Not in the top 1,000 by GitHub stars
AndrewNgGirl/SkillLens
Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/skill-scorer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/banking-workflow-assistant/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/finance-scenario-advisor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/financial-data-analysis-agent/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/financial-education-coach/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/a11y/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/api/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/async/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/audit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/authn/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/authz/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/backend/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/caching/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/circuit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/complexity/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/compliance/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/config/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/cors/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/coverage/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/crypto/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/csrf/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/deps/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/docs/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/env/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/events/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/frontend/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/gdpr/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/headers/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/i18n/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/idor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/imports/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/infra/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/licensing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/logging/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/memory/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/metrics/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/migration/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/naming/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/observability/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/perf/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/privacy/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/ratelimit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/rbac/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/retries/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/schema/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/secrets/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/security/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/serialization/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/sql/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/sqli/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/streaming/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/style/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/tests/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/threading/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/timeout/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/tracing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/typing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/mega-pipeline/agents/xss/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/pr-pipeline/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/pr-pipeline/agents/reviewer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/pr-pipeline/agents/summarizer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/pr-reviewer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/quant-trading-researcher/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/securities-research-analyst/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/startup-fundraising-advisor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
skills/skill-scorer/examples/stock-trading-analyst/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 0005e1d20d8c
No earlier version was observed for comparison.
Heat
0.4- 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
- skill-scorer
skills/skill-scorer - banking-workflow-assistant
skills/skill-scorer/examples/banking-workflow-assistant - finance-scenario-advisor
skills/skill-scorer/examples/finance-scenario-advisor - financial-data-analysis-agent
skills/skill-scorer/examples/financial-data-analysis-agent - financial-education-coach
skills/skill-scorer/examples/financial-education-coach - mega-pipeline
skills/skill-scorer/examples/mega-pipeline - pr-a11y-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/a11y - pr-api-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/api - pr-async-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/async - pr-audit-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/audit - pr-authn-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/authn - pr-authz-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/authz - pr-backend-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/backend - pr-caching-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/caching - pr-circuit-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/circuit - pr-complexity-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/complexity - pr-compliance-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/compliance - pr-config-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/config - pr-cors-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/cors - pr-coverage-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/coverage - pr-crypto-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/crypto - pr-csrf-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/csrf - pr-deps-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/deps - pr-docs-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/docs - pr-env-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/env - pr-events-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/events - pr-frontend-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/frontend - pr-gdpr-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/gdpr - pr-headers-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/headers - pr-i18n-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/i18n - pr-idor-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/idor - pr-imports-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/imports - pr-infra-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/infra - pr-licensing-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/licensing - pr-logging-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/logging - pr-memory-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/memory - pr-metrics-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/metrics - pr-migration-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/migration - pr-naming-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/naming - pr-observability-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/observability - pr-perf-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/perf - pr-privacy-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/privacy - pr-ratelimit-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/ratelimit - pr-rbac-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/rbac - pr-retries-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/retries - pr-schema-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/schema - pr-secrets-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/secrets - pr-security-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/security - pr-serialization-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/serialization - pr-sql-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/sql - pr-sqli-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/sqli - pr-streaming-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/streaming - pr-style-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/style - pr-tests-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/tests - pr-threading-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/threading - pr-timeout-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/timeout - pr-tracing-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/tracing - pr-typing-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/typing - pr-xss-reviewer
skills/skill-scorer/examples/mega-pipeline/agents/xss - pr-pipeline
skills/skill-scorer/examples/pr-pipeline - pr-reviewer-agent
skills/skill-scorer/examples/pr-pipeline/agents/reviewer - pr-summarizer-agent
skills/skill-scorer/examples/pr-pipeline/agents/summarizer - pr-reviewer
skills/skill-scorer/examples/pr-reviewer - quant-trading-researcher
skills/skill-scorer/examples/quant-trading-researcher - securities-research-analyst
skills/skill-scorer/examples/securities-research-analyst - startup-fundraising-advisor
skills/skill-scorer/examples/startup-fundraising-advisor - stock-trading-analyst
skills/skill-scorer/examples/stock-trading-analyst
How it works
skill-scorer
When your agent uses it
Evaluates Agent Skills (Cursor / Claude / OpenClaw compatible) and produces a quantitative, rubric-based score with actionable improvement suggestions. Use when the user asks to review, rate, audit, grade, lint, or improve a SKILL.md file, a skill folder, or a skill archive, or says things like "给这个 skill 打分", "评估一下 skill 质量", "audit this skill", "rate my agent skill".
