Set up or align a GitHub Actions deploy pipeline for an app or service. Use when standardizing repos around the verify-then-deploy shape: push to main → detect affected lanes → verify and build artifacts → e2e → deploy each lane to its host (Cloudflare Pages, AWS Amplify, GHCR + VPS).
99
100%
Does it follow best practices?
Impact
97%
1.21xAverage score across 4 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that is highly specific, includes rich trigger terms, clearly delineates both what and when, and explicitly distinguishes itself from a related skill (`gh-release-pipeline`). The negative scoping ('not publishing artifacts to a registry') is particularly effective for disambiguation. The description is information-dense without being padded.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and architectural details: 'set up or align a GitHub Actions deploy pipeline', 'push to main → detect affected lanes → verify and build artifacts → e2e → deploy each lane', and names specific hosts like Cloudflare Pages, AWS Amplify, GHCR + VPS. Very concrete. | 3 / 3 |
Completeness | Clearly answers both 'what' (set up/align a GitHub Actions deploy pipeline with the verify-then-deploy shape) and 'when' ('Use when standardizing repos around the verify-then-deploy shape'). Also includes explicit negative scoping ('use for deploying running apps, not publishing artifacts to a registry') and pairs guidance with `gh-release-pipeline`. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'GitHub Actions', 'deploy pipeline', 'Cloudflare Pages', 'AWS Amplify', 'GHCR', 'VPS', 'e2e', 'concurrency group', 'push to main'. These cover a wide range of terms a user working on CI/CD deployment would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically about deploy pipelines (not release/publish pipelines), explicitly differentiates from `gh-release-pipeline`, and describes a specific architectural pattern (verify-then-deploy with per-lane concurrency). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that efficiently communicates a complex multi-stage deploy pipeline pattern. It respects Claude's intelligence by focusing on the non-obvious decisions (concurrency grouping, artifact reuse, lane independence) while providing concrete YAML and tool references. The progressive disclosure to reference files is well-structured, and the workflow includes proper validation checkpoints including smoke tests and end-to-end verification.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No explanation of what GitHub Actions is, no padding about CI/CD concepts. The ASCII pipeline diagram is dense and informative. The guardrails section is tight and non-obvious. Claude doesn't need to be told what a concurrency group is, but the specific non-cancellable per-(env, lane) pattern is genuinely novel guidance. | 3 / 3 |
Actionability | Provides concrete YAML snippets, specific action names (dorny/paths-filter@v4, actions/download-artifact@v8), exact file paths (.github/workflows/main.yml), and a clear executable example with the deploy-web job. The workflow steps are specific enough to act on immediately — naming tools, secret strategies, and concurrency group patterns. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with explicit validation at step 9 (end-to-end validation with a specific sequence to observe), smoke checks at step 8, and a troubleshooting cross-check at step 10. The feedback loop is present: deploy is not green until smoke passes. The guardrails reinforce the 'never rebuild inside deploy' constraint, preventing a common failure mode. | 3 / 3 |
Progressive Disclosure | The main skill is a clear overview with well-signaled one-level-deep references: references/targets.md for host-specific details, references/workflows.md for detailed snippets, references/secrets.md for env loading, and references/troubleshooting.md for debugging. The instruction to load references only when needed ('only after the target lanes and host are known') is excellent progressive disclosure guidance. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents