lint
Run shellcheck and actionlint on shell scripts and GitHub Actions workflows. Use before pushing or when fixing lint issues.
91
93%
Does it follow best practices?
Impact
87%
1.14xAverage score across 6 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 a strong, concise description that names specific tools and targets, includes natural trigger terms, and provides explicit 'Use when' guidance. It clearly carves out a distinct niche around shell script and GitHub Actions linting. The only minor improvement could be mentioning file extensions like .sh or .yml/.yaml for additional trigger coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Run shellcheck and actionlint' on specific targets: 'shell scripts and GitHub Actions workflows'. Names the exact tools and file types involved. | 3 / 3 |
Completeness | Clearly answers both what ('Run shellcheck and actionlint on shell scripts and GitHub Actions workflows') and when ('Use before pushing or when fixing lint issues') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'shellcheck', 'actionlint', 'shell scripts', 'GitHub Actions workflows', 'lint issues', 'pushing'. These cover the main ways users would refer to this task. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to naming specific tools (shellcheck, actionlint) and specific file types (shell scripts, GitHub Actions workflows). Unlikely to conflict with other linting or code quality skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides executable commands for linting shell scripts and GitHub Actions workflows. Its main weakness is the lack of an explicit re-validation step after fixing lint issues, which would complete the feedback loop. The $ARGUMENTS placeholder for optional guidance is a nice touch for extensibility.
Suggestions
Add an explicit re-run/re-validate step after fixing issues (e.g., '4. Re-run the linter to confirm all issues are resolved before reporting') to complete the feedback loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It doesn't explain what shellcheck or actionlint are, assumes Claude knows how to use them, and every section serves a clear purpose. No unnecessary padding. | 3 / 3 |
Actionability | Provides fully executable bash commands for both shellcheck and actionlint, including git diff filtering for changed files, file existence checks, and specific output format flags. The disable directive example is concrete and copy-paste ready. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced (find changed files → run linter → fix issues), but there's no explicit validation/feedback loop after fixing issues (e.g., re-run linters to confirm fixes). For a lint-and-fix workflow, a re-validation step would be expected to score 3. | 2 / 3 |
Progressive Disclosure | For a simple, focused skill under 50 lines, the content is well-organized with clear sections (Shell Scripts, GitHub Actions, Handling Issues, Optional Guidance). No need for external file references given the scope. | 3 / 3 |
Total | 11 / 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
- aaddrick/claude-desktop-debian
- Commit
814cd52
- 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.