": "..."}` - Network accessline 92
http PUT http://localhost:7533/instructions - Access to secretsline 114
[Credential-related source omitted]
internal/skills/bundled/skills/kocoro/references/agents.md
- Network accessline 49
| `display_name_taken` | 409 | duplicate (case-folded, trimmed) | - To customize a built-in agent (`explorer` / `reviewer`), use `PUT /agents/{name}` against its slug — POST always creates a brand-new agent under a fresh auto-slug. - `a - Network accessline 50
- To customize a built-in agent (`explorer` / `reviewer`), use `PUT /agents/{name}` against its slug — POST always creates a brand-new agent under a fresh auto-slug. - `avatar` is **optional** — the agent's avatar image URL, stored in `PR - Network accessline 51
- `avatar` is **optional** — the agent's avatar image URL, stored in `PROFILE.yaml` and synced to Cloud. Must be an `https://` CDN URL with a host; any other scheme (`http://`, `javascript:`, `data:`) returns `400`. Omit / send `""` for no - Network accessline 63
- Renaming to a `display_name` already used by another agent returns `409` with `{"error": "...", "code": "display_name_taken"}`. Renaming to the agent's own current `display_name` is a no-op success. - display_name errors carry the same - Network accessline 64
- display_name errors carry the same `code` table as `POST /agents` above (`display_name_required` 400, `display_name_too_long` 400, `display_name_invalid_chars` 400, `display_name_taken` 409). `error` is a non-localized fallback; clients l - Network accessline 65
- `avatar` is optional (omit = unchanged). Sending an `https://` CDN URL sets it; sending `""` clears it. Non-`https` values (`http://`, `javascript:`, `data:`) return `400`. Avatar editing is gated on the daemon advertising `agent_avatar_v - Dangerous shell operationline 77
- Body: `{"cwd": "/path/to/project", "agent": {"model": "claude-opus-4-5", "model_tier": "large"}, "tools": {"allow": ["bash:git *"], "deny": ["bash:rm *"]}}` - Dangerous shell operationline 92
- Notes: Appends the tool name to `permissions.always_allow_tools` in the agent's `config.yaml`. Next time this agent calls the named tool, the approval prompt is skipped. Idempotent (duplicate add is a no-op). Distinct from `tools.allow` — - Dangerous shell operationline 106
- Notes: Appends to `permissions.always_allow_tools` in `~/.shannon/config.yaml` (global scope). Applies to EVERY agent including the default agent that has no per-agent config. Use this for tools the user trusts broadly (e.g. `bash`, `file - Network accessline 181
`202 {"task_id": "share-...", "session_id": "...", "agent": "...", "phase": "accepted", "status": "accepted"}` - Sync response (`async=false`): `200 {"url": "https://...", "key": "...", "size": 12345, "upload_id": "uuid-or-empty", "summar - Network accessline 182
- Sync response (`async=false`): `200 {"url": "https://...", "key": "...", "size": 12345, "upload_id": "uuid-or-empty", "summary_fallback": false}` - Notes: Renders the session as a self-contained HTML page and uploads it to the cloud upl - Network accessline 183
`200 {"url": "https://...", "key": "...", "size": 12345, "upload_id": "uuid-or-empty", "summary_fallback": false}` - Access to secretsline 190
[Credential-related source omitted] - Network accessline 205
- Method: GET - Path: /sessions/{id}/shares[?agent={name}] - Response: `{"shares": [{"upload_id": "uuid", "url": "https://...", "filename": "session-...-20260518-051234.html", "created_at": "2026-05-18T05:12:34Z"}]}` - Network accessline 206
- Path: /sessions/{id}/shares[?agent={name}] - Response: `{"shares": [{"upload_id": "uuid", "url": "https://...", "filename": "session-...-20260518-051234.html", "created_at": "2026-05-18T05:12:34Z"}]}` - Notes: Returns the daemon-side reco - Network accessline 207
- Response: `{"shares": [{"upload_id": "uuid", "url": "https://...", "filename": "session-...-20260518-051234.html", "created_at": "2026-05-18T05:12:34Z"}]}` - Dangerous shell operationline 299
2. From now on, every bash call from this agent skips approval — **except** commands matching the always-ask gate (`pip install`, `rm -rf`, `python -c`, `git push --force`, `npx`, `curl|sh`, etc.), which still prompt every call regardless.
