Skill Audit Report

completeness (55%)

• Rich runbook body (14354 words, 159 sections, 514 bullets)
• Has 1 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (45%)

• Well-structured body (159 sections, 514 bullets)

• Add a clear, concise description (20-200 characters ideal)
• Replace vague words: things

actionability (75%)

• Body contains actionable instructions (0 action items, 19 numbered)
• Body references tools or includes code
• No inputs defined (not always needed)

safety (30%)

• Mentions error handling concepts

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (65%)

• Contains 1 executable code block(s): bash
• [bash] cp engineering-team/skills/senior-fullstack/profiles/saas-startup.json \
• Contains 4 inline command(s):
• $ bash cp engineering-team/skills/senior-fullstack/profiles/saas-startup.json \ ...
• $ npm install docx
• $ pip install mkdocs-material
• $ pip install mkdocs-material mkdocs-redirects
• HIGH: 1 suspicious pattern(s) found

• [EXFILTRATION] Node child_process.exec — potential RCE

completeness (55%)

• Rich runbook body (5125 words, 16 sections, 120 bullets)
• Has 3 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (45%)

• Well-structured body (16 sections, 120 bullets)

• Add a clear, concise description (20-200 characters ideal)
• Replace vague words: things

actionability (75%)

• Body contains actionable instructions (1 action items, 11 numbered)
• Body references tools or includes code
• No inputs defined (not always needed)

safety (30%)

• Mentions error handling concepts

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (65%)

• Contains 1 executable code block(s): bash
• [bash] # 1. Always start from dev
• Contains 2 inline command(s):
• $ bash # 1. Always start from dev git checkout dev git pull origin dev # 2. Creat...
• $ Python tool and comprehensive reference docs on visual design, platform specific...
• HIGH: 1 suspicious pattern(s) found

• [EXFILTRATION] Node child_process.exec — potential RCE

completeness (43%)

• Rich runbook body (715 words, 11 sections, 10 bullets)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add usage examples showing how to invoke this skill
• Extract warnings into a dedicated ## Gotchas section

clarity (65%)

• Well-structured body (11 sections, 10 bullets)
• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)

actionability (35%)

• Runbook body present
• No inputs defined (not always needed)

• Add action-oriented instructions (bullet points starting with verbs)
• Include code examples or tool references in the body

safety (5%)

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)
• Address what happens when things go wrong (errors, failures, retries)

testability (15%)

• Structured body describes expected behavior

• Add examples showing how to use this skill
• Add examples with concrete parameter values

trust (100%)

• No executable code or suspicious patterns detected

completeness (55%)

• Rich runbook body (870 words, 20 sections, 42 bullets)
• Has 9 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (65%)

• Well-structured body (20 sections, 42 bullets)
• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)

actionability (75%)

• Body contains actionable instructions (0 action items, 6 numbered)
• Body references tools or includes code
• No inputs defined (not always needed)

safety (30%)

• Mentions error handling concepts

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (100%)

• Contains 4 executable code block(s): bash, python
• [bash] git clone https://github.com/YOUR_USERNAME/claude-skills.git
• [bash] # Example: new engineering skill
• [python] #!/usr/bin/env python3
• [bash] # Structure validation
• Contains 4 inline command(s):
• $ bash git clone https://github.com/YOUR_USERNAME/claude-skills.git cd claude-skil...
• $ bash # Example: new engineering skill mkdir -p engineering/my-new-skill/scripts ...
• $ python #!/usr/bin/env python3 """Tool Name — brief description.""" import argpa...
• $ bash # Structure validation python3 engineering/skill-tester/scripts/skill_valid...
• Executable code found — no suspicious patterns detected

completeness (55%)

• Rich runbook body (1239 words, 18 sections, 16 bullets)
• Has 9 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (65%)

• Well-structured body (18 sections, 16 bullets)
• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)

actionability (75%)

• Body contains actionable instructions (0 action items, 8 numbered)
• Body references tools or includes code
• No inputs defined (not always needed)

safety (5%)

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)
• Address what happens when things go wrong (errors, failures, retries)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (100%)

