一键导入
ci-monitor
Monitor GitHub Actions CI runs, identify failures, and coordinate specialist agent fixes using GOAP/ADR workflow
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 GitHub Actions CI runs, identify failures, and coordinate specialist agent fixes using GOAP/ADR workflow
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
Enhance session checkpoints with git context and diff summaries. Use after completing significant work to enrich checkpoint.md files with repository state, recent commits, and code change summaries. Triggers include "enhance checkpoint", "update checkpoint with git", "add git context to checkpoint", or when finishing a multi-file change session.
Use for model training, hyperparameter tuning, and Modal GPU training.
Use when invoking training, evaluation, and dataset preparation via CLI. Provides all standard commands for this project.
Multi-perspective code analysis using three AI personas (RYAN, FLASH, SOCRATES) for comprehensive decision-making. Use when complex code decisions need analysis from multiple viewpoints, or when avoiding single-perspective blind spots is critical.
Use for authentication management, token validation, and credential troubleshooting.
Use for secrets management, credentials handling, and security best practices.
| name | ci-monitor |
| description | Monitor GitHub Actions CI runs, identify failures, and coordinate specialist agent fixes using GOAP/ADR workflow |
This skill monitors CI/CD pipelines and orchestrates fixes using specialist agents.
git push# Get latest runs
gh run list --repo <owner>/<repo> --limit 5
# Watch in real-time
gh run watch --repo <owner>/<repo>
# View specific run
gh run view <run-id> --repo <owner>/<repo>
# Get failed run ID
gh run list --json databaseId,status,conclusion --jq '.[] | select(.conclusion == "failure") | .databaseId'
# View failure details
gh run view <run-id> --log-failed
# Get job-level failures
gh run view <run-id> --json jobs --jq '.jobs[] | select(.conclusion == "failure")'
| Failure Pattern | Specialist Agent | Skill |
|---|---|---|
flake8, ruff, black errors | code-quality | @skill code-quality |
pytest failures | testing-workflow | @skill testing-workflow |
mypy type errors | code-quality | @skill code-quality |
npm, tsc, frontend build | frontend (if exists) | Create skill |
modal, training, GPU | model-training | @skill model-training |
| Workflow config, runner issues | gh-actions | @skill gh-actions |
| Secrets, tokens, credentials | security | @skill security |
@task
**Description**: Fix <failure type> in CI run <run-id>
**Prompt**:
CI run <run-id> failed with:
```
Fix this issue using . After fixing:
### 5. Track Progress
Create/update GOAP action item:
```markdown
## Current Action Items
- [x] <completed fix>
- [ ] <current fix in progress>
- [ ] <remaining fixes>
# Wait for new run
sleep 30 && gh run list --limit 1
# Check if passed
gh run view <new-run-id>
# If still failing, repeat from step 2
1. git commit → git push
2. gh run list → get run-id
3. gh run view <id> → identify failures
4. FOR EACH failure:
a. Analyze error type → determine specialist needed
b. Spawn specialist agent with @task
c. Agent fixes → commits → pushes
d. gh run view <new-id> → verify
e. Repeat until all pass
5. Update GOAP.md with completed items
6. NEVER skip: each fix must go through full cycle
# 1. Push code
git add -A && git commit -m "feat: add new feature" && git push
# 2. Monitor CI
gh run watch
# 3. CI fails - check what failed
gh run view 123456 --log-failed
# Output shows: flake8 E501 errors in src/model.py
# 4. Spawn specialist
@task
**Description**: Fix flake8 E501 errors
**Prompt**: CI run 123456 failed with flake8 E501 errors in src/model.py. Fix using @skill code-quality.
**Subagent**: general-purpose
# 5. Agent fixes and pushes
# Agent reports: "Fixed, pushed commit abc123"
# 6. Verify
gh run view 123457 # New run ID
# 7. If passed, update GOAP
# Mark action complete in plans/GOAP.md
## Current Action Items
- [x] Fix flake8 E501 errors (CI run 123456)
- [x] Fix mypy type errors (CI run 123457)
- [ ] Fix frontend build errors (CI run 123458)
# If architectural decision needed
python scripts/adr-scaffold.py "Title"
# Edit plans/ADR-XXX-*.md
# Document problem, decision, consequences
| Command | Purpose |
|---|---|
gh run list | List recent runs |
gh run view <id> | View run details |
gh run view <id> --log-failed | View failure logs |
gh run watch | Watch in real-time |
gh run rerun <id> | Re-run failed run |
gh workflow list | List workflows |
gh workflow run <name> | Trigger workflow |
git-workflow - Git operations, commits, pushescode-quality - Linting, formatting, type checkingtesting-workflow - Test failures, coveragegh-actions - Workflow configuration, runnersgoap - Planning, ADR, action items