fix-github-issue
Fix GitHub issues using gh CLI. Use when asked to fix, resolve, or address a GitHub issue. Creates fixes on separate branches, runs tests locally, and creates PRs when tests pass. Requires gh CLI authenticated and repo cloned locally.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 skill description that clearly communicates the specific workflow (fix issues → branch → test → PR), provides explicit trigger terms ('fix, resolve, or address a GitHub issue'), and includes useful prerequisite information. It is concise, uses third person voice, and would be easily distinguishable from other skills in a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: fix GitHub issues, create fixes on separate branches, run tests locally, create PRs when tests pass. Also mentions prerequisites (gh CLI authenticated, repo cloned locally). | 3 / 3 |
Completeness | Clearly answers both what ('Fix GitHub issues using gh CLI, creates fixes on separate branches, runs tests locally, creates PRs') and when ('Use when asked to fix, resolve, or address a GitHub issue') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'fix', 'resolve', 'address', 'GitHub issue', 'gh CLI', 'PR', 'tests'. These are terms users would naturally use when requesting this workflow. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to a specific workflow: fixing GitHub issues via gh CLI with a branch-test-PR pipeline. The combination of GitHub issues, gh CLI, branching, testing, and PR creation makes this highly distinctive and unlikely to conflict with general coding or git skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A solid, actionable skill with a clear multi-step workflow and good validation checkpoints for both local testing and CI. The main weakness is some unnecessary advice that Claude already knows (code style, reading issues thoroughly) and minor inconsistency in branch naming conventions between the workflow steps and quick reference. The quick reference section adds value but partially duplicates content.
Suggestions
Remove generic advice Claude already knows ('Read the issue thoroughly', 'Make minimal, focused changes', 'Follow existing code style') to improve conciseness.
Fix the branch naming inconsistency: step 2 uses 'fix-<description>' while step 7 and quick reference use 'fix/issue-<number>-<description>' — pick one convention.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary guidance Claude already knows, like 'Read the issue thoroughly', 'Make minimal, focused changes', and 'Follow existing code style and patterns'. The 'Analyze the Codebase' step is vague filler. However, the overall structure is reasonably tight. | 2 / 3 |
Actionability | Provides concrete, executable bash commands throughout the workflow — from viewing issues, creating branches, committing, pushing, creating PRs, and monitoring CI. The commands are copy-paste ready with clear placeholders. | 3 / 3 |
Workflow Clarity | Clear 8-step sequence with explicit validation checkpoints: tests must pass before proceeding (step 5), CI monitoring with failure recovery loop (step 8), and a fix-rerun feedback loop for both local tests and CI. This covers the destructive/batch operation concern well. | 3 / 3 |
Progressive Disclosure | The content is well-structured with numbered steps and a quick reference section, but it's somewhat monolithic. The quick reference at the end partially duplicates the workflow above. For a skill of this length (~80 lines), the organization is adequate but the duplication slightly hurts. No external references are needed but none are offered for edge cases either. | 2 / 3 |
Total | 10 / 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
- freekmurze/dotfiles
- Commit
05d40bb
- 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.