simplify-and-harden-ci
CI-only Simplify & Harden workflow for pull requests using gh-aw (GitHub Agentic Workflows). Runs headless scan-and-report checks for simplify/harden/document, posts structured findings, and can block merges on critical or advisory classes. Use when: you want automated quality/security review in CI without interactive approvals.
61
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/simplify-and-harden-ci/SKILL.mdQuality
Discovery
85%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 a strong description that clearly communicates what the skill does and when to use it, with a well-defined niche around CI-based quality/security review using gh-aw. Its main weakness is that some trigger terms are overly technical ('advisory classes', 'headless scan-and-report') and it could benefit from including more natural language variations that users might employ when seeking this functionality.
Suggestions
Add more natural trigger terms users might say, such as 'PR checks', 'automated code review', 'GitHub Actions', 'CI pipeline', or 'merge gate'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'runs headless scan-and-report checks for simplify/harden/document', 'posts structured findings', 'can block merges on critical or advisory classes'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (CI workflow for scan-and-report checks, posting findings, blocking merges) and 'when' with an explicit 'Use when:' clause specifying 'automated quality/security review in CI without interactive approvals'. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'CI', 'pull requests', 'quality/security review', 'block merges', and 'gh-aw', but relies on specialized jargon ('headless scan-and-report', 'advisory classes') and misses common natural terms users might say like 'PR checks', 'code review automation', 'GitHub Actions', or 'pipeline'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: CI-only workflow specifically for 'gh-aw' (GitHub Agentic Workflows) with simplify/harden/document checks. The combination of CI-only, headless, and the specific tool name makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured CI skill that clearly defines its scope and contract, with good progressive disclosure and concrete commands for setup and authoring. Its main weaknesses are the absence of the actual workflow template inline (or at least a minimal working example), some redundancy between the CI Contract and Prompt Template sections, and missing error recovery guidance in the authoring workflow.
Suggestions
Include a minimal but complete workflow example inline (even if abbreviated) rather than solely deferring to 'references/workflow-example.md', so the skill is actionable without external files.
Add explicit error recovery steps to the authoring workflow (e.g., 'If compile --validate fails: review error output, fix the .md workflow file, re-run validation').
Remove or condense the 'Context Limitation' section—Claude understands CI agent constraints; a single sentence ('CI mode is scan/report only; do not auto-apply changes') suffices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., the 'Context Limitation' section explaining what CI agents can and cannot do is somewhat obvious for Claude). The 'Purpose' bullet points are concise, but some sections like 'CI Contract' restate what's already implied by the prompt template. | 2 / 3 |
Actionability | Provides concrete install commands, YAML setup snippets, and a detailed prompt template, but the actual workflow file is deferred to a reference file ('references/workflow-example.md') that isn't included. The compile/validate/run commands are specific and executable, but the core CI workflow definition—the most critical artifact—is absent from the skill body. | 2 / 3 |
Workflow Clarity | The authoring workflow (steps 1-4) is clearly sequenced with a validate step ('gh aw compile --validate --strict'), but there's no explicit error recovery or feedback loop if validation fails. The overall CI execution flow (scan → report → gate) is described conceptually but not as a step-by-step sequence with checkpoints. | 2 / 3 |
Progressive Disclosure | Good structure with clear sections, appropriate use of a reference file for the workflow template example, and a pointer to the interactive 'simplify-and-harden' skill for local use. Content is well-organized with logical section ordering and no deeply nested references. | 3 / 3 |
Total | 9 / 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.
- Repository
- pskoett/pskoett-ai-skills
- Commit
fe0da1c
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.