agentleFS
y-miyazakiy-miyazaki/config/.agents/skills/github-actions-review/SKILL.md

github-actions-review

Skill1 starsChanged 9 days agoApache-2.0View on GitHub

Review GitHub Actions workflows for correctness, security, and maintainability. Use when reviewing GitHub Actions workflow PRs, checking workflow security, evaluating CI/CD pipeline design, or assessing permissions and secret handling.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not modify workflow files or approve/merge PRs

    line 27
  2. Very specific:

    Read PR context and workflow intent.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Input

  • Workflow YAML and/or composite action YAML (action.yml) and PR context or file diffs (required)
  • Validation output from the companion github-actions-validation report or CI (optional): used to skip tool-detectable checks

Output Specification

Return structured Markdown in accordance with references/common-output-format.md. That file is the source of truth for the output contract.

Each issue must include file path with line reference (<path>#L<line>), risk summary, and remediation guidance.

Execution Scope

  • Systematically apply review checklist from references/common-checklist.md
  • Do not modify workflow files or approve/merge PRs

USE FOR:

  • review workflow security and correctness with human judgment
  • assess trigger design, permissions, and secrets handling
  • review multi-workflow PRs for policy and maintainability risks

DO NOT USE FOR:

  • execute syntax/security validators (actionlint, ghalint, zizmor)
  • auto-fix workflow YAML files
  • replace deterministic workflow validation checks

Reference Files Guide

  • common-checklist.md (always read)
  • common-output-format.md (always read)
  • category-global.md (always read)
  • category-ordering.md (always read)
  • category-security.md (always read)
  • category-best-practices.md (always read)
  • category-error-handling.md (always read)
  • category-performance.md (always read)
  • category-tool-integration.md (always read)
  • category-anti-patterns.md (always read)
  • common-troubleshooting.md (read on failure)

Workflow

  1. Read PR context and workflow intent; extract events, permissions, secret usage, and external action references. If PR context is unavailable, review file diffs only and defer PR-context-dependent checks.
  2. Scope findings to changed files and hunks. Report violations in unchanged code outside the diff only under ## Expert Assessment, not ## Issues. For ad-hoc file review without a diff, treat the whole file as in scope.
  3. Exclude generated files and vendored third-party code (for example workflow files produced by a generator) from primary findings unless they introduce security-critical risk.
  4. For very large PRs (>50 changed workflow or action files), prioritize security/correctness checks first and defer low-risk style checks if evidence is insufficient.
  5. When validation output (companion github-actions-validation report or equivalent CI results) is supplied, do not re-report failures those tools detect: take the overlapping ItemID's status from the tool result, cite the tool, and spend the review on judgment checks. Category items with a validation Note: name the known overlaps.
  6. Apply the full review checklist and collect failed/deferred items.
  7. Output report with the required sections per references/common-output-format.md. Prioritize SEC-* findings first, then correctness, then maintainability.

Error Handling

ConditionSeverityAction
common-checklist.md unavailableFatalStop, report missing dependency
common-output-format.md unavailableRecoverableNote missing file; emit ## Checks Summary, ## Checks (Failed/Deferred Only), and ## Issues only
PR contains no workflow YAML filesRecoverableReport "no reviewable workflows" and stop

Examples

  • Prompt: Review workflow PR and report failed/deferred checks
  • Result: Structured report per references/common-output-format.md; each issue includes path, line, and remediation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.