internal/skills/bundled/skills/kocoro/references/auth.md
- Access to secretsline 5
[Credential-related source omitted] - Access to secretsline 7
[Credential-related source omitted] - Access to secretsline 9
[Credential-related source omitted] - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Access to secretsline 90
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Access to secretsline 124
[Credential-related source omitted] - Access to secretsline 128
[Credential-related source omitted] - Access to secretsline 129
[Credential-related source omitted] - Access to secretsline 130
[Credential-related source omitted] - Access to secretsline 135
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted] - Access to secretsline 143
[Credential-related source omitted] - Access to secretsline 146
[Credential-related source omitted] - Access to secretsline 151
[Credential-related source omitted] - Access to secretsline 152
[Credential-related source omitted]
internal/skills/bundled/skills/kocoro/references/config.md
- Access to secretsline 20
[Credential-related source omitted] - Access to secretsline 46
[Credential-related source omitted] - Instruction override signalline 79
| `tools.bash_timeout` | Max seconds a bash command can run (default: 120) | No | | `tools.browser_result_truncation` | Per-observation capture cap (chars) for browser/GUI page/DOM dumps — tighter than `tools.result_truncation` because page - Instruction override signalline 80
| `tools.browser_result_truncation` | Per-observation capture cap (chars) for browser/GUI page/DOM dumps — tighter than `tools.result_truncation` because page dumps are large and front-loaded; truncation adds a self-describing marker. 0 = f - Instruction override signalline 81
| `daemon.auto_approve` | Skip approval prompts except for tools on the unattended deny-list (`computer_use`, `computer`, `accessibility`, `applescript`, `ghostty`). This generic switch never grants Computer Use; only an explicit persisted - Dangerous shell operationline 86
| `permissions.always_allow_tools` | **Tool-level approval bypass** (global scope, applies to every agent). `computer_use` here is the single global Computer Use permission and is honored for interactive and unattended runs; no entry means - Access to secretsline 145
[Credential-related source omitted] - Access to secretsline 160
[Credential-related source omitted]
internal/skills/bundled/skills/kocoro/references/events.md
- Network accessline 139
# Tail all events live curl -N http://localhost:7533/events - Network accessline 140
curl -N http://localhost:7533/events - Network accessline 142
# Replay from a known cursor (last event seq) curl -N "http://localhost:7533/events?since=42" - Network accessline 143
curl -N "http://localhost:7533/events?since=42" - Network accessline 175
curl http://localhost:7533/notifications?limit=50 - Network accessline 176
curl "http://localhost:7533/notifications?since=120&types=notification,agent_error"
internal/skills/bundled/skills/kocoro/references/feishu.md
- Network accessline 33
- Feishu: [https://open.feishu.cn/page/launcher?from=backend_oneclick](https://open.feishu.cn/page/launcher?from=backend_oneclick) - Network accessline 34
- Lark: [https://open.larksuite.com/page/launcher?from=backend_oneclick](https://open.larksuite.com/page/launcher?from=backend_oneclick) - Network accessline 36
### Steps to give the user (mirror https://kocoro.ai/zh/help/lark/) - Network accessline 65
You need a bot **display name** for the create-app form. **Before suggesting one, `GET http://localhost:7533/channels/feishu/app-installs`** to see which display - Network accessline 66
`GET http://localhost:7533/channels/feishu/app-installs`** to see which display - Network accessline 85
`{host}` = `https://open.feishu.cn` (Feishu) or `https://open.larksuite.com` - Network accessline 100
2. **Register with Kocoro.** Call the local daemon endpoint (it forwards to Cloud with the user's API key — you never handle the key): - `http POST http://localhost:7533/channels/feishu/app-installs` - Network accessline 101
with the user's API key — you never handle the key): - `http POST http://localhost:7533/channels/feishu/app-installs` ```json - Network accessline 102
- `http POST http://localhost:7533/channels/feishu/app-installs` - Network accessline 159
1. **List the bots:** `http GET http://localhost:7533/channels/feishu/app-installs`. - Network accessline 163
app_id and ask which; do NOT guess. Empty list → tell them nothing is bound. 3. **Confirm before deleting** — destructive. State which bot, get a clear yes. 4. **Delete:** `http DELETE http://localhost:7533/channels/feishu/app-installs/{id} - Network accessline 164
3. **Confirm before deleting** — destructive. State which bot, get a clear yes. 4. **Delete:** `http DELETE http://localhost:7533/channels/feishu/app-installs/{id}`. - 200/204: unbound — Cloud tears down the long connection. - Network accessline 165
4. **Delete:** `http DELETE http://localhost:7533/channels/feishu/app-installs/{id}`. - Network accessline 178
then **always present the result as a markdown link `[文件名](url)`** — never a bare URL. Cloud automatically turns a `[name](url)` link pointing at the Kocoro CDN (`https://static.kocoro.ai/…`, URL ending in a file extension) into a - Network accessline 179
bare URL. Cloud automatically turns a `[name](url)` link pointing at the Kocoro CDN (`https://static.kocoro.ai/…`, URL ending in a file extension) into a **downloadable Feishu/Lark attachment**. - Network accessline 180
CDN (`https://static.kocoro.ai/…`, URL ending in a file extension) into a - Network accessline 185
Do this without the user having to ask for "markdown format" — it is the default expected behavior on Feishu/Lark. Example reply: `报告好了：[2026-Q2.pdf](https://static.kocoro.ai/…/2026-Q2.pdf)`. - Network accessline 186
expected behavior on Feishu/Lark. Example reply: `报告好了：[2026-Q2.pdf](https://static.kocoro.ai/…/2026-Q2.pdf)`.
internal/skills/bundled/skills/kocoro/references/mcp.md
- Network accessline 18
[Credential-related source omitted] - Network accessline 19
[Credential-related source omitted] - Network accessline 20
- Body (http): `{"mcp_servers": {"my-server": {"type": "http", "url": "https://my-mcp-server.example.com/mcp"}}}` - Network accessline 88
1. (Desktop) If `mcp_server_info.<name>.requires_auth === true` AND `authorized !== true`, show a confirm modal with `auth_hint` as the body. Bail out on cancel. 2. `PATCH /config` body `{"mcp_servers": {"intercom": {"disabled": false}}}` 3 - Network accessline 89
2. `PATCH /config` body `{"mcp_servers": {"intercom": {"disabled": false}}}` 3. `POST /config/reload` — daemon spawns the configured subprocess. For Intercom this runs `npx mcp-remote https://mcp.intercom.com/mcp`, which opens the user's de - Network accessline 90
3. `POST /config/reload` — daemon spawns the configured subprocess. For Intercom this runs `npx mcp-remote https://mcp.intercom.com/mcp`, which opens the user's default browser for OAuth on first run. On re-enable after a previous successfu - Access to secretsline 101
[Credential-related source omitted]
internal/skills/bundled/skills/kocoro/references/memory.md
- Network accessline 25
[Credential-related source omitted] - Network accessline 26
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Network accessline 27
endpoint: https://api.shannon.run - Network accessline 35
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Network accessline 37
endpoint: https://memory.shannon.run # falls back to cloud.endpoint when empty - Network accessline 45
curl --unix-socket ~/.shannon/memory.sock http://unix/health
internal/skills/bundled/skills/kocoro/references/permissions.md
- Dangerous shell operationline 8
1. **Hard-blocks** — always denied, cannot be overridden (e.g., `rm -rf /`) - Dangerous shell operationline 10
3. **High-risk prefixes (always-ask)** — arbitrary-code-execution gateways like `python -c`, `node -e`, `bash -c`, `agent-browser eval`, supply-chain installers (`pip install` / `pip3 install`, `npm install` / `npm i`, `npx`, `pnpm install` - Dangerous shell operationline 21
- Response includes: `{"permissions": {"allowed_commands": ["git *", "npm test"], "denied_commands": ["rm -rf *"]}}` - Dangerous shell operationline 36
- Notes: Appends to `permissions.always_allow_tools` in `~/.shannon/config.yaml`. Applies to EVERY agent including the default agent. For `computer_use`, this is the single global Computer Use permission and also authorizes unattended tasks - Dangerous shell operationline 84
- **Token-prefix family matching is implicit**: Even without `*`, an entry like `terraform workspace list` automatically covers `terraform workspace show`, `terraform workspace select`, etc. — same exec, same first N tokens. Different sub-c - Dangerous shell operationline 85
- **High-risk always re-prompts**: `python -c`, `pip install`, `agent-browser eval`, any `git push` with destructive flags, `rm -rf`, bare `&` background separators, and similar gateways always trigger an approval dialog, even if listed in
internal/skills/bundled/skills/kocoro/references/recipes.md
- Network accessline 11
1. **Create a Slack app**: Go to [api.slack.com/apps](https://api.slack.com/apps) → "Create New App" → "From scratch" → name it (e.g., "Shannon") → select your workspace. - Access to secretsline 20
[Credential-related source omitted] - Network accessline 113
PUT /agents/monitor/config {"tools": {"allow": ["bash:git *", "bash:curl *", "file_read", "grep"]}} - Network accessline 114
{"tools": {"allow": ["bash:git *", "bash:curl *", "file_read", "grep"]}} - Network accessline 119
{"agent": "monitor", "cron": "0 * * * *", "prompt": "Check for: 1) any git commits since last check, 2) any error patterns in the last hour of logs at ~/app/logs/app.log, 3) whether the app is responding (curl http://localhost:3000/health). - Network accessline 187
3. The user is prompted for approval unless the user has opted into always-allow for `publish_to_web`. 4. On approval, the tool POSTs to Shannon Cloud's `/api/v1/uploads` and returns a permanent HTTPS URL. 5. Embed the URL in the assistant' - Network accessline 189
5. Embed the URL in the assistant's reply ("Here's the landing page: https://…"). - Access to secretsline 201
[Credential-related source omitted] - Network accessline 227
- `GET /uploads?limit=&offset=&kind=` — same response shape as the cloud's `/api/v1/uploads`. `kind` whitelist (`session_share` / `report` / `landing_page` / `image` / `other`) is enforced locally; invalid values return 400 without a round - Network accessline 228
- `POST /uploads` — multipart **image** upload, used for agent avatars. Send a `file` part (`png` / `jpeg` / `webp`, body capped at 10 MiB; Desktop caps at 2 MiB) plus an optional `content_type` field; returns `{"url": "https://static.kocor - Access to secretsline 231
[Credential-related source omitted] - Access to secretsline 233
[Credential-related source omitted] - Network accessline 256
2. The user is prompted for approval (always — paid quota + permanent public URL). 3. On approval, the tool POSTs to Shannon Cloud's `/api/v1/images/generations` and returns one or more permanent HTTPS URLs. 4. Embed the URL(s) in the assis - Network accessline 258
4. Embed the URL(s) in the assistant's reply with markdown: `` so Desktop renders the image inline. - Access to secretsline 279
[Credential-related source omitted] - Network accessline 295
`image_urls` must contain **1–4 entries, each starting with `https://static.kocoro.ai/`**. External URLs are rejected by the server and pre-rejected client-side. If the user gives you an external URL or a local path, do this first: - Network accessline 306
{ "prompt": "Change the cat's fur to orange and add a small wizard hat", "image_urls": ["https://static.kocoro.ai/public/abc123/cat.png"], - Network accessline 307
"prompt": "Change the cat's fur to orange and add a small wizard hat", "image_urls": ["https://static.kocoro.ai/public/abc123/cat.png"], "quality": "low" - Network accessline 308
"image_urls": ["https://static.kocoro.ai/public/abc123/cat.png"], - Network accessline 312
2. The user is prompted for approval (always — paid quota + permanent public URL). 3. On approval, the tool POSTs to `/api/v1/images/edits` and returns the modified image's permanent HTTPS URL. 4. Embed it with markdown: ``. - Network accessline 330
**Failure modes the LLM should adapt to:** - 400 `invalid_image_url` — server rejected one of the URLs as not under `https://static.kocoro.ai/`. **Don't retry the same args.** Tell the user, or pipe the source through `publish_to_web` and r - Network accessline 331
- 400 `invalid_image_url` — server rejected one of the URLs as not under `https://static.kocoro.ai/`. **Don't retry the same args.** Tell the user, or pipe the source through `publish_to_web` and retry with the returned CDN URL. - Access to secretsline 338
[Credential-related source omitted]
internal/skills/bundled/skills/kocoro/references/session-sync.md
- Access to secretsline 64
[Credential-related source omitted]
internal/skills/bundled/skills/kocoro/references/skills.md
- Network accessline 50
The `/skills/clawhub/*` endpoints are backed by ClawHub's live online catalog (~12k skills), a SEPARATE API from `/skills/marketplace/*`. They use opaque cursor pagination and expose per-version file browsing. Base URL is `skills.marketplac - Access to secretsline 139
[Credential-related source omitted] - Access to secretsline 146
[Credential-related source omitted] - Access to secretsline 152
[Credential-related source omitted] - Access to secretsline 158
[Credential-related source omitted] - Access to secretsline 186
[Credential-related source omitted] - Access to secretsline 187
[Credential-related source omitted] - Access to secretsline 188
[Credential-related source omitted] - Access to secretsline 276
[Credential-related source omitted]
internal/skills/bundled/skills/mcp-builder/LICENSE.txt
internal/skills/bundled/skills/mcp-builder/SKILL.md
- Network accessline 41
Start with the sitemap to find relevant pages: `https://modelcontextprotocol.io/sitemap.xml` - Network accessline 43
Then fetch specific pages with `.md` suffix for markdown format (e.g., `https://modelcontextprotocol.io/specification/draft.md`). - Network accessline 60
**For TypeScript (recommended):** - **TypeScript SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` - Network accessline 61
- **TypeScript SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` - Network accessline 64
