write
Write a documentation fix on a branch. Makes the minimal change, formats, self-reviews, and commits. Use after research has identified what to change. "write the fix", "make the changes", "implement the fix for #1234".
93
92%
Does it follow best practices?
Impact
93%
2.26xAverage 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 description that clearly communicates what the skill does (write documentation fixes with formatting, self-review, and commits) and when to use it (after research identifies what to change). The trigger phrases are natural and realistic. The main weakness is that some trigger terms like 'make the changes' are generic enough to potentially conflict with non-documentation fix skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: writes a documentation fix on a branch, makes minimal changes, formats, self-reviews, and commits. These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers both what (writes documentation fix on a branch with minimal change, formatting, self-review, and commit) and when ('Use after research has identified what to change') with explicit trigger examples. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'write the fix', 'make the changes', 'implement the fix for #1234'. These are realistic user utterances that would help Claude match this skill. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies 'documentation fix' and 'on a branch', phrases like 'write the fix' and 'make the changes' are fairly generic and could overlap with code fix skills or other implementation skills. The documentation focus helps but isn't strongly emphasized in the triggers. | 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, highly actionable skill with a clear sequential workflow, explicit validation steps, and lean prose. It assumes Claude's competence appropriately and provides concrete, executable commands at every step. The only minor weakness is that referenced files (CLAUDE.md, STYLE.md, COMPONENTS.md, lint script) are not available in the bundle, making it harder to fully assess progressive disclosure, though the references themselves are clearly signaled.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what git, linting, or front matter are. Instructions assume Claude's competence throughout and each token contributes actionable value. | 3 / 3 |
Actionability | Provides executable bash commands for branching, linting, staging, and committing. The commit message template is copy-paste ready with a complete heredoc structure. Concrete guidance on front matter fields, file restrictions, and rename detection. | 3 / 3 |
Workflow Clarity | Clear 6-step numbered sequence with explicit validation checkpoints: lint after edits (step 4), self-review with git diff verification (step 5), and a staging verification before commit (step 6). The feedback loop of fix-then-re-validate is present in step 4. | 3 / 3 |
Progressive Disclosure | References CLAUDE.md, STYLE.md, and COMPONENTS.md for writing guidelines, and a lint script, but these are not provided in the bundle. The content is well-structured with clear sections, but the skill is somewhat monolithic for its length — the commit message template and notes could potentially be separated. Still, for a skill of this size, the organization is reasonable. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- docker/docs
- Commit
c0aa985
- 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.