メニュー
Use when checking e2e test health or reviewing recent e2e failures on main.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
PR review orchestrator. Triages the change, dispatches specialized sub-agents in parallel across review dimensions, synthesizes their findings, runs PR-specific checks, and produces a structured review result. Sub-agent definitions live in sub-agents/ relative to this file.
Check whether ADR numbers in the current branch conflict with ADRs already on the PR's target branch, and renumber if needed. Use before merging a PR that adds new ADRs, to avoid number collisions with concurrently merged ADRs.
Use when the user wants to tag a release, cut a release candidate, or ship a new version. Also use when asking about release process, versioning, or how GoReleaser is configured.
Standalone procedure for reviewing any code change. Identifies the change, reads surrounding source, evaluates across six review dimensions, and compiles structured findings. Can be invoked directly for local review or delegated to by the pr-review skill.
Use when you need to analyze the delta between agent review and human review on a PR to identify structural repo improvements that would close review gaps or justify increased agent autonomy.
Step-by-step procedure for implementing a GitHub issue. Gathers context, discovers repo conventions, plans the change, implements, verifies with tests and linters, and commits to a feature branch.
| name | e2e-health |
| description | Use when checking e2e test health or reviewing recent e2e failures on main. |
| allowed-tools | Bash(bash skills/e2e-health/scripts/list-runs.sh:*), Bash(gh run view:*) |
Check the health of the E2E Tests workflow on main over the last 2 days, summarize results in a table, and explain any failures.
bash skills/e2e-health/scripts/list-runs.sh # default: last 2 days
bash skills/e2e-health/scripts/list-runs.sh "7 days ago" # custom lookback
The argument is any string date -d accepts. Returns JSON with fields: databaseId, displayTitle, conclusion, status, createdAt, url.
Format the results as a markdown table with clickable links:
| Status | Run | Commit Title | When |
|---|---|---|---|
| pass/fail/in_progress | run-id (linked) | displayTitle | relative time |
Use a green checkmark for success, red X for failure, and a spinner for in-progress.
To determine the Status column: check status first — if it is not completed, the run is in-progress (conclusion will be null). If status is completed, use conclusion (success or failure).
For each failed run, fetch the failed step logs:
gh run view <run-id> --log-failed 2>&1 | grep -iE "(FAIL|--- FAIL|Error|panic|timeout)"
Read the matched lines and provide a brief explanation of why the run failed. Common failure categories:
ready-for-triage label path)End with a one-line verdict: whether main is healthy, degraded, or broken based on the pattern of results.