一键导入
check-ci
Monitor CI/CD pipeline status after pushes and investigate failures.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Monitor CI/CD pipeline status after pushes and investigate failures.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Manual E2E tester that starts the app and exercises new features end-to-end
Generate a single self-contained HTML page that is genuinely visual AND interactive — charts, diagrams, motion, tabs, comparison toggles, click-to-expand, base64-inlined images, opinionated typography. Use whenever the user wants ANY rich visual artifact from arbitrary content: explainer, research write-up, PRD or spec page, pitch, internal one-pager, "make this less boring" rebuild, scroll-snap deck, landing-style summary, distilled report. Trigger phrasings: "make me a page about X", "turn this PDF/doc into something visual", "build me a deck/talk/pitch", "explain Y in a visual way", "make this readable", "give it some eye candy", "I want something I can show the team", "less boring version of this", "rebuild that page", "redo it with more visuals". Output is one .html file that renders identically when DM'd — CDN libraries (Tailwind, Chart.js, D3, GSAP, Mermaid, Lucide) load from stable jsdelivr/unpkg URLs; every image is base64-inlined. Not for plain Markdown docs (use technical-writer), not for code revi
Vision-based visual QA reviewer — captures rendered output (live web pages, static HTML artifacts, PDFs) as screenshots, inspects them with a designer's eye for layout defects a human catches instantly, and normalizes findings into the verify pipeline format
Independent second-opinion reviewer that shells out to the local Codex CLI for a broad code review, then normalizes findings into the verify pipeline format
Comment-hygiene-only reviewer — flags ephemeral review-ID references, historical change-narration, stale comments, reviewer-appeasement, and redundant restating in the scoped diff, and normalizes findings into the verify pipeline format
Adversarial cooperation loop — player implements, /verify reviews, creates PR, passes CI
| name | check-ci |
| description | Monitor CI/CD pipeline status after pushes and investigate failures. |
| argument-hint | [optional: commit-sha or branch] |
| allowed-tools | ["Read","Bash","Grep","Glob","Skill"] |
Monitor CI/CD pipeline status after pushing commits. When failures occur, delegate to the debugger skill for systematic investigation and evidence-based root cause analysis.
Optional commit reference: $ARGUMENTS (e.g., HEAD, abc1234, feature-branch)
debugger to investigateThe command automatically detects the CI/CD platform by examining configuration files:
GitHub Actions
.github/workflows/*.yml or .github/workflows/*.yamlgh CLI for API accessGitLab CI
.gitlab-ci.ymlglab CLI for API accessCircleCI
.circleci/config.ymlJenkins
Jenkinsfile or .jenkinsTravis CI
.travis.ymlAzure DevOps
azure-pipelines.yml# Get latest commit
git rev-parse HEAD
# Get commit details
git log -1 --format="%H %s"
# Check push status
git log origin/[branch]..HEAD
For GitHub Actions:
# List workflow runs for commit
gh run list --commit [SHA]
# Get run details
gh run view [RUN_ID]
# Watch run status
gh run watch [RUN_ID]
For GitLab CI:
# Get pipeline for commit
glab ci list --per-page 1
# View pipeline details
glab ci view [PIPELINE_ID]
# Get job logs
glab ci trace [JOB_ID]
Display status updates every 5-10 seconds:
⏳ CI Status: In Progress
✓ Build: Success
⏳ Tests: Running... (2m 15s)
⏳ Lint: Queued
- Deploy: Pending
When CI fails, delegate investigation to the debugger skill:
Use the Skill tool to invoke debugger with:
Example prompt:
Investigate CI failure for commit [SHA]:
- Failed jobs: [job names]
- CI platform: [GitHub Actions/GitLab CI/etc]
- Job logs available via: [command to fetch logs]
Please gather evidence about:
1. What specifically failed (tests, build, lint, etc.)
2. Exact error messages and stack traces
3. Which files/changes are involved
4. Root cause based on evidence
Provide a complete investigation report.
The debugger skill will:
✅ CI Status: All checks passed!
📊 Summary:
✓ Build: Success (1m 23s)
✓ Tests: 156 passed (2m 45s)
✓ Lint: No issues (0m 15s)
✓ Security: No vulnerabilities (0m 38s)
🎉 Your code is ready to merge!
❌ CI Status: Failed
📊 Summary:
✓ Build: Success (1m 23s)
❌ Tests: 2 failed, 154 passed (2m 45s)
⚠️ Lint: 3 warnings (0m 15s)
✓ Security: No vulnerabilities (0m 38s)
🔍 Launching `debugger` to investigate...
Then present the skill's complete investigation report, which will include:
The skill's report provides evidence-based findings without implementing fixes.
Users can customize behavior via environment variables:
CI_CHECK_TIMEOUT: Maximum time to wait for CI completion (default: 30m)CI_POLL_INTERVAL: How often to check status (default: 10s)debugger immediatelydebugger:
# Check CI for latest commit
/check-ci
# Check CI for specific commit
/check-ci abc1234
# Check CI for a branch
/check-ci feature/new-api