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
2,521 tokensWhen the skill is activated
Reference documents
4,890 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Code Agent Quick Start
- Inputs
- Outputs
- Workflow
- Official Tool Contract
- Guardrails
- Files
- Report Rendering Rules
Scripts executed separately
scripts/render_report.pyscripts/score.pyscripts/sync_rubric_to_ts.py
Files
SKILL.mdcore9,241 bytesSKILL.mdcore9,241 bytesSKILL.mdcore9,241 bytesSKILL.mdcore9,241 bytesSKILL.mdcore9,241 bytesSKILL.mdcore9,241 bytesUSAGE.mddoc16,475 bytesdomains/finance/rubric.yamlasset24,290 bytesreferences/best-practices.mddoc2,532 bytesrubric/rubric.yamlasset48,516 bytesscripts/render_report.pyruns95,408 bytesscripts/score.pyruns84,010 bytesscripts/sync_rubric_to_ts.pyruns2,696 bytes
Read SKILL.md
# skill-scorer
一个"评测 Skill 的 Skill"。接收任意 Agent Skill 的源文件,必须依据本仓库的官方评分入口和 `rubric/rubric.yaml`
给出 5 大支柱的 100 分制评分、等级、证据引用与改进建议。Rubric 内置三类型差异化(atomic / pipeline / composite),子维度数随 skill 结构自动启用,由 `applies_to` 字段控制。同时兼容 **Cursor / Claude / OpenClaw** 三套规范。
## When to use
- 用户提供 `SKILL.md` / skill 文件夹 / `.zip` / GitHub URL,并请求评分、审计或改进建议。
- 用户询问"我这个 skill 写得怎么样"、"怎么提升我的 skill 质量"、"帮我对齐官方最佳实践"。
- **不适用于**:评价非 Skill 类文档(普通 README / 博客 / prompt 模板)。
## Code Agent Quick Start
如果你是 Cursor、WorkBuddy、Hermes、小龙虾或类似 code agent,先读 `USAGE.md`。View the complete source on GitHubbanking-workflow-assistant
When your agent uses it
Use when bank operations, relationship managers, or credit middle-office teams need to pre-check onboarding, credit, KYB, due diligence, or post-loan documents, route exceptions, track SLA risk, and preserve audit-ready compliance reasoning.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
648 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
- Description
- When to use
- Inputs
- Workflow
- Compliance boundaries
- Output
- Example prompt
Files
SKILL.mdcore2,538 bytes
Read SKILL.md
# Banking Workflow Exception Assistant
## Description
面向银行运营、信贷中台和客户经理的流程助手,用于识别业务材料缺口、异常处理路径、审批 SLA 和合规风险。
## When to use
- 客户经理提交授信、开户、尽调或贷后检查材料前,需要预检查材料完整性。
- 运营团队需要根据异常类型生成分流建议和补件清单。
- 管理者需要追踪流程 SLA、卡点原因和人工复核比例。
## Inputs
- `workflow_type`: 开户、授信、贷后、反洗钱尽调、票据或对公变更。
- `customer_profile`: 客户类型、行业、风险等级、受益所有人信息。
- `documents`: 营业执照、财报、流水、合同、担保材料、KYC 表单。View the complete source on GitHubfinance-scenario-advisor
When your agent uses it
Use when a finance-related Agent Skill does not clearly fit one sub-scenario and needs intake classification, decision-impact assessment, risk boundary review, and recommendations for whether to evaluate it as fundraising, quant trading, stock trading, securities research, banking workflow, financial education, or financial data analysis.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
673 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
- Description
- When to use
- Inputs
- Workflow
- Risk boundaries
- Output
- Example prompt
Files
SKILL.mdcore2,824 bytes
Read SKILL.md
# Finance Scenario Intake Advisor
## Description
用于尚未明确归类的金融场景,先帮助用户识别任务属于投融资、量化交易、短线盯盘、证券研究、银行流程、金融教育还是金融数据分析,再生成对应的评测和改造建议。
## When to use
- 用户上传的 skill 混合了多个金融任务,无法直接归入单一场景。
- 产品经理需要判断一个金融 Agent 应该走哪个专业评测 rubric。
- 团队需要在正式开发前明确用户、数据、风险边界和商业化路径。
## Inputs
- `skill_description`: Agent 的目标、输入、输出和使用场景。
- `user_roles`: 面向投资者、研究员、银行员工、学生、创业者还是数据分析师。
- `decision_impact`: 输出是否会影响投资、授信、交易、教育或运营决策。View the complete source on GitHubfinancial-data-analysis-agent
When your agent uses it
Use when analysts, finance teams, or operators need to clean financial datasets, check data quality, analyze revenue, margin, cash flow, customer value, anomalies, or trends, and produce traceable management-ready insights with confidence caveats.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
638 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
- Description
- When to use
- Inputs
- Workflow
- Risk controls
- Output
- Example prompt
Files
SKILL.mdcore2,600 bytes
Read SKILL.md
# Financial Data Analysis Agent
## Description
面向分析师、财务团队和运营管理者的金融数据分析助手,用于清洗财务、交易、客户和经营数据,生成可追溯的数据洞察报告。
## When to use
- 需要分析收入、成本、利润、现金流、应收账款或客户分层数据。
- 需要从 CSV、Excel、数据库导出中识别异常、缺失、口径不一致和趋势变化。
- 需要把数据分析结果转成管理层可读的 dashboard 摘要。
## Inputs
- `dataset_schema`: 字段名、类型、币种、时间粒度、主键。
- `analysis_goal`: 盈利分析、现金流预测、客户价值、异常检测或经营复盘。
- `data_quality_rules`: 缺失值、重复值、异常值、币种转换和会计口径。View the complete source on GitHubfinancial-education-coach
When your agent uses it
Use when learners, educators, or financial literacy teams need beginner-friendly explanations, analogies, quizzes, misconception tracking, and safety boundaries for topics such as funds, stocks, bonds, insurance, asset allocation, risk, and return.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
632 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
- Description
- When to use
- Inputs
- Workflow
- Safety rules
- Output
- Example prompt
Files
SKILL.mdcore2,512 bytes
Read SKILL.md
# Financial Education Coach
## Description
面向金融知识学习者的教学助手,用通俗例子解释基金、股票、债券、保险、资产配置和风险收益关系,并根据用户水平生成学习路径。
## When to use
- 新手需要理解复利、波动、回撤、分散投资、指数基金等基础概念。
- 课程作者需要把复杂金融概念改写成分层教学内容。
- 用户希望通过测验和案例复盘检查自己是否真正理解风险。
## Inputs
- `learner_profile`: 年龄段、金融基础、学习目标、风险承受能力。
- `topic`: 要学习的金融概念或产品类型。
- `constraints`: 是否允许讨论具体产品、是否面向未成年人、地区监管边界。View the complete source on GitHubmega-pipeline
When your agent uses it
Use when user wants to orchestrate 50+ specialized PR review agents covering different concerns (security, performance, style, dependencies, accessibility, i18n, testing, docs, etc.). Routes through specialist agents and aggregates findings.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
90 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.mdcore397 bytes
Read SKILL.md
# Mega PR Review Pipeline
Orchestrator for 50+ domain-specialist review sub-agents.View the complete source on GitHubpr-a11y-reviewer
When your agent uses it
Use when the parent pipeline routes a a11y-related PR review request. Reads the diff and emits structured a11yFindings using the a11y specialist heuristics.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
74 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.mdcore275 bytes
Read SKILL.md
# A11Y reviewer
Specialist for a11y concerns in PR review.View the complete source on GitHubpr-api-reviewer
When your agent uses it
Use when the parent pipeline routes a api-related PR review request. Reads the diff and emits structured apiFindings using the api specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore269 bytes
Read SKILL.md
# Api reviewer
Specialist for api concerns in PR review.View the complete source on GitHubpr-async-reviewer
When your agent uses it
Use when the parent pipeline routes a async-related PR review request. Reads the diff and emits structured asyncFindings using the async specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore281 bytes
