Skip to content

wandelbotsgmbh/wandelbots-nova / .agents/skills/ci

Read GitHub Actions CI for the current branch or open PR, triage failing checks, reproduce locally, and fix scoped issues until green. Use whenever the user mentions CI failures, red checks, failed pipeline, GitHub Actions, merge blocked, fix the build, babysit CI, gh run failed, ruff/ty errors, failing pytest, example run failed, or asks to check CI on this branch — even if they only paste a log snippet. Also use after implementing a feature when tests, lint, or typecheck might have broken.

FileKindSize
SKILL.mdskill md6.6 KB
evals/evals.jsonconfig1.1 KB
references/gh-commands.mdmarkdown1.3 KB
references/nova-ci.mdmarkdown3.5 KB

references/gh-commands.md

View on GitHub
# GitHub CLI — CI inspection

Requires `gh` authenticated (`gh auth status`). Run from repo root.

## Current branch PR summary

```bash
git branch --show-current
gh pr view --json number,url,headRefName,baseRefName,statusCheckRollup,mergeable,mergeStateStatus
```

`statusCheckRollup` entries:

- `CheckRun`: GitHub Actions (`conclusion`, `name`, `detailsUrl`, `workflowName`)
- `StatusContext`: External statuses (`state`, `context`, `targetUrl`)

## No PR yet

```bash
gh run list --branch "$(git branch --show-current)" --limit 20
```

## Failed job logs

From the run list, copy the run ID:

```bash
gh run view 27340993761 --log-failed
```

Truncated output — pipe to a file for large logs:

```bash
gh run view <id> --log-failed 2>&1 | tail -100
```

## Filter by workflow file

```bash
gh run list --branch feat/my-branch --workflow nova-dev.yaml --limit 5
gh run list --branch feat/my-branch --workflow nova-run-examples.yaml --limit 3
gh run list --branch feat/my-branch --workflow yamllint.yaml --limit 3
gh run list --branch feat/my-branch --workflow uv-audit.yaml --limit 3
```

## Watch after push

```bash
gh run watch
gh run watch <run-id>
```

## Compare with base branch CI

If failures look unrelated to your changes:

```bash
git fetch origin main
git merge origin/main   # or rebase — user preference
```

Then re-run local checks before pushing.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall