gen-docs

Update Kimi Code CLI user documentation after meaningful code changes that affect product behavior or user experience.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/gen-docs/SKILL.md

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, actionable instruction skill: lean prose, concrete commands, and clean delegation to sibling skills and the style guide. The only gap is the absence of a final validation/verification step for the batch bilingual update.

Suggestions

Add an explicit final verification step in the workflow, e.g. confirm both locales are in sync and that all affected pages were updated before completing.

Optionally include a quick check that the VitePress build still passes after doc edits to catch broken links or frontmatter.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: uses git commands without explaining them and assumes Claude's competence; the repo-specific doc structure and changelog-flow rules earn their place as non-obvious context.	3 / 3
Actionability	Provides fully concrete, executable guidance — exact git commands, a runnable sync script, specific file paths, named doc sections, and neutral placeholder examples.	3 / 3
Workflow Clarity	A clear 5-step sequence with decision gates ('say so and stop', prerequisites stop) exists, but there is no final verification step for this batch operation (multi-page, two-locale updates), which caps the score at 2.	2 / 3
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled references (docs/AGENTS.md, translate-docs and audit-docs skills) and no nested pointer chains; detail is appropriately delegated.	3 / 3
	Total	11 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is clear and domain-specific but uniformly mid-tier: it states one concrete action and a conditional trigger without an explicit 'Use when...' clause or natural keyword variations, leaving every dimension at 2.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when code changes affect product behavior or user experience and docs need updating.'

List multiple concrete actions (e.g. 'update guides, config reference, and release notes') to raise specificity beyond a single verb.

Include natural keyword variations users would say ('docs', 'documentation', 'release notes') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('Update...user documentation') and a clear domain, but offers only one action verb rather than multiple specific actions like 'extract, fill, merge'.	2 / 3
Completeness	Answers 'what' (update user docs) and gives a 'when' condition ('after meaningful code changes'), but has no explicit 'Use when...' clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant keywords ('documentation', 'code changes') but lacks natural variations ('docs') and an explicit 'Use when...' phrasing a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	Scoped to post-change doc updates with a clear niche, but 'documentation' is broad and risks overlap with sibling doc skills (audit-docs, translate-docs).	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MoonshotAI/kimi-code
Path: .agents/skills/gen-docs/SKILL.md
Commit: 77618e3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.