Read SKILL.md
# Async reviewer
Specialist for async concerns in PR review.View the complete source on GitHubpr-audit-reviewer
When your agent uses it
Use when the parent pipeline routes a audit-related PR review request. Reads the diff and emits structured auditFindings using the audit specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore281 bytes
Read SKILL.md
# Audit reviewer
Specialist for audit concerns in PR review.View the complete source on GitHubpr-authn-reviewer
When your agent uses it
Use when the parent pipeline routes a authn-related PR review request. Reads the diff and emits structured authnFindings using the authn specialist heuristics.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
68 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.mdcore281 bytes
Read SKILL.md
# Authn reviewer
Specialist for authn concerns in PR review.View the complete source on GitHubpr-authz-reviewer
When your agent uses it
Use when the parent pipeline routes a authz-related PR review request. Reads the diff and emits structured authzFindings using the authz specialist heuristics.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
68 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.mdcore281 bytes
Read SKILL.md
# Authz reviewer
Specialist for authz concerns in PR review.View the complete source on GitHubpr-backend-reviewer
When your agent uses it
Use when the parent pipeline routes a backend-related PR review request. Reads the diff and emits structured backendFindings using the backend specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Backend reviewer
Specialist for backend concerns in PR review.View the complete source on GitHubpr-caching-reviewer
When your agent uses it
Use when the parent pipeline routes a caching-related PR review request. Reads the diff and emits structured cachingFindings using the caching specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
64 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.mdcore293 bytes
Read SKILL.md
# Caching reviewer
Specialist for caching concerns in PR review.View the complete source on GitHubpr-circuit-reviewer
When your agent uses it
Use when the parent pipeline routes a circuit-related PR review request. Reads the diff and emits structured circuitFindings using the circuit specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Circuit reviewer
Specialist for circuit concerns in PR review.View the complete source on GitHubpr-complexity-reviewer
When your agent uses it
Use when the parent pipeline routes a complexity-related PR review request. Reads the diff and emits structured complexityFindings using the complexity specialist heuristics.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
64 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.mdcore311 bytes
Read SKILL.md
# Complexity reviewer
Specialist for complexity concerns in PR review.View the complete source on GitHubpr-compliance-reviewer
When your agent uses it
Use when the parent pipeline routes a compliance-related PR review request. Reads the diff and emits structured complianceFindings using the compliance specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore311 bytes
Read SKILL.md
# Compliance reviewer
Specialist for compliance concerns in PR review.View the complete source on GitHubpr-config-reviewer
When your agent uses it
Use when the parent pipeline routes a config-related PR review request. Reads the diff and emits structured configFindings using the config specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore287 bytes
Read SKILL.md
# Config reviewer
Specialist for config concerns in PR review.View the complete source on GitHubpr-cors-reviewer
When your agent uses it
Use when the parent pipeline routes a cors-related PR review request. Reads the diff and emits structured corsFindings using the cors specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore275 bytes
Read SKILL.md
# Cors reviewer
Specialist for cors concerns in PR review.View the complete source on GitHubpr-coverage-reviewer
When your agent uses it
Use when the parent pipeline routes a coverage-related PR review request. Reads the diff and emits structured coverageFindings using the coverage specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore299 bytes
Read SKILL.md
# Coverage reviewer
Specialist for coverage concerns in PR review.View the complete source on GitHubpr-crypto-reviewer
When your agent uses it
Use when the parent pipeline routes a crypto-related PR review request. Reads the diff and emits structured cryptoFindings using the crypto specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore287 bytes
Read SKILL.md
# Crypto reviewer
Specialist for crypto concerns in PR review.View the complete source on GitHubpr-csrf-reviewer
When your agent uses it
Use when the parent pipeline routes a csrf-related PR review request. Reads the diff and emits structured csrfFindings using the csrf specialist heuristics.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
65 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.mdcore275 bytes
Read SKILL.md
# Csrf reviewer
Specialist for csrf concerns in PR review.View the complete source on GitHubpr-deps-reviewer
When your agent uses it
Use when the parent pipeline routes a deps-related PR review request. Reads the diff and emits structured depsFindings using the deps specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
64 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.mdcore275 bytes
Read SKILL.md
# Deps reviewer
Specialist for deps concerns in PR review.View the complete source on GitHubpr-docs-reviewer
When your agent uses it
Use when the parent pipeline routes a docs-related PR review request. Reads the diff and emits structured docsFindings using the docs specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore275 bytes
Read SKILL.md
# Docs reviewer
Specialist for docs concerns in PR review.View the complete source on GitHubpr-env-reviewer
When your agent uses it
Use when the parent pipeline routes a env-related PR review request. Reads the diff and emits structured envFindings using the env specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore269 bytes
Read SKILL.md
# Env reviewer
Specialist for env concerns in PR review.View the complete source on GitHubpr-events-reviewer
When your agent uses it
Use when the parent pipeline routes a events-related PR review request. Reads the diff and emits structured eventsFindings using the events specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore287 bytes
Read SKILL.md
# Events reviewer
Specialist for events concerns in PR review.View the complete source on GitHubpr-frontend-reviewer
When your agent uses it
Use when the parent pipeline routes a frontend-related PR review request. Reads the diff and emits structured frontendFindings using the frontend specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
64 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.mdcore299 bytes
Read SKILL.md
# Frontend reviewer
Specialist for frontend concerns in PR review.View the complete source on GitHubpr-gdpr-reviewer
When your agent uses it
Use when the parent pipeline routes a gdpr-related PR review request. Reads the diff and emits structured gdprFindings using the gdpr specialist heuristics.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
70 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.mdcore275 bytes
Read SKILL.md
# Gdpr reviewer
Specialist for gdpr concerns in PR review.View the complete source on GitHubpr-headers-reviewer
When your agent uses it
Use when the parent pipeline routes a headers-related PR review request. Reads the diff and emits structured headersFindings using the headers specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Headers reviewer
Specialist for headers concerns in PR review.View the complete source on GitHubpr-i18n-reviewer
When your agent uses it
Use when the parent pipeline routes a i18n-related PR review request. Reads the diff and emits structured i18nFindings using the i18n specialist heuristics.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
74 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.mdcore275 bytes
Read SKILL.md
# I18N reviewer
Specialist for i18n concerns in PR review.View the complete source on GitHubpr-idor-reviewer
When your agent uses it
Use when the parent pipeline routes a idor-related PR review request. Reads the diff and emits structured idorFindings using the idor specialist heuristics.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
68 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.mdcore275 bytes
Read SKILL.md
# Idor reviewer
Specialist for idor concerns in PR review.View the complete source on GitHubpr-imports-reviewer
When your agent uses it
Use when the parent pipeline routes a imports-related PR review request. Reads the diff and emits structured importsFindings using the imports specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Imports reviewer
Specialist for imports concerns in PR review.View the complete source on GitHubpr-infra-reviewer
When your agent uses it
Use when the parent pipeline routes a infra-related PR review request. Reads the diff and emits structured infraFindings using the infra specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore281 bytes
Read SKILL.md
# Infra reviewer
Specialist for infra concerns in PR review.View the complete source on GitHubpr-licensing-reviewer
When your agent uses it
Use when the parent pipeline routes a licensing-related PR review request. Reads the diff and emits structured licensingFindings using the licensing specialist heuristics.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
64 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.mdcore305 bytes
Read SKILL.md
# Licensing reviewer
Specialist for licensing concerns in PR review.View the complete source on GitHubpr-logging-reviewer
When your agent uses it
Use when the parent pipeline routes a logging-related PR review request. Reads the diff and emits structured loggingFindings using the logging specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Logging reviewer
Specialist for logging concerns in PR review.View the complete source on GitHubpr-memory-reviewer
When your agent uses it
Use when the parent pipeline routes a memory-related PR review request. Reads the diff and emits structured memoryFindings using the memory specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore287 bytes
Read SKILL.md
# Memory reviewer
Specialist for memory concerns in PR review.View the complete source on GitHubpr-metrics-reviewer
When your agent uses it
Use when the parent pipeline routes a metrics-related PR review request. Reads the diff and emits structured metricsFindings using the metrics specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Metrics reviewer
Specialist for metrics concerns in PR review.View the complete source on GitHubpr-migration-reviewer
When your agent uses it
Use when the parent pipeline routes a migration-related PR review request. Reads the diff and emits structured migrationFindings using the migration specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore305 bytes
Read SKILL.md
# Migration reviewer
Specialist for migration concerns in PR review.View the complete source on GitHubpr-naming-reviewer
When your agent uses it
Use when the parent pipeline routes a naming-related PR review request. Reads the diff and emits structured namingFindings using the naming specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore287 bytes
Read SKILL.md
# Naming reviewer
Specialist for naming concerns in PR review.View the complete source on GitHubpr-observability-reviewer
When your agent uses it
Use when the parent pipeline routes a observability-related PR review request. Reads the diff and emits structured observabilityFindings using the observability specialist heuristics.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
69 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.mdcore329 bytes
Read SKILL.md
# Observability reviewer
Specialist for observability concerns in PR review.View the complete source on GitHubpr-perf-reviewer
When your agent uses it
Use when the parent pipeline routes a perf-related PR review request. Reads the diff and emits structured perfFindings using the perf specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore275 bytes
Read SKILL.md
# Perf reviewer
Specialist for perf concerns in PR review.View the complete source on GitHubpr-privacy-reviewer
When your agent uses it
Use when the parent pipeline routes a privacy-related PR review request. Reads the diff and emits structured privacyFindings using the privacy specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Privacy reviewer
Specialist for privacy concerns in PR review.View the complete source on GitHubpr-ratelimit-reviewer
When your agent uses it
Use when the parent pipeline routes a ratelimit-related PR review request. Reads the diff and emits structured ratelimitFindings using the ratelimit specialist heuristics.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
74 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.mdcore305 bytes
Read SKILL.md
# Ratelimit reviewer
Specialist for ratelimit concerns in PR review.View the complete source on GitHubpr-rbac-reviewer
When your agent uses it
Use when the parent pipeline routes a rbac-related PR review request. Reads the diff and emits structured rbacFindings using the rbac specialist heuristics.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
68 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.mdcore275 bytes
Read SKILL.md
# Rbac reviewer
Specialist for rbac concerns in PR review.View the complete source on GitHubpr-retries-reviewer
When your agent uses it
Use when the parent pipeline routes a retries-related PR review request. Reads the diff and emits structured retriesFindings using the retries specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
64 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.mdcore293 bytes
Read SKILL.md
# Retries reviewer
Specialist for retries concerns in PR review.View the complete source on GitHubpr-schema-reviewer
When your agent uses it
Use when the parent pipeline routes a schema-related PR review request. Reads the diff and emits structured schemaFindings using the schema specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore287 bytes
Read SKILL.md
# Schema reviewer
Specialist for schema concerns in PR review.View the complete source on GitHubpr-secrets-reviewer
When your agent uses it
Use when the parent pipeline routes a secrets-related PR review request. Reads the diff and emits structured secretsFindings using the secrets specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Secrets reviewer
Specialist for secrets concerns in PR review.View the complete source on GitHubpr-security-reviewer
When your agent uses it
Use when the parent pipeline routes a security-related PR review request. Reads the diff and emits structured securityFindings using the security specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore299 bytes
Read SKILL.md
# Security reviewer
Specialist for security concerns in PR review.View the complete source on GitHubpr-serialization-reviewer
When your agent uses it
Use when the parent pipeline routes a serialization-related PR review request. Reads the diff and emits structured serializationFindings using the serialization specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore329 bytes
Read SKILL.md
# Serialization reviewer
Specialist for serialization concerns in PR review.View the complete source on GitHubpr-sql-reviewer
When your agent uses it
Use when the parent pipeline routes a sql-related PR review request. Reads the diff and emits structured sqlFindings using the sql specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore269 bytes
Read SKILL.md
# Sql reviewer
Specialist for sql concerns in PR review.View the complete source on GitHubpr-sqli-reviewer
When your agent uses it
Use when the parent pipeline routes a sqli-related PR review request. Reads the diff and emits structured sqliFindings using the sqli specialist heuristics.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
68 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.mdcore275 bytes
Read SKILL.md
# Sqli reviewer
Specialist for sqli concerns in PR review.View the complete source on GitHubpr-streaming-reviewer
When your agent uses it
Use when the parent pipeline routes a streaming-related PR review request. Reads the diff and emits structured streamingFindings using the streaming specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore305 bytes
Read SKILL.md
# Streaming reviewer
Specialist for streaming concerns in PR review.View the complete source on GitHubpr-style-reviewer
When your agent uses it
Use when the parent pipeline routes a style-related PR review request. Reads the diff and emits structured styleFindings using the style specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore281 bytes
Read SKILL.md
# Style reviewer
Specialist for style concerns in PR review.View the complete source on GitHubpr-tests-reviewer
When your agent uses it
Use when the parent pipeline routes a tests-related PR review request. Reads the diff and emits structured testsFindings using the tests specialist heuristics.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
62 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.mdcore281 bytes
Read SKILL.md
# Tests reviewer
Specialist for tests concerns in PR review.View the complete source on GitHubpr-threading-reviewer
When your agent uses it
Use when the parent pipeline routes a threading-related PR review request. Reads the diff and emits structured threadingFindings using the threading specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
64 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.mdcore305 bytes
Read SKILL.md
# Threading reviewer
Specialist for threading concerns in PR review.View the complete source on GitHubpr-timeout-reviewer
When your agent uses it
Use when the parent pipeline routes a timeout-related PR review request. Reads the diff and emits structured timeoutFindings using the timeout specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
63 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.mdcore293 bytes
Read SKILL.md
# Timeout reviewer
Specialist for timeout concerns in PR review.View the complete source on GitHubpr-tracing-reviewer
When your agent uses it
Use when the parent pipeline routes a tracing-related PR review request. Reads the diff and emits structured tracingFindings using the tracing specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
64 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.mdcore293 bytes
Read SKILL.md
# Tracing reviewer
Specialist for tracing concerns in PR review.View the complete source on GitHubpr-typing-reviewer
When your agent uses it
Use when the parent pipeline routes a typing-related PR review request. Reads the diff and emits structured typingFindings using the typing specialist heuristics.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
64 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.mdcore287 bytes
Read SKILL.md
# Typing reviewer
Specialist for typing concerns in PR review.View the complete source on GitHubpr-xss-reviewer
When your agent uses it
Use when the parent pipeline routes a xss-related PR review request. Reads the diff and emits structured xssFindings using the xss specialist heuristics.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
68 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.mdcore269 bytes
Read SKILL.md
# Xss reviewer
Specialist for xss concerns in PR review.View the complete source on GitHubpr-pipeline
When your agent uses it
Use when the user wants to review a GitHub pull request through a multi-stage pipeline. Routes through reviewer, summarizer, and final report stages.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
136 tokensWhen the skill is activated
Reference documents
23 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Sub-skills
Scripts executed separately
scripts/schemas.py
Files
SKILL.mdcore551 bytesreferences/best-practices.mddoc110 bytesscripts/schemas.pyruns269 bytes
Read SKILL.md
# PR Pipeline Orchestrator
When to use: PR review automation for OSS maintainers handling weekly batches.
## Workflow
1. agents/reviewer — line-by-line code review
2. agents/summarizer — summarize findings into a digest
3. Final stage — emit JSON report
## Sub-skills
- agents/reviewer/SKILL.md
- agents/summarizer/SKILL.mdView the complete source on GitHubpr-reviewer-agent
When your agent uses it
Use when the parent pipeline routes a PR review request. Reads diff and produces a Pydantic ReviewReport.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
100 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
- Inputs
- Outputs (defined in scripts/schemas.py)
- Examples
Files
SKILL.mdcore443 bytesSKILL.mdcore443 bytes
Read SKILL.md
# PR Reviewer Sub-Agent
## Inputs
- diff_text (str)
## Outputs (defined in scripts/schemas.py)
ReviewReport(BaseModel) with fields: comments, severity, suggestions
## Examples
```python
from scripts.schemas import ReviewReport
report = ReviewReport(comments=[...], severity="medium")
```View the complete source on GitHubpr-summarizer-agent
When your agent uses it
Use when the pipeline needs to compress reviewer output into a digest. Pure function over ReviewReport.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
60 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
- Inputs
- Outputs
Files
SKILL.mdcore278 bytes
Read SKILL.md
# PR Summarizer Sub-Agent
## Inputs
- review_report (ReviewReport from sibling reviewer)
## Outputs
DigestReport(BaseModel)View the complete source on GitHubpr-reviewer
When your agent uses it
Use when the user asks to review, audit, comment on, or 评审 / 审查 a GitHub Pull Request. Generates structured review comments covering team-specific code style, naming, and structural conventions — complements (not replaces) bug-finding tools like Copilot Code Review or CodeQL.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
1,509 tokensWhen the skill is activated
Reference documents
712 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Target users
- Why this skill
- Inputs
- Workflow
- Outputs
- Dependencies
- Determinism
- Failure handling
- Privacy
- Example
- Files
- Changelog
Scripts executed separately
scripts/fetch_pr.pyscripts/validate_review.py
Files
CHANGELOG.mddoc405 bytesSKILL.mdcore5,756 bytesSKILL.mdcore5,756 bytesSKILL.mdcore5,756 bytesassets/review.schema.jsonasset774 bytesreferences/default-rules.mddoc1,473 bytesreferences/privacy.mddoc891 bytesrequirements.txtdoc171 bytesscripts/fetch_pr.pyruns1,346 bytesscripts/validate_review.pyruns999 bytestests/expected_outputs.jsonasset656 bytestests/sample_inputs.jsonasset443 bytes
Read SKILL.md
# pr-reviewer
## When to use
When the user asks to review / audit / comment / 评审 / 审查 a GitHub PR by URL or local diff. Trigger phrases include:
- "帮我 review 这个 PR"
- "review https://github.com/.../pull/123"
- "check this diff before I merge"
**Not suitable for**: bug-hunting (use Copilot Code Review), security scans (use CodeQL), runtime performance review.
## Target users
View the complete source on GitHubquant-trading-researcher
When your agent uses it
Use when quant researchers or strategy developers need to evaluate factor ideas, backtest validity, statistical reliability, trading costs, implementation risk, and live monitoring readiness before paper trading or limited production deployment.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
748 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
- Description
- When to use
- Inputs
- Workflow
- Guardrails
- Output
- Example prompt
Files
SKILL.mdcore2,837 bytes
Read SKILL.md
# Quant Strategy Researcher
## Description
面向量化研究员和个人策略开发者的策略研究助手,用于把因子想法、回测配置、交易成本和上线监控要求整理成可复现的策略研究报告。
## When to use
- 需要评估一个因子或交易信号是否具备统计可靠性。
- 需要检查回测是否存在未来函数、幸存者偏差、过拟合或交易成本低估。
- 策略准备从 notebook 进入 paper trading 或小资金实盘观察。
## Inputs
- `universe`: 股票池、期货品种、ETF 或加密资产范围。
- `signal_definition`: 因子公式、调仓频率、持仓约束。
- `backtest_result`: 收益、波动、最大回撤、换手率、胜率、IC、IR、分年度表现。View the complete source on GitHubsecurities-research-analyst
When your agent uses it
Use when research analysts or investment teams need to turn filings, earnings calls, announcements, financial metrics, and industry data into traceable securities research notes with evidence links, scenario analysis, valuation assumptions, and compliance-safe risk flags.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
692 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
- Description
- When to use
- Inputs
- Workflow
- Risk controls
- Output
- Example prompt
Files
SKILL.mdcore2,749 bytes
Read SKILL.md
# Securities Research Note Analyst
## Description
将财报、公告、电话会纪要、行业数据和券商研报摘要整理为证券研究笔记,帮助投研人员形成可追溯、可审计的研究结论。
## When to use
- 研究员需要快速梳理上市公司季度业绩、经营拐点和估值假设。
- 投资经理希望检查研究结论是否过度依赖单一消息或未经证实的传闻。
- 团队需要把财务指标、行业景气度和催化剂整理成标准投研模板。
## Inputs
- `company`: 股票代码、公司名称、交易所、覆盖行业。
- `financials`: 收入、利润、毛利率、现金流、负债、分业务数据。
- `sources`: 财报、公告、电话会纪要、行业数据库、新闻链接。View the complete source on GitHubstartup-fundraising-advisor
When your agent uses it
Use when founders, CFOs, or fundraising advisors need to turn pitch decks, traction metrics, financial assumptions, and market notes into an investor-facing fundraising memo with due diligence risks, evidence gaps, and non-misleading financing recommendations.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
813 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
- Description
- When to use
- Inputs
- Workflow
- Risk and compliance boundaries
- Output
- Example prompt
Files
SKILL.mdcore3,220 bytes
Read SKILL.md
# Startup Fundraising Memo Advisor
## Description
帮助早期创业团队把融资材料、运营数据和市场假设整理成可投资人沟通的融资备忘录。适用于准备天使轮、Pre-A 或 A 轮融资的创始人、CFO 和投融资顾问。
## When to use
- 创始人需要把 pitch deck、财务模型、用户增长数据和竞品信息转成一页式投资人 memo。
- 团队需要识别融资故事里的关键缺口,例如牵引力不足、商业模式证据薄弱、估值假设过激。
- 投融资顾问需要在路演前快速形成 due diligence 风险清单和下一步补证建议。
## Inputs
- `company_profile`: 公司简介、团队背景、产品阶段、目标融资轮次。
- `traction_metrics`: MRR、ARR、留存、CAC、LTV、毛利率、回款周期、客户数量。
- `fundraising_terms`: 目标融资金额、估值区间、资金用途、runway。View the complete source on GitHubstock-trading-analyst
