Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 skill description that clearly communicates what the skill does (write contextual commits with structured action lines following Conventional Commits), when to use it (committing code, finishing tasks), and what makes it distinctive (preserving WHY over WHAT). It uses third person voice correctly and includes natural trigger terms. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Write contextual commits', 'capture intent, decisions, and constraints', 'Extends Conventional Commits with structured action lines', 'preserve WHY code was written'. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Write contextual commits that capture intent, decisions, and constraints alongside code changes') and when ('Use when committing code, finishing a task, or when the user asks to commit') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'committing code', 'commit', 'finishing a task', 'Conventional Commits', 'commit body'. These cover common variations of how users would request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — focuses specifically on contextual/conventional commits with structured action lines preserving intent. The emphasis on WHY-focused commit messages with a specific methodology (Conventional Commits + structured action lines) creates a clear niche unlikely to conflict with general git or coding 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.
This is a strong, highly actionable skill that provides clear commit message formats with excellent real-world examples covering multiple complexity levels. Its main weakness is verbosity — some sections explain things Claude doesn't need explained (the problem statement, git workflow preservation), and the action type catalog with 'When to use' guidance could be more compact or split into a reference file. The workflow for determining commit scope is well-sequenced with good guardrails against fabricating context.
Suggestions
Remove or drastically shorten the 'Problem You Solve' and 'Git Workflows' sections — Claude doesn't need motivation or reassurance that commit bodies survive merges.
Consider moving the detailed action type definitions (with all 'When to use' subsections and multiple examples per type) into a separate REFERENCE.md, keeping only a compact summary table in the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-written but somewhat verbose. The 'Problem You Solve' section explains concepts Claude can infer. The action type definitions include 'When to use' subsections that add bulk. The Git Workflows section stating 'no special handling needed' could be omitted entirely. However, the examples and rules sections are appropriately dense. | 2 / 3 |
Actionability | Highly actionable with concrete, copy-paste-ready commit message formats, multiple realistic examples covering simple to complex scenarios, and a clear pre-commit checklist (check staged changes, identify context). The action type definitions include specific real-world examples that serve as templates. | 3 / 3 |
Workflow Clarity | The 'Before You Write the Commit' section provides a clear sequenced workflow: check staged changes → identify session context → identify gaps → write action lines accordingly. The branching logic (staged vs. unstaged) is explicit, and the 'When You Lack Conversation Context' section serves as a validation checkpoint preventing fabricated context. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a monolithic document (~200 lines) with no references to external files. The action type definitions and extensive examples could be split into separate reference files, with the main skill containing a quick-start overview and links. | 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.
8196cab
Table of Contents
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.