• Contains 2 executable code block(s): bash, python
• [python] #!/usr/bin/env python3
• [bash] # Structure validation
• Contains 2 inline command(s):
• $ python #!/usr/bin/env python3 """Tool Name — brief description.""" import argpa...
• $ bash # Structure validation python3 engineering/skill-tester/scripts/skill_valid...
• Executable code found — no suspicious patterns detected

completeness (55%)

• Rich runbook body (359 words, 7 sections, 6 bullets)
• Has 4 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (65%)

• Well-structured body (7 sections, 6 bullets)
• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)

actionability (50%)

• Runbook body present
• Body references tools or includes code
• No inputs defined (not always needed)

• Add action-oriented instructions (bullet points starting with verbs)

safety (5%)

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)
• Address what happens when things go wrong (errors, failures, retries)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (100%)

• Contains 4 executable code block(s): bash, javascript
• [javascript] activate_skill(name="senior-architect")
• [javascript] activate_skill(name="cs-engineering-lead")
• [bash] python3 marketing-skill/content-production/scripts/seo_checker.py article.txt
• [bash] ./scripts/gemini-install.sh
• Contains 2 inline command(s):
• $ bash python3 marketing-skill/content-production/scripts/seo_checker.py article.t...
• $ bash ./scripts/gemini-install.sh
• Executable code found — no suspicious patterns detected

completeness (55%)

• Rich runbook body (2800 words, 78 sections, 37 bullets)
• Has 58 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (65%)

• Well-structured body (78 sections, 37 bullets)
• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)

actionability (75%)

• Body contains actionable instructions (3 action items, 9 numbered)
• Body references tools or includes code
• No inputs defined (not always needed)

safety (30%)

• Mentions error handling concepts

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (60%)