When your agent uses it
Use when the user needs an A-share stock watchlist, short-term theme rotation review, or trading-plan risk audit based on user-provided market data. Produces evidence-based sector analysis, signal confidence, risk warnings, and a non-advisory action checklist for retail investors, research assistants, and trading educators.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
2,344 tokensWhen the skill is activated
Reference documents
659 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Target users
- Value proposition
- Inputs
- Workflow
- Analysis framework
- Outputs
- Dependencies
- Determinism
- Failure handling
- Privacy and compliance
- Example
- Files
- Changelog
Scripts executed separately
scripts/validate_signal.py
Files
SKILL.mdcore9,706 bytesSKILL.mdcore9,706 bytesSKILL.mdcore9,706 bytesSKILL.mdcore9,706 bytesassets/stock_signal.schema.jsonasset2,583 bytesreferences/risk-policy.mddoc1,445 bytesreferences/scoring-model.mddoc1,580 bytesrequirements.txtdoc16 bytesscripts/validate_signal.pyruns1,267 bytestests/expected_signal_report.jsonasset1,622 bytestests/sample_market_rows.jsonasset975 bytes
Read SKILL.md
# stock-trading-analyst
## When to use
Use this skill when the user provides A-share market data and asks for:
- 今日题材轮动、涨停归因、资金生态分析
- 短线候选股筛选、观察池复盘、交易计划风控检查
- 个股异动原因拆解、板块强弱比较、情绪周期研判
- "帮我看看这批股票哪个更值得观察"
**Not suitable for**:直接给出买入 / 卖出指令、承诺收益、代客理财、荐股收费、绕过投顾合规要求、处理内幕信息或未授权账户数据。
## Target usersView the complete source on GitHubSkills included
- skill-scorer
- banking-workflow-assistant
- finance-scenario-advisor
- financial-data-analysis-agent
- financial-education-coach
- mega-pipeline
- pr-a11y-reviewer
- pr-api-reviewer
- pr-async-reviewer
- pr-audit-reviewer
- pr-authn-reviewer
- pr-authz-reviewer
- pr-backend-reviewer
- pr-caching-reviewer
- pr-circuit-reviewer
- pr-complexity-reviewer
- pr-compliance-reviewer
- pr-config-reviewer
- pr-cors-reviewer
- pr-coverage-reviewer
- pr-crypto-reviewer
- pr-csrf-reviewer
- pr-deps-reviewer
- pr-docs-reviewer
- pr-env-reviewer
- pr-events-reviewer
- pr-frontend-reviewer
- pr-gdpr-reviewer
- pr-headers-reviewer
- pr-i18n-reviewer
- pr-idor-reviewer
- pr-imports-reviewer
- pr-infra-reviewer
- pr-licensing-reviewer
- pr-logging-reviewer
- pr-memory-reviewer
- pr-metrics-reviewer
- pr-migration-reviewer
- pr-naming-reviewer
- pr-observability-reviewer
- pr-perf-reviewer
- pr-privacy-reviewer
- pr-ratelimit-reviewer
- pr-rbac-reviewer
- pr-retries-reviewer
- pr-schema-reviewer
- pr-secrets-reviewer
- pr-security-reviewer
- pr-serialization-reviewer
- pr-sql-reviewer
- pr-sqli-reviewer
- pr-streaming-reviewer
- pr-style-reviewer
- pr-tests-reviewer
- pr-threading-reviewer
- pr-timeout-reviewer
- pr-tracing-reviewer
- pr-typing-reviewer
- pr-xss-reviewer
- pr-pipeline
- pr-reviewer-agent
- pr-summarizer-agent
- pr-reviewer
- quant-trading-researcher
- securities-research-analyst
- startup-fundraising-advisor
- stock-trading-analyst
Repository facts
- License
- MIT
- Created
- May 5, 2026
- Last pushed
- May 17, 2026
- Forks
- 5
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 11 notes
skills/skill-scorer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/examples/pr-pipeline/agents/reviewer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/examples/pr-reviewer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/examples/pr-reviewer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/examples/stock-trading-analyst/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/examples/stock-trading-analyst/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-scorer/examples/stock-trading-analyst/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 4 dangerous shell commandsin 3 files: skill-scorer/rubric/rubric.yaml:756 skill-scorer/references/best-practices.md:44 skill-scorer/scripts/score.py:288
- 29 network referencesin 6 files: pr-reviewer/scripts/fetch_pr.py:15 pr-reviewer/SKILL.md:16 stock-trading-analyst/tests/sample_market_rows.json:14 and 3 more
- No hidden or obfuscated text
- No instruction overrides
- 7 executable scriptsin 7 files: pr-pipeline/scripts/schemas.py:1 pr-reviewer/scripts/fetch_pr.py:1 pr-reviewer/scripts/validate_review.py:1 and 4 more
- 3 references to secretsin 2 files: skill-scorer/rubric/rubric.yaml:764 pr-reviewer/scripts/fetch_pr.py:4
- No requests to vote in Hot
Show all 43 signals by file
skills/skill-scorer/examples/pr-pipeline/scripts/schemas.py
- Executable scriptline 1
Executable file
skills/skill-scorer/examples/pr-reviewer/SKILL.md
- Network accessline 16
- "帮我 review 这个 PR" - "review https://github.com/.../pull/123" - Network accessline 17
- "review https://github.com/.../pull/123" - Network accessline 38
| Field | Type | Required | Notes | |---|---|---|---| | `pr_url` | string | yes | e.g. `https://github.com/owner/repo/pull/123` | - Network accessline 39
|---|---|---|---| | `pr_url` | string | yes | e.g. `https://github.com/owner/repo/pull/123` | | `team_rules` | string | optional | path to team convention markdown; defaults to `references/default-rules.md` | - Network accessline 40
| `pr_url` | string | yes | e.g. `https://github.com/owner/repo/pull/123` | - Network accessline 97
# input pr-reviewer review https://github.com/octocat/hello-world/pull/42 - Network accessline 98
pr-reviewer review https://github.com/octocat/hello-world/pull/42
skills/skill-scorer/examples/pr-reviewer/assets/review.schema.json
skills/skill-scorer/examples/pr-reviewer/scripts/fetch_pr.py
- Executable scriptline 1
Executable file - Access to secretsline 4
[Credential-related source omitted] - Network accessline 15
[Credential-related source omitted] - Network accessline 18
raise ValueError(f"not a recognizable PR URL: {pr_url}") owner, repo, num = m.group(1), m.group(2), m.group(3) api = f"https://api.github.com/repos/{owner}/{repo}/pulls/{num}" - Network accessline 19
