github-actions-authorlisted
Install: claude install-skill mthines/agent-skills
# GitHub Actions Author
Generate or audit GitHub Actions workflow YAML against 2026 best
practices for speed, cost, reusability, and security.
> **This `SKILL.md` is a thin index.** Detailed rules live in
> [`rules/*.md`](./rules/) and load on demand. Drop-in starters live in
> [`templates/*.md`](./templates/). The decision tree for picking a
> shape lives in [`references/decision-tree.md`](./references/decision-tree.md).
---
## Non-negotiable โ every step's output reaches the run log
This applies to **both modes** and outranks every other preference in this skill.
Every command in every scaffolded or reviewed workflow must write its stdout **and** stderr to the job log.
Output that lands only in a file, only in an artifact, only in `$GITHUB_STEP_SUMMARY`, or in `/dev/null` is invisible to `gh run view <run-id> --log-failed` โ the only surface `/ci-auto-fix`, `/test-auto-fix`, `/implement-suggestion`, and an on-call human read a failure from.
A failing step that printed nothing cannot be diagnosed or fixed by an agent; it can only be escalated.
Minimum bar for every `run:` block:
```yaml
- name: Run unit tests
shell: bash
run: |
set -euo pipefail
npm test 2>&1 | tee test-output.log # tee, never `> file`
```
Forbidden outright: `> /dev/null`, `2>/dev/null`, `cmd > out.txt 2>&1`, `--silent`, `--quiet`, `-q`, a machine-only reporter with no human output, and `|| true` without echoing the captured output and exit code.
`tee` requires `set -o pipefail`, o