// Diagnose and fix GitHub Actions CI failures. Inspects workflow runs and logs, identifies root causes, implements minimal fixes, and pushes to a fix branch. Use when CI is failing, red, broken, or needs diagnosis.
Generate reproducible analysis artifacts — SQL queries, Python visualizations, and summary tables — as you work through a BigQuery data analysis. Use when asked to conduct a deep dive, exploratory analysis, or investigation that goes beyond a simple data lookup.
Provide a lookup index of dbt models (BigQuery tables) to guide query writing against a data warehouse. Use when you need to query, analyze, or look up data in a dbt-powered data warehouse, or when resolving a vague data question into the right BigQuery tables to query.
Create a GitHub pull request following project conventions. Use when the user asks to create a PR, submit changes for review, or open a pull request. Handles commit analysis, branch management, and PR creation using the gh CLI tool.
Update user-facing documentation when code changes. Use when asked to update docs, review docs, handle documentation changes, run scheduled documentation tasks, or analyze recent commits for documentation needs.
Triage GitHub bug reports for actionability. Use when evaluating whether a bug issue has sufficient detail and identifying missing information from the reporter.
Detect duplicate GitHub issues using semantic search and keyword matching. Use when asked to find duplicates, check for similar issues, or set up automated duplicate detection.
| name | ci-fix |
| description | Diagnose and fix GitHub Actions CI failures. Inspects workflow runs and logs, identifies root causes, implements minimal fixes, and pushes to a fix branch. Use when CI is failing, red, broken, or needs diagnosis. |
| license | MIT |
Diagnose CI failures and implement fixes with minimal, targeted diffs. Pushes fixes to a dedicated branch without creating PRs.
Verify GitHub CLI authentication before proceeding:
gh auth status
If not authenticated, instruct the user to run gh auth login first.
Determine the failing workflow run. If working on a PR branch:
gh pr view --json statusCheckRollup --jq '.statusCheckRollup[] | select(.conclusion == "FAILURE")'
If working from a branch or run ID:
gh run list --branch <branch> --status failure --limit 5
gh run view <run-id> --verbose
Pull logs from failed steps to identify the root cause:
gh run view <run-id> --log-failed
For deeper inspection:
gh run view <run-id> --log --job <job-id>
gh run download <run-id> -D .artifacts/<run-id>
Analyze logs for common failure patterns:
Prefer the smallest fix that resolves the issue. Deterministic code fixes are better than workflow plumbing changes.
Make minimal, scoped changes matching the repository's existing style:
Create or update a dedicated fix branch:
git checkout -b ci-fix/<original-branch>
git add -A
git commit -m "fix: resolve CI failure in <job-name>
Co-Authored-By: Warp <agent@warp.dev>"
git push -u origin ci-fix/<original-branch>
If the fix branch already exists, update it:
git checkout ci-fix/<original-branch>
git pull origin <original-branch>
# make fixes
git commit -m "fix: <description>
Co-Authored-By: Warp <agent@warp.dev>"
git push
Trigger CI on the fix branch and monitor:
gh run list --branch ci-fix/<original-branch> --limit 1
gh run watch <new-run-id> --exit-status
To rerun only failed jobs:
gh run rerun <run-id> --failed
pull_request_target unless explicitly requested—it can expose secrets to untrusted codepermissions: minimal; don't broaden access to make tests passAfter fixing, provide a brief summary: