furballroller/super_cat_game/gh-debug
Claude Code and agent skill by furballroller/super_cat_game
- community
Checking that the SKILL.md file is still in the repository.
Debug GitHub Actions build failures by fetching and analyzing workflow logs. Use when CI/CD pipelines fail and you need to identify the root cause.
Install
npx vskill@latest install furballroller/super_cat_game/gh-debugSKILL.md
The same SKILL.md was published earlier as furballroller/super_cat_game/gh-debug.
Pull GitHub Actions logs for a workflow run, parse them to identify errors, and provide a clear diagnostic report.
Arguments: $ARGUMENTS
Primary Method (Recommended): Use the Python script for efficient log analysis:
This script:
- Tries build-summary artifacts first (small, focused files uploaded by CI — much faster)
- Falls back to streaming full logs if no summary artifact is available
- Filters for errors in real-time
- Stops after finding 10 errors (configurable with --max-errors)
- Shows context around each error (5 lines before/after, configurable with --context)
Fallback Method: If the Python script fails, use manual analysis:
Smart Log Fetching Strategy
- Identify failed jobs/steps using
gh run view <run-id> --log-failed - For each failed step, use targeted log extraction with grep filters
- Parse logs for: compilation errors, test failures, runtime issues
- Extract error context: ~10 lines before and after each error
Input Handling
Handle:
- Run IDs (e.g., "18391541037")
- Workflow URLs
- Most recent failed run if no argument provided (use
gh run list --status failure --limit 1)
Output Format
Provide:
- Workflow name and run number
- Job(s) that failed with step names
- Specific error messages with surrounding context (max ~50 lines per error)
- File paths and line numbers where applicable
- Suggested next steps or potential fixes
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingsoftware/template/lib/FastLED-master/.claude/skills/gh-debug/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/furballroller/super_cat_game/gh-debug)