commit-with-docs
Summarizes code changes, validates staged diffs, updates documentation (docs/, README, CLAUDE.md, changelog), and creates git commits with aligned docs. Use when completing a feature or fix that requires documentation updates alongside code changes, writing commit messages, or updating changelogs and README files.
93
92%
Does it follow best practices?
Impact
95%
1.97xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
92%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 articulates specific capabilities and provides explicit trigger guidance. It uses proper third-person voice and covers the documentation-commit workflow comprehensively. Minor weakness is potential overlap with standalone commit or documentation skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Summarizes code changes', 'validates staged diffs', 'updates documentation (docs/, README, CLAUDE.md, changelog)', and 'creates git commits with aligned docs'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (summarizes changes, validates diffs, updates docs, creates commits) AND when with explicit 'Use when...' clause covering feature completion, commit messages, and changelog/README updates. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'commit', 'commit messages', 'changelog', 'README', 'documentation updates', 'feature', 'fix'. Good coverage of terms developers naturally use when completing work. | 3 / 3 |
Distinctiveness Conflict Risk | While specific to documentation-aligned commits, there's potential overlap with generic commit message skills or documentation-only skills. The combination of 'docs + commits' is distinctive but 'commit messages' alone could trigger multiple skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
92%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 skill with clear safety constraints, concrete commands, and a logical two-phase workflow. The content is appropriately concise while providing actionable guidance including example scenarios. Minor improvement could be made in progressive disclosure by potentially splitting detection rules or examples into separate files for larger-scale use.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, using bullet points and structured sections without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides concrete, executable git commands throughout (git status --porcelain, git diff --cached, etc.), specific file paths to check, and copy-paste ready commit message formats. The example workflows show exact command sequences. | 3 / 3 |
Workflow Clarity | Clear two-phase workflow with explicit prerequisites, detection rules, and numbered execution steps. Includes validation checkpoints (verify no business code modified) and explicit handling for edge cases (SESSION.md doesn't exist → create template and stop). | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in a single file. The detection rules and example workflows could potentially be split into separate reference files for cleaner navigation, though the current length is manageable. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- tibelf/ai_project_init
- Commit
56f4516
- 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.