• Contains 55 executable code block(s): bash, cmd, javascript
• [bash] # In Claude Code, run:
• [bash] # Option 1: Universal installer
• [bash] # Setup script for Gemini CLI
• [bash] # Install from ClawHub
• [bash] npx agent-skills-cli add alirezarezvani/claude-skills
• [bash] # In Claude Code, run:
• [bash] # Install by domain (bundles of skills)
• [bash] # Marketing
• [bash] # Update all installed plugins
• [bash] # Remove specific plugin
• [bash] # Install to all supported agents
• [bash] # Claude Code only
• [bash] # Dry run to see what will be installed
• [bash] # Content Creator
• [bash] # CEO Advisor
• [bash] # Product Manager Toolkit
• [bash] # Senior PM Expert
• [bash] # Core Engineering
• [bash] # Regulatory & Quality Leadership
• [bash] # Install marketing skills to Claude Code (for content strategist)
• [bash] # Full engineering suite to Claude Code
• [bash] git clone https://github.com/alirezarezvani/claude-skills.git
• [bash] # Optional dependencies for future features
• [bash] # Copy all skills
• [bash] # Copy to project directory
• [bash] # Copy to project directory
• [bash] # Test marketing tools
• [bash] # Check Claude Code installation
• [bash] # Create test file
• [bash] # macOS
• [bash] # Install entire domain bundle
• [bash] # Check network
• [bash] # Verify installation
• [bash] chmod +x marketing-skill/content-creator/scripts/*.py
• [bash] # Install Python dependencies
• [bash] # Check SKILL.md exists
• [bash] # Reset skills directory
• [bash] # Cursor uses project-local skills
• [bash] # GitHub Copilot uses .github/skills/
• [bash] # Remove from Claude Code
• [bash] # Clone directory
• [bash] # Example: Remove content-creator from Claude Code
• [bash] git clone https://github.com/alirezarezvani/claude-skills.git
• [bash] ./scripts/gemini-install.sh
• [javascript] // Activate a core skill
• [bash] python3 marketing-skill/content-production/scripts/brand_voice_analyzer.py artic
• [bash] # Install from ClawHub registry
• [bash] # Clone the repository
• [bash] # List installed skills
• [bash] python3 engineering-team/senior-security/scripts/threat_modeler.py --help
• [bash] # Install all skills to Codex
• [bash] # Clone repository
• [cmd] REM Clone repository
• [bash] # Clone repository
• [bash] # Check installed skills
• Contains 53 inline command(s):
• $ bash # In Claude Code, run: /plugin marketplace add alirezarezvani/claude-skills...
• $ bash # Option 1: Universal installer npx agent-skills-cli add alirezarezvani/cla...
• $ bash # Setup script for Gemini CLI git clone https://github.com/alirezarezvani/c...
• $ bash # Install from ClawHub clawhub install alirezarezvani/claude-skills # Or m...
• $ bash npx agent-skills-cli add alirezarezvani/claude-skills
• $ bash # In Claude Code, run: /plugin marketplace add alirezarezvani/claude-skills
• $ bash # Install by domain (bundles of skills) /plugin install marketing-skills@cl...
• $ bash # Marketing /plugin install content-creator@claude-code-skills /plugin inst...
• $ bash # Update all installed plugins /plugin update # Update specific plugin /pl...
• $ bash # Remove specific plugin /plugin remove marketing-skills # Remove marketpl...
• $ bash # Install to all supported agents npx agent-skills-cli add alirezarezvani/c...
• $ bash # Claude Code only npx agent-skills-cli add alirezarezvani/claude-skills --...
• $ bash # Dry run to see what will be installed npx agent-skills-cli add alirezarez...
• $ bash # Content Creator npx agent-skills-cli add alirezarezvani/claude-skills/mar...
• $ bash # CEO Advisor npx agent-skills-cli add alirezarezvani/claude-skills/c-level...
• $ bash # Product Manager Toolkit npx agent-skills-cli add alirezarezvani/claude-sk...
• $ bash # Senior PM Expert npx agent-skills-cli add alirezarezvani/claude-skills/pr...
• $ bash # Core Engineering npx agent-skills-cli add alirezarezvani/claude-skills/en...
• $ bash # Regulatory & Quality Leadership npx agent-skills-cli add alirezarezvani/c...
• $ bash # Install marketing skills to Claude Code (for content strategist) npx agen...
• $ bash # Full engineering suite to Claude Code npx agent-skills-cli add alirezarez...
• $ bash git clone https://github.com/alirezarezvani/claude-skills.git cd claude-ski...
• $ bash # Optional dependencies for future features pip install pyyaml
• $ bash # Copy all skills cp -r marketing-skill ~/.claude/skills/ cp -r c-level-adv...
• $ bash # Copy to project directory mkdir -p .cursor/skills cp -r marketing-skill ....
• $ bash # Copy to project directory mkdir -p .github/skills cp -r engineering-team ...
• $ bash # Test marketing tools python3 marketing-skill/content-production/scripts/b...
• $ bash # Check Claude Code installation ls ~/.claude/skills/ # Check Cursor insta...
• $ bash # Create test file echo "Sample content for analysis" > test-article.txt #...
• $ bash # macOS brew install node # Ubuntu/Debian sudo apt-get install nodejs npm ...
• $ bash # Install entire domain bundle npx agent-skills-cli add alirezarezvani/clau...
• $ bash # Check network curl https://github.com/alirezarezvani/claude-skills # Che...
• $ bash # Verify installation ls -R ~/.claude/skills/ # Restart Claude Code # Clos...
• $ bash chmod +x marketing-skill/content-creator/scripts/*.py chmod +x c-level-advi...
• $ bash # Install Python dependencies pip install pyyaml # Or use Python 3 specifi...
• $ bash # Check SKILL.md exists ls ~/.claude/skills/content-creator/SKILL.md # Ver...
• $ bash # Reset skills directory rm -rf ~/.claude/skills/ mkdir -p ~/.claude/skills...
• $ bash # Cursor uses project-local skills # Verify project directory has .cursor/s...
• $ bash # GitHub Copilot uses .github/skills/ # Verify directory structure ls .git...
• $ bash # Remove from Claude Code rm -rf ~/.claude/skills/alirezarezvani/claude-ski...
• $ bash # Clone directory rm -rf claude-skills/ # Copied skills rm -rf ~/.claude/s...
• $ bash # Example: Remove content-creator from Claude Code rm -rf ~/.claude/skills/...
• $ bash git clone https://github.com/alirezarezvani/claude-skills.git cd cl...
• $ bash ./scripts/gemini-install.sh
• $ bash python3 marketing-skill/content-production/scripts/brand_voice_analyzer.py ...
• $ bash # Install from ClawHub registry clawhub install alirezarezvani/claude-skill...
• $ bash # Clone the repository git clone https://github.com/alirezarezvani/claude-s...
• $ bash # List installed skills ls ~/.openclaw/skills/ # Verify a skill's frontmat...
• $ bash python3 engineering-team/senior-security/scripts/threat_modeler.py --help p...
• $ bash # Install all skills to Codex npx agent-skills-cli add alirezarezvani/claud...
• $ bash # Clone repository git clone https://github.com/alirezarezvani/claude-skill...
• $ bash # Clone repository git clone https://github.com/alirezarezvani/claude-skill...
• $ bash # Check installed skills ls ~/.codex/skills/ # Verify skill structure ls ~...
• HIGH: 2 suspicious pattern(s) found

