docs
Keep documentation in sync with what the code actually does. Audit drift, generate new docs, update existing pages. Reads the code first, then the docs, then identifies the gap.
56
65%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./deliver/skills/docs/SKILL.mdQuality
Discovery
67%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 description does well at specifying concrete actions and a clear workflow, making it distinctive in its niche of code-documentation synchronization. However, it lacks an explicit 'Use when...' clause which caps completeness, and could benefit from more natural trigger terms that users would actually say when they need this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about outdated documentation, wants to check if docs match the code, or needs to regenerate or refresh documentation.'
Include more natural trigger terms and variations users might say, such as 'outdated docs', 'stale documentation', 'README update', 'API docs', 'docstrings', or 'docs don't match the code'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Audit drift', 'generate new docs', 'update existing pages', and describes the process: 'Reads the code first, then the docs, then identifies the gap.' | 3 / 3 |
Completeness | Clearly answers 'what' (audit drift, generate docs, update pages) and describes the process, but lacks an explicit 'Use when...' clause with trigger guidance. The 'when' is only implied by the nature of the actions described. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'documentation', 'docs', 'code', 'drift', 'sync', but misses common user phrasings like 'outdated docs', 'README', 'API docs', 'docstring', or file extensions. Users might say 'my docs are out of date' which partially maps to 'drift' but isn't a natural match. | 2 / 3 |
Distinctiveness Conflict Risk | The specific niche of keeping documentation in sync with code, auditing drift, and the described workflow (code → docs → gap) is quite distinctive and unlikely to conflict with general documentation or code generation skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%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-structured instructional skill with a clear three-part workflow and good coverage of edge cases, transitions, and failure modes. Its main weakness is the lack of concrete, executable examples — no sample audit output, no before/after doc correction, no template. It's also somewhat verbose for what could be a more concise set of instructions, though the verbosity is mostly purposeful rather than padded.
Suggestions
Add a concrete example of an audit report output (e.g., a short structured markdown showing a page with drift, specifics of the mismatch, and the recommended fix).
Include a before/after example of a doc update — showing a drifted doc snippet alongside the corrected version matched to actual code.
Trim the doc-type structure list in the Generate section (API reference, How-to, Concept, Tutorial patterns) — Claude already knows these formats; a one-line reminder suffices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-written but includes some sections that over-explain concepts Claude would already understand (e.g., the doc type structures like 'API reference: name, signature, parameters...' and 'How-to: scenario, prerequisites, steps'). The 'What Docs Does NOT Do' and 'Failure Modes' sections, while useful, add significant length. Some tightening is possible. | 2 / 3 |
Actionability | The skill provides structured guidance (the three moves: audit, generate, update) with clear checklists, but lacks concrete executable examples — no code snippets, no sample audit report format, no example of a drift finding or a corrected doc page. It describes what to do conceptually rather than showing exactly how to do it. | 2 / 3 |
Workflow Clarity | The three-move workflow (Audit → Generate → Update) is clearly sequenced with explicit sub-steps. The audit has a structured checklist (Names, Shapes, Behavior, Coverage, Links) with a defined output format. The update move includes validation logic ('match the code,' 'update neighbors'). Transitions to other skills serve as decision checkpoints for edge cases like bugs vs. drift. | 3 / 3 |
Progressive Disclosure | The skill references external files (foundation/SKILL.md, foundation/model.md, foundation/guidelines.md, agents/tech-writer.md) which is good, but no bundle files are provided to verify these exist. The content itself is somewhat monolithic — the failure modes and transitions sections could potentially be split out. The cross-references are one-level deep and clearly signaled, which is positive. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- audenaert/etak
- Commit
632c389
- 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.