owner, repo, num = m.group(1), m.group(2), m.group(3) api = f"https://api.github.com/repos/{owner}/{repo}/pulls/{num}" headers = {"Accept": "application/vnd.github+json"} - Network accessline 20
api = f"https://api.github.com/repos/{owner}/{repo}/pulls/{num}" - Network accessline 22
[Credential-related source omitted] - Network accessline 23
headers["Authorization"] = f"Bearer {token}" req = urllib.request.Request(api, headers=headers) try: - Network accessline 24
req = urllib.request.Request(api, headers=headers) - Network accessline 25
try: with urllib.request.urlopen(req, timeout=20) as r: meta = json.loads(r.read()) - Network accessline 26
with urllib.request.urlopen(req, timeout=20) as r: - Network accessline 31
diff_req = urllib.request.Request(api, headers={**headers, "Accept": "application/vnd.github.v3.diff"}) - Network accessline 32
with urllib.request.urlopen(diff_req, timeout=20) as r: - Network accessline 37
if __name__ == "__main__": print(json.dumps(fetch(sys.argv[1]), ensure_ascii=False, indent=2)) - Network accessline 38
print(json.dumps(fetch(sys.argv[1]), ensure_ascii=False, indent=2))
skills/skill-scorer/examples/pr-reviewer/scripts/validate_review.py
- Executable scriptline 1
Executable file
skills/skill-scorer/examples/stock-trading-analyst/assets/stock_signal.schema.json
skills/skill-scorer/examples/stock-trading-analyst/scripts/validate_signal.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/skill-scorer/examples/stock-trading-analyst/tests/sample_market_rows.json
- Network accessline 14
"net_inflow_cny": 125000000, "limit_up_reason": "AI应用催化,金融科技资金回流", "news": ["https://example.com/public-news-a"], - Network accessline 15
"limit_up_reason": "AI应用催化,金融科技资金回流", "news": ["https://example.com/public-news-a"], "data_source": "user_upload", - Network accessline 16
"news": ["https://example.com/public-news-a"],
skills/skill-scorer/references/best-practices.md
- Dangerous shell operationline 44
- 破坏性动作(`rm -rf` / `git push --force` / SQL `DROP` / 文件删除等)必须**显式标红**并要求二次确认。
skills/skill-scorer/rubric/rubric.yaml
- Dangerous shell operationline 756
fix_zh: "对 rm -rf / git push --force / DROP TABLE 这类命令前加 '⚠<U+FE0F> 危险',并要求二次确认或更安全的替代。" - Dangerous shell operationline 757
fix_en: "Prefix rm -rf / git push --force / DROP TABLE with '⚠<U+FE0F> Destructive' and require a confirm or safer path." - Access to secretsline 764
[Credential-related source omitted] - Access to secretsline 765
[Credential-related source omitted]
skills/skill-scorer/scripts/render_report.py
skills/skill-scorer/scripts/score.py
skills/skill-scorer/scripts/sync_rubric_to_ts.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 1 fact
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionskill-scorer/scripts/render_report.py:1376High confidence
Signal confidence: 32 facts
- Executable script in code of a file that runspr-pipeline/scripts/schemas.py:1High confidence
- Network access in prose of the SKILL.mdpr-reviewer/SKILL.md:16Low confidence
- Network access in prose of the SKILL.mdpr-reviewer/SKILL.md:17Low confidence
- Network access in prose of the SKILL.mdpr-reviewer/SKILL.md:38Low confidence
- Network access in prose of the SKILL.mdpr-reviewer/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdpr-reviewer/SKILL.md:40Low confidence
- Network access in code of the SKILL.mdpr-reviewer/SKILL.md:97High confidence
- Network access in code of the SKILL.mdpr-reviewer/SKILL.md:98High confidence
- Executable script in prose of a file that runspr-reviewer/scripts/fetch_pr.py:1Low confidence
- Access to secrets in prose of a file that runs: a variable, placeholder or call, not a stored valuepr-reviewer/scripts/fetch_pr.py:4Low confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:15High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:18High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:19High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:20High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:22High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:23High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:24High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:25High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:26High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:31High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:32High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:37High confidence
- Network access in code of a file that runspr-reviewer/scripts/fetch_pr.py:38High confidence
- Executable script in prose of a file that runspr-reviewer/scripts/validate_review.py:1Low confidence
- Executable script in code of a file that runsstock-trading-analyst/scripts/validate_signal.py:1High confidence
- Dangerous shell operation in prose of documentationskill-scorer/references/best-practices.md:44Low confidence
- Executable script in prose of a file that runsskill-scorer/scripts/render_report.py:1Low confidence
- Network access in code of a file that runsskill-scorer/scripts/render_report.py:1375High confidence
- Network access in code of a file that runsskill-scorer/scripts/render_report.py:1376High confidence
- Executable script in code of a file that runsskill-scorer/scripts/score.py:1High confidence
- Dangerous shell operation in code of a file that runsskill-scorer/scripts/score.py:288High confidence
- Executable script in code of a file that runsskill-scorer/scripts/sync_rubric_to_ts.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/skill-scorer/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/skill-scorer/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/skill-scorer/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/skill-scorer/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/skill-scorer/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/skill-scorer/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.