SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsskill-sentinel

skill-sentinel

Security & auditing

View repository

Updated 10-16 01:57

About this skill

Skill Sentinel

Overview

Audit and evolution of the skills ecosystem. Code quality, security, costs, gaps, duplications, dependencies, and health reports.

When to Use This Skill

  • When the user mentions "auditar skills" or related topics
  • When the user mentions "qualidade skills" or related topics
  • When the user mentions "verificar skills ecossistema" or related topics
  • When the user mentions "saude ecossistema skills" or related topics
  • When the user mentions "skills duplicadas" or related topics
  • When the user mentions "otimizar skills" or related topics

Do Not Use This Skill When

  • The task is unrelated to skill sentinel
  • A simpler, more specific tool can handle the request
  • The user needs general-purpose assistance without domain expertise

How It Works

Meta-agent that monitors, audits, and evolves the skills ecosystem. Analyzes all skills across 7 dimensions, identifies problems, suggests improvements, and recommends new specialist skills.

Quick Summary

Area Script What it does
Discovery scanner.py Discovers all skills automatically
Quality analyzers/code_quality.py Complexity, docstrings, error handling
Security analyzers/security.py Secrets, SQL injection, HTTPS
Performance analyzers/performance.py API calls, caching, retry
Governance analyzers/governance_audit.py Rate limits, audit log, confirmations
Documentation analyzers/documentation.py SKILL.md, triggers, references
Dependencies analyzers/dependencies.py requirements.txt, versions
Cross-Skill analyzers/cross_skill.py Duplication, shared patterns
Costs cost_optimizer.py Tokens, verbosity, output
Recommendations recommender.py Gap analysis, new skills
Report report_generator.py Structured Markdown
Orchestration run_audit.py Main CLI

Location

C:\Users\renat\skills\skill-sentinel\
├── SKILL.md
├── scripts/
│   ├── requirements.txt
│   ├── config.py
│   ├── db.py
│   ├── governance.py
│   ├── scanner.py
│   ├── analyzers/
│   │   ├── code_quality.py
│   │   ├── security.py
│   │   ├── performance.py
│   │   ├── governance_audit.py
│   │   ├── documentation.py
│   │   ├── dependencies.py
│   │   └── cross_skill.py
│   ├── recommender.py
│   ├── cost_optimizer.py
│   ├── report_generator.py
│   └── run_audit.py
├── references/
│   ├── analysis_criteria.md
│   ├── security_patterns.md
│   ├── skill_template.md
│   └── schema.md
└── data/
    ├── sentinel.db
    └── reports/

Installation

pip install -r C:\Users\renat\skills\skill-sentinel\scripts\requirements.txt

Main Commands


## Auditoria Completa De Todas As Skills

python C:\Users\renat\skills\skill-sentinel\scripts\run_audit.py

## Auditar Apenas Uma Skill

python C:\Users\renat\skills\skill-sentinel\scripts\run_audit.py --skill instagram

## Apenas Recomendacoes De Novas Skills

python C:\Users\renat\skills\skill-sentinel\scripts\run_audit.py --recommend

## Comparar Com Auditoria Anterior (Tendencias)

python C:\Users\renat\skills\skill-sentinel\scripts\run_audit.py --compare

## Output Em Json (Para Processamento)

python C:\Users\renat\skills\skill-sentinel\scripts\run_audit.py --format json

## Ver Historico De Auditorias

python C:\Users\renat\skills\skill-sentinel\scripts\run_audit.py --history

## Descobrir Skills Disponiveis

python C:\Users\renat\skills\skill-sentinel\scripts\scanner.py

## Ver Audit Log Do Sentinel

python C:\Users\renat\skills\skill-sentinel\scripts\governance.py

## Verificar Banco De Dados

python C:\Users\renat\skills\skill-sentinel\scripts\db.py

1. Code Quality (Weight: 20%)

  • Cyclomatic complexity per function (threshold: 10)
  • Function size (threshold: 50 lines)
  • File size (threshold: 500 lines)
  • Docstring coverage
  • Error handling patterns (bare except, broad except)

2. Security (Weight: 20%)

  • Hardcoded secrets (tokens, passwords, API keys)
  • SQL injection (f-strings in queries)
  • Insecure HTTP URLs
  • Tokens in logs
  • Input validation

3. Performance (Weight: 15%)

  • Retry with backoff for APIs
  • Configured timeouts
  • HTTP connection reuse
  • N+1 queries
  • Async/concurrency

4. Governance (Weight: 15%)

  • Level 0: None
  • Level 1: Action logging
  • Level 2: Logging + rate limiting
  • Level 3: Complete (+ 2-step confirmations)
  • Level 4: Advanced (+ alerts and trends)

5. Documentation (Weight: 15%)

  • SKILL.md with frontmatter (name, description, version)
  • Trigger keywords (PT-BR and EN)
  • Mandatory and recommended sections
  • Reference files

6. Dependencies (Weight: 15%)

  • requirements.txt present
  • Pinned versions
  • Imported vs listed deps
  • Listed vs imported deps

7. Cross-Skill (Global Analysis)

  • Modules duplicated between skills
  • Shared Database patterns
  • Inconsistent governance
  • Extraction opportunities

Cost Optimization

Beyond the 7 dimensions, the sentinel analyzes cost impact:

  • Size of SKILL.md (tokens consumed per activation)
  • Large references without an index
  • Verbose script output
  • Absence of structured JSON output

Gap Analysis And Recommendations

The recommender identifies capabilities missing from the ecosystem by comparing with a taxonomy of 20 categories and generates ready-made SKILL.md templates for suggested new skills.

Sentinel Governance

The sentinel itself practices what it preaches:

  • All audits are recorded in action_log
  • Score history in score_history for trends
  • Reports saved in data/reports/

Common Workflows

1. First audit of the ecosystem:

python run_audit.py

Generates a complete report with scores, findings and recommendations.

2. Monitor evolution over time:

python run_audit.py --compare

Shows score delta between audits.

3. Validate a skill before deploy:

python run_audit.py --skill nome-da-skill

Focused audit with specific findings.

4. Identify the next skill to create:

python run_audit.py --recommend

Gap analysis with ready-made templates.

Report Format

The report generated in data/reports/ contains:

  1. Executive summary (score table)
  2. Trends (if there is a previous audit)
  3. Findings by severity (critical/high/medium/low/info)
  4. Analysis by skill (detailed)
  5. Recommendations for new skills
  6. Prioritized action plan

References

For technical details, consult:

  • references/analysis_criteria.md - Scoring rubrics
  • references/security_patterns.md - Security patterns
  • references/skill_template.md - Template for new skills
  • references/schema.md - Database schema

Best Practices

  • Provide clear, specific context about your project and requirements
  • Review all suggestions before applying them to production code
  • Combine with other complementary skills for comprehensive analysis

Common Pitfalls

  • Using this skill for tasks outside its domain expertise
  • Applying recommendations without understanding your specific context
  • Not providing enough project context for accurate analysis

Related Skills

  • skill-installer - Complementary skill for enhanced analysis

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.