maxwell2732/claudecode-research-harness-workflow/ci
Claude Code and agent skill by maxwell2732/claudecode-research-harness-workflow
- community
Checking that the SKILL.md file is still in the repository.
CI red? Call us. Pipeline fire brigade deploys. Use when user mentions CI failures, build errors, test failures, or pipeline issues. Do NOT load for: local builds, standard implementation work, reviews, or setup.
Install
npx vskill@latest install maxwell2732/claudecode-research-harness-workflow/ciSKILL.md
CI/CD Skills
A set of skills for resolving CI/CD pipeline issues.
Trigger Conditions
- "CI failed", "GitHub Actions failure"
- "Build error", "Tests won't pass"
- "Fix the pipeline"
Feature Details
| Feature | Details | Trigger | |
|---|---|---|---|
| Failure Analysis | See references/analyzing-failures.md | "Read the log", "Investigate the cause" | |
| Test Fixing | See references/fixing-tests.md | "Fix the test", "Suggest a fix" |
Execution Steps
- Test vs. Implementation determination (Step 0)
- Classify user intent (analyze or fix)
- Assess complexity (see below)
- Read the appropriate reference file from "Feature Details" above, or launch the ci-cd-fixer sub-agent
- Review results and re-run if necessary
Step 0: Test vs. Implementation Determination (Quality Gate)
When a CI failure occurs, first triage the cause:
Prohibited Actions (Anti-tampering)
Decision Flow
When Approval Is Needed
If changes to tests/configuration are unavoidable:
Using Extended Git Log Flags (CC 2.1.49+)
Use structured logs to identify the commit that caused the CI failure.
Identifying the Culprit Commit
Key Use Cases
| Use | Flag | Effect | ||
|---|---|---|---|---|
| Identify failure cause | `--format="%h | %s"` | Structured commit list | |
| Chronological tracking | --topo-order | Track considering merge order | ||
| Understand change impact | --raw | Detailed file change display | ||
| Exclude-merge analysis | --cherry-pick --no-merges | Extract only real commits |
Sample Output
Sub-agent Integration
Launch ci-cd-fixer via the Task tool when the following conditions are met:
- Fix → re-run → fail loop has occurred 2 or more times
- Or the error spans multiple files in a complex case
Launch pattern:
ci-cd-fixer operates with safety first (default dry-run mode). See agents/ci-cd-fixer.md for details.
For VibeCoder
Security
- Security scanPassed, 90 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 repositoryCheckingskills/ci/SKILL.md
Popularity
- 7-day trend score
- 0
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/maxwell2732/claudecode-research-harness-workflow/ci)