till-crazy-tears-us-apart/skills/repo-audit
skills/repo-audit/SKILL.md
--- name: repo-audit description: Analyzes a GitHub repository. Stage 1: Fetches metadata (README, Size) using GH CLI to assess complexity. Stage 2: Clones to a temporary sandbox for deep inspection upon user confirmation. disable-model-invocation: true allowed-tools: Bash, Glob, Grep, Read --- # Repository Audit Skill This skill allows you to safely inspect GitHub repositories without polluting your main workspace. It operates in two stages to prevent unnecessary cloning of massive repositori
$ install --global
skillsauthnpx skillsauth add till-crazy-tears-us-apart/claude-code-engineering-suite skills/repo-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 13, 2026, 4:28 AM158.3s4 files scanned
SKILL.md
- name:
- repo-audit
- description:
- Analyzes a GitHub repository. Stage 1: Fetches metadata (README, Size) using GH CLI to assess complexity. Stage 2: Clones to a temporary sandbox for deep inspection upon user confirmation.
- disable-model-invocation:
- true
- allowed-tools:
- Bash, Glob, Grep, Read
Repository Audit Skill
This skill allows you to safely inspect GitHub repositories without polluting your main workspace. It operates in two stages to prevent unnecessary cloning of massive repositories.
Requirements:
gitgh(GitHub CLI) - Must be authenticated (gh auth login)
Usage
/repo-audit <url>
Workflow
Stage 1: Reconnaissance (Metadata Analysis)
- Validate URL: Ensure the input is a valid GitHub URL.
- Fetch Metadata: Execute
gh repo view <url> --json description,stargazerCount,diskUsage,defaultBranchRef. - Fetch README:
- Extract the
owner/repofrom the URL. - Execute
gh api repos/<owner>/<repo>/readme --jq .content | python -c "import sys, base64; print(base64.b64decode(sys.stdin.read().strip()).decode('utf-8', errors='replace'))".
- Extract the
- Report & Ask: Present a summary including the full README content.
- CRITICAL CHECK: If
diskUsage> 500MB, WARN the user. - YOU MUST Ask the user if they want to proceed with a full clone (Stage 2).
- STOP generation here. Wait for user confirmation.
- CRITICAL CHECK: If
Stage 2: Deep Inspection (Sandboxed Clone)
Only execute this after user confirmation.
- Run Runner Script: Execute the bundled Python script. This script performs a secondary size check, clones the repo to
%TEMP%, and generates a structure report. - Analyze: Review the generated file tree and tech stack.
- Interact: Use standard tools (
Glob,Grep,Read) to explore the files in the temp directory. - Cleanup: When the user is done or the session ends, YOU MUST delete the temp directory using the command provided in the report.
Execution Instructions
To run the analysis script (Stage 2), execute:
# Windows (PowerShell) - Adapt path as needed
# Note: The script includes a 500MB safety limit. Use --force to override.
python ~/.claude/skills/repo-audit/scripts/audit_runner.py <repo_url> [--force]
Related Skills
till-crazy-tears-us-apart/remy-insight
data-ai
VerifiedTrustedCommunity
Deep repository analysis with multi-agent parallel perspectives. Requires /init + /remy-index as prerequisites. Produces structured research reports.
27SKILL.mdUpdated May 30, 2026
till-crazy-tears-us-apart/remy-ci
tools
VerifiedTrustedCommunity
Analyze CI/CD failure logs to diagnose build, test, and gate failures. Supports GitHub Actions (gh CLI), local log files, and pasted logs. Produces evidence packets for /remy-patch.
27SKILL.mdUpdated May 30, 2026
till-crazy-tears-us-apart/remy-testgen
development
VerifiedTrustedCommunity
Generate persistent unit tests for existing or stub code. Supports post-hoc testing (default) and TDD mode (--tdd). Multi-angle agent analysis at medium/high effort levels.
27SKILL.mdUpdated May 26, 2026
till-crazy-tears-us-apart/skills/remy-secure
tools
VerifiedTrustedCommunity
--- name: remy-secure description: Review branch changes for security vulnerabilities. Multi-stage: regex pre-scan, parallel agents, and false-positive filtering. allowed-tools: Read, Grep, Glob, Bash, AskUserQuestion, Agent argument-hint: "[low|medium|high] [diff_range (optional, e.g. HEAD~3...HEAD)]" disable-model-invocation: true --- # Security Audit Protocol Security-focused review of code changes on the current branch. Identifies exploitable vulnerabilities with high confidence (≥ 8/10),
27SKILL.mdUpdated May 26, 2026