• [DESTRUCTIVE] Destructive rm -rf on root or home directory
• [PRIVILEGE] Requests elevated privileges

completeness (55%)

• Rich runbook body (2376 words, 25 sections, 16 bullets)
• Has 13 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (65%)

• Well-structured body (25 sections, 16 bullets)
• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)

actionability (60%)

• Body has some actionable content
• Body references tools or includes code
• No inputs defined (not always needed)

• Add more action-oriented bullet points or numbered steps

safety (30%)

• Mentions error handling concepts

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (100%)

• Contains 9 executable code block(s): bash
• [bash] # Clone the repository
• [bash] # Add the marketplace
• [bash] npx agent-skills-cli add alirezarezvani/claude-skills --agent codex
• [bash] bash <(curl -s https://raw.githubusercontent.com/alirezarezvani/claude-skills/ma
• [bash] git clone https://github.com/alirezarezvani/claude-skills.git
• [bash] # 1. Convert all skills to all tools (takes ~15 seconds)
• [bash] # Claude Code
• [bash] python3 engineering/skill-security-auditor/scripts/skill_security_auditor.py /pa
• [bash] # SaaS health check
• Contains 11 inline command(s):
• $ python scripts/sync-hermes-skills.py
• $ bash # Clone the repository git clone https://github.com/alirezarezvani/claude-s...
• $ bash # Add the marketplace /plugin marketplace add alirezarezvani/claude-skills ...
• $ bash npx agent-skills-cli add alirezarezvani/claude-skills --agent codex # Or: g...
• $ bash bash <(curl -s https://raw.githubusercontent.com/alirezarezvani/claude-skil...
• $ bash git clone https://github.com/alirezarezvani/claude-skills.git # Copy any sk...
• $ python scripts/sync-hermes-skills.py --verbose
• $ bash # 1. Convert all skills to all tools (takes ~15 seconds) ./scripts/convert....
• $ bash # Claude Code cp agents/personas/startup-cto.md ~/.claude/agents/ # Any to...
• $ bash python3 engineering/skill-security-auditor/scripts/skill_security_auditor.p...
• $ bash # SaaS health check python3 finance/saas-metrics-coach/scripts/metrics_calc...
• Executable code found — no suspicious patterns detected

completeness (55%)

• Rich runbook body (950 words, 20 sections, 74 bullets)
• Has 5 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (65%)

• Well-structured body (20 sections, 74 bullets)
• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)

actionability (75%)

• Body contains actionable instructions (1 action items, 5 numbered)
• Body references tools or includes code
• No inputs defined (not always needed)

safety (30%)

• Mentions error handling concepts

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (100%)

• Contains 4 executable code block(s): bash, python
• [bash] # Read the script first
• [bash] # Use virtual environments
• [python] import os
• [bash] # Audit Python dependencies
• Contains 4 inline command(s):
• $ bash # Read the script first cat scripts/tool.py # Check for: # - External netw...
• $ bash # Use virtual environments python -m venv venv source venv/bin/activate pip...
• $ python import os import re def safe_read_file(filename: str) -> str: """Saf...
• $ bash # Audit Python dependencies pip install safety safety check # Or use pip-a...
• Executable code found — no suspicious patterns detected

completeness (55%)

• Rich runbook body (2197 words, 42 sections, 109 bullets)
• Has 12 code block(s) in body (inline examples)
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add a dedicated ## Examples section for discoverability
• Extract warnings into a dedicated ## Gotchas section

clarity (45%)

• Well-structured body (42 sections, 109 bullets)

• Add a clear, concise description (20-200 characters ideal)
• Replace vague words: things

actionability (75%)

• Body contains actionable instructions (4 action items, 1 numbered)
• Body references tools or includes code
• No inputs defined (not always needed)

safety (5%)

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)
• Address what happens when things go wrong (errors, failures, retries)

testability (60%)

• Body contains inline examples
• Body code blocks serve as examples
• Structured body describes expected behavior

trust (100%)

• Contains 1 executable code block(s): python
• [python] #!/usr/bin/env python3
• Contains 1 inline command(s):
• $ python #!/usr/bin/env python3 """Tool description — what it does in one line."""...
• Executable code found — no suspicious patterns detected

completeness (63%)

• Has 21 steps
• Has 1 examples
• Body contains warning/caveat language
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Extract warnings into a dedicated ## Gotchas section

clarity (45%)

• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)
• Too many steps (21) — consider grouping or splitting the skill

actionability (51%)

• Steps reference specific tools or commands
• No inputs defined (not always needed)

• Start each step with an action verb (Run, Check, Verify, etc.)

safety (30%)

• Mentions error handling concepts

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)

testability (70%)

• Has 1 examples
• Examples include parameters/flags

• Add descriptions to examples showing expected behavior

trust (100%)

• Contains 10 executable code block(s): bash
• [bash] python -m scripts.aggregate_benchmark <workspace>/iteration-N --skill-name <name
• [bash] python -m scripts.run_loop \
• [bash] echo "Review this skill for Anthropic compliance:
• [bash] tessl skill review <skill-path>
• [bash] # Claude Code marketplace (via plugin in repo)
• [bash] # Users setup with:
• [bash] clawhub publish ./category/skill-name
• [bash] # Users install with:
• [bash] # 1. Register marketplace (if not already)
• [bash] cd ~/workspace/projects/claude-skills
• Contains 11 inline command(s):
• $ git revert <commit>
• $ bash python -m scripts.aggregate_benchmark <workspace>/iteration-N --skill-name ...
• $ bash python -m scripts.run_loop \ --eval-set <trigger-eval.json> --skill...
• $ bash echo "Review this skill for Anthropic compliance: 1. No malware, exploit co...
• $ bash tessl skill review <skill-path>
• $ bash # Claude Code marketplace (via plugin in repo) # Users install with: /plugi...
• $ bash # Users setup with: ./scripts/gemini-install.sh
• $ bash clawhub publish ./category/skill-name
• $ bash # Users install with: npx agent-skills-cli add alirezarezvani/claude-skills...
• $ bash # 1. Register marketplace (if not already) # In Claude Code: /plugin market...
• $ bash cd ~/workspace/projects/claude-skills # NOTE: generate-docs.py and static.y...
• Executable code found — no suspicious patterns detected

completeness (33%)

• Rich runbook body (650 words, 16 sections, 40 bullets)
• Runbook style (no formal inputs)

• Add a description explaining what this skill does
• Add usage examples showing how to invoke this skill
• Add gotchas/caveats to warn about common failure points

clarity (65%)

• Well-structured body (16 sections, 40 bullets)
• Language is concrete and specific

• Add a clear, concise description (20-200 characters ideal)

actionability (75%)

• Body contains actionable instructions (0 action items, 5 numbered)
• Body references tools or includes code
• No inputs defined (not always needed)

safety (5%)

• Add gotchas/caveats to warn about common failure points
• Add specific gotchas (describe what can go wrong and why)
• Address what happens when things go wrong (errors, failures, retries)

testability (15%)

• Structured body describes expected behavior

• Add examples showing how to use this skill
• Add examples with concrete parameter values

trust (100%)

• No executable code or suspicious patterns detected