**For Python:** - **Python SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 65
- **Python SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 202
### Core MCP Documentation (Load First) - **MCP Protocol**: Start with sitemap at `https://modelcontextprotocol.io/sitemap.xml`, then fetch specific pages with `.md` suffix - Network accessline 203
- **MCP Protocol**: Start with sitemap at `https://modelcontextprotocol.io/sitemap.xml`, then fetch specific pages with `.md` suffix - Network accessline 211
### SDK Documentation (Load During Phase 1/2) - **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 212
- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 213
- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
internal/skills/bundled/skills/mcp-builder/reference/evaluation.md
- Access to secretsline 398
[Credential-related source omitted] - Access to secretsline 440
[Credential-related source omitted] - Access to secretsline 444
[Credential-related source omitted] - Network accessline 454
python scripts/evaluation.py \ -t sse \ -u https://example.com/mcp \ - Network accessline 455
[Credential-related source omitted] - Network accessline 456
-u https://example.com/mcp \ - Network accessline 467
python scripts/evaluation.py \ -t http \ -u https://example.com/mcp \ - Network accessline 468
[Credential-related source omitted] - Network accessline 469
-u https://example.com/mcp \ - Access to secretsline 557
[Credential-related source omitted]
internal/skills/bundled/skills/mcp-builder/reference/node_mcp_server.md
- Dangerous shell operationline 541
"clean": "rm -rf dist" - Network accessline 600
// Constants const API_BASE_URL = "https://api.example.com/v1"; - Network accessline 601
const API_BASE_URL = "https://api.example.com/v1"; - Access to secretsline 707
[Credential-related source omitted] - Access to secretsline 708
[Credential-related source omitted] - Access to secretsline 719
[Credential-related source omitted] - Access to secretsline 720
[Credential-related source omitted] - Network accessline 737
const port = parseInt(process.env.PORT || '3000'); app.listen(port, () => { console.error(`MCP server running on http://localhost:${port}/mcp`); - Network accessline 738
app.listen(port, () => { console.error(`MCP server running on http://localhost:${port}/mcp`); }); - Network accessline 739
console.error(`MCP server running on http://localhost:${port}/mcp`);
internal/skills/bundled/skills/mcp-builder/reference/python_mcp_server.md
- Network accessline 42
**For complete SDK documentation, use WebFetch to load:** `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 43
`https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - Network accessline 233
async def _make_api_request(endpoint: str, method: str = "GET", **kwargs) -> dict: '''Reusable function for all API calls.''' async with httpx.AsyncClient() as client: - Network accessline 234
'''Reusable function for all API calls.''' async with httpx.AsyncClient() as client: response = await client.request( - Network accessline 235
async with httpx.AsyncClient() as client: - Network accessline 251
# Good: Async network request async def fetch_data(resource_id: str) -> dict: async with httpx.AsyncClient() as client: - Network accessline 252
async def fetch_data(resource_id: str) -> dict: async with httpx.AsyncClient() as client: response = await client.get(f"{API_URL}/resource/{resource_id}") - Network accessline 253
async with httpx.AsyncClient() as client: - Network accessline 258
# Bad: Synchronous request def fetch_data(resource_id: str) -> dict: response = requests.get(f"{API_URL}/resource/{resource_id}") # Blocks - Network accessline 259
def fetch_data(resource_id: str) -> dict: response = requests.get(f"{API_URL}/resource/{resource_id}") # Blocks return response.json() - Network accessline 260
response = requests.get(f"{API_URL}/resource/{resource_id}") # Blocks - Network accessline 352
# Constants API_BASE_URL = "https://api.example.com/v1" - Network accessline 353
API_BASE_URL = "https://api.example.com/v1" - Network accessline 382
async def _make_api_request(endpoint: str, method: str = "GET", **kwargs) -> dict: '''Reusable function for all API calls.''' async with httpx.AsyncClient() as client: - Network accessline 383
'''Reusable function for all API calls.''' async with httpx.AsyncClient() as client: response = await client.request( - Network accessline 384
async with httpx.AsyncClient() as client: - Access to secretsline 511
[Credential-related source omitted] - Access to secretsline 517
[Credential-related source omitted]
internal/skills/bundled/skills/mcp-builder/scripts/connections.py
- Executable scriptline 1
Executable file
internal/skills/bundled/skills/mcp-builder/scripts/evaluation.py
internal/skills/bundled/skills/pdf-reader/SKILL.md
- Broad permissionsline 1
file_read bash think
internal/skills/bundled/skills/skill-creator/LICENSE.txt
internal/skills/bundled/skills/skill-creator/assets/eval_review.html
- Network accessline 5
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Eval Set Review - __SKILL_NAME_PLACEHOLDER__</title> <link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 6
<title>Eval Set Review - __SKILL_NAME_PLACEHOLDER__</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 7
<link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 8
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 9
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
internal/skills/bundled/skills/skill-creator/eval-viewer/generate_review.py
internal/skills/bundled/skills/skill-creator/eval-viewer/viewer.html
- Network accessline 5
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Eval Review</title> <link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 6
<title>Eval Review</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 7
<link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 8
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 9
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet"> - Network accessline 10
<script src="https://cdn.sheetjs.com/xlsx-0.20.3/package/dist/xlsx.full.min.js" integrity="sha384-EnyY0/GSHQGSxSgMwaIPzSESbqoOLSexfnSMN2AP+39Ckmn92stwABZynq1JyzdT" crossorigin="anonymous"></script> - Network accessline 664
if (!hasPrevious) { try { const resp = await fetch("/api/feedback"); - Network accessline 665
try { const resp = await fetch("/api/feedback"); const data = await resp.json(); - Network accessline 666
const resp = await fetch("/api/feedback"); - Network accessline 1012
fetch("/api/feedback", { - Network accessline 1042
} const payload = JSON.stringify({ reviews, status: "complete" }, null, 2); fetch("/api/feedback", { - Network accessline 1043
const payload = JSON.stringify({ reviews, status: "complete" }, null, 2); fetch("/api/feedback", { method: "POST", - Network accessline 1044
fetch("/api/feedback", {
internal/skills/bundled/skills/skill-creator/scripts/__init__.py
- Executable scriptline 1
Executable file
internal/skills/bundled/skills/skill-creator/scripts/aggregate_benchmark.py
- Executable scriptline 1
#!/usr/bin/env python3
internal/skills/bundled/skills/skill-creator/scripts/generate_report.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 37
<meta charset="utf-8"> """ + refresh_tag + """ <title>""" + title_prefix + """Skill Description Optimization</title> <link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 38
""" + refresh_tag + """ <title>""" + title_prefix + """Skill Description Optimization</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 39
<link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 40
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 41
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
internal/skills/bundled/skills/skill-creator/scripts/improve_description.py
internal/skills/bundled/skills/skill-creator/scripts/package_skill.py
- Executable scriptline 1
#!/usr/bin/env python3
internal/skills/bundled/skills/skill-creator/scripts/quick_validate.py
- Executable scriptline 1
#!/usr/bin/env python3
internal/skills/bundled/skills/skill-creator/scripts/run_eval.py
internal/skills/bundled/skills/skill-creator/scripts/run_loop.py
- Executable scriptline 1
#!/usr/bin/env python3
internal/skills/bundled/skills/skill-creator/scripts/utils.py
- Executable scriptline 1
Executable file
internal/skills/bundled/skills/slack-gif-creator/LICENSE.txt
internal/skills/bundled/skills/slack-gif-creator/core/easing.py
- Executable scriptline 1
#!/usr/bin/env python3
internal/skills/bundled/skills/slack-gif-creator/core/frame_composer.py
- Executable scriptline 1
#!/usr/bin/env python3
internal/skills/bundled/skills/slack-gif-creator/core/gif_builder.py
- Executable scriptline 1
#!/usr/bin/env python3
internal/skills/bundled/skills/slack-gif-creator/core/validators.py
- Executable scriptline 1
#!/usr/bin/env python3
internal/skills/bundled/skills/theme-factory/LICENSE.txt
internal/skills/bundled/skills/web-artifacts-builder/LICENSE.txt
internal/skills/bundled/skills/web-artifacts-builder/SKILL.md
- Network accessline 74
- **shadcn/ui components**: https://ui.shadcn.com/docs/components
internal/skills/bundled/skills/web-artifacts-builder/scripts/bundle-artifact.sh
internal/skills/bundled/skills/web-artifacts-builder/scripts/init-artifact.sh
internal/skills/bundled/skills/webapp-testing/LICENSE.txt
internal/skills/bundled/skills/webapp-testing/SKILL.md
- Network accessline 57
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 58
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 59
page.goto('http://localhost:5173') # Server already running and ready
internal/skills/bundled/skills/webapp-testing/examples/console_logging.py
internal/skills/bundled/skills/webapp-testing/examples/element_discovery.py
internal/skills/bundled/skills/webapp-testing/examples/static_html_automation.py
- Executable scriptline 1
Executable file
internal/skills/bundled/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):
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: 2 facts
- Contacts fonts.googleapis.com, which SKILL.md, the README and the plugin manifest do not mentionskill-creator/scripts/generate_report.py:39High confidence
- Contacts fonts.gstatic.com, which SKILL.md, the README and the plugin manifest do not mentionskill-creator/scripts/generate_report.py:40High confidence
Signal confidence: 498 facts
- Network access in prose of documentationalgorithmic-art/LICENSE.txt:2Low confidence
- Network access in prose of documentationalgorithmic-art/LICENSE.txt:4Low confidence
- Network access in prose of documentationalgorithmic-art/LICENSE.txt:196Low confidence
- Network access in code of the SKILL.mdalgorithmic-art/SKILL.md:278High confidence
- Network access in code of the SKILL.mdalgorithmic-art/SKILL.md:279High confidence
- Network access in code of the SKILL.mdalgorithmic-art/SKILL.md:280High confidence
- Executable script in a comment of a file that runsalgorithmic-art/templates/generator_template.js:1Low confidence
- Network access in prose of documentationbrand-guidelines/LICENSE.txt:2Low confidence
- Network access in prose of documentationbrand-guidelines/LICENSE.txt:4Low confidence
- Network access in prose of documentationbrand-guidelines/LICENSE.txt:196Low confidence
- Network access in prose of documentationcanvas-design/LICENSE.txt:2Low confidence
- Network access in prose of documentationcanvas-design/LICENSE.txt:4Low confidence
- Network access in prose of documentationcanvas-design/LICENSE.txt:196Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/ArsenalSC-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/ArsenalSC-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/BigShoulders-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/BigShoulders-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/BigShoulders-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Boldonse-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Boldonse-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Boldonse-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/BricolageGrotesque-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/BricolageGrotesque-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/BricolageGrotesque-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/CrimsonPro-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/CrimsonPro-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/CrimsonPro-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/DMMono-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/DMMono-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/DMMono-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/EricaOne-OFL.txt:4Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/EricaOne-OFL.txt:6Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/GeistMono-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/GeistMono-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/GeistMono-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Gloock-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Gloock-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Gloock-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/IBMPlexMono-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/IBMPlexMono-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/InstrumentSans-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/InstrumentSans-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/InstrumentSans-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Italiana-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Italiana-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/JetBrainsMono-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/JetBrainsMono-OFL.txt:3Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/JetBrainsMono-OFL.txt:5Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Jura-OFL.txt:1Low confidence
- Network access in prose of documentationcanvas-design/canvas-fonts/Jura-OFL.txt:3Low confidence
and 448 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path CLAUDE.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md internal/migrate/claudecode/testdata/claude_home_basic/skills/dir-style/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md internal/migrate/claudecode/testdata/claude_home_basic/skills/dir-style/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md internal/migrate/claudecode/testdata/claude_home_basic/skills/dir-style/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md internal/migrate/claudecode/testdata/claude_home_basic/skills/dir-style/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.
