docs-that-work

Project documentation guidelines. Use when asked to "write documentation", "create a CLAUDE.md", "write a README", "document this project", "improve documentation", or when creating/updating CLAUDE.md or README.md files.

1.11x

Quality

—

Does it follow best practices?

Impact

97%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

100%

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

The body is an efficient, well-organized guidance skill that adds only non-obvious principles, gives concrete and applicable rules, and cleanly defers detail to two real reference files via a navigation table. It is a strong example of an instruction-only skill that respects the context window.

Dimension	Reasoning	Score
Conciseness	The body is lean and principle-driven, assumes Claude's competence (no basic explanations of what a README is), and uses tight bullets and a table where every section earns its place, matching the score-3 anchor.	3 / 3
Actionability	Provides concrete, applicable directives such as "target <30 lines", explicit belongs/does-not-belong lists, a document-job table, and "Never duplicate between them"; for an instruction-only skill this concrete guidance meets the score-3 bar.	3 / 3
Workflow Clarity	The skill applies a clear decision process (discoverability rule -> CLAUDE.md rules -> README rules -> when docs ARE needed) with no destructive batch operations requiring validation checkpoints; per the simple-skill scoring note, clear organization merits a 3.	3 / 3
Progressive Disclosure	References two real, one-level-deep files (references/anti-patterns.md and references/claude-md-guide.md, both verified to exist) with a final Deep Dives navigation table, matching the score-3 well-signaled one-level-deep anchor.	3 / 3
	Total	12 / 12 Passed

Description

90%

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 concise, uses third-person/imperative voice, and clearly covers both capability and explicit use-when triggers with natural phrasing. Its only weakness is a somewhat narrow action set concentrated on CLAUDE.md and README rather than a broader documentation toolkit.

Dimension	Reasoning	Score
Specificity	Names the documentation domain and concrete actions like "create a CLAUDE.md" and "write a README", but focuses narrowly on CLAUDE.md/README rather than listing multiple distinct capabilities, so it stops short of the comprehensive score-3 anchor.	2 / 3
Completeness	Explicitly states both what it does ("Project documentation guidelines") and when to use it ("Use when asked to... or when creating/updating CLAUDE.md or README.md files"), matching the score-3 what-AND-when anchor.	3 / 3
Trigger Term Quality	Includes several natural phrases a user would say ("write documentation", "write a README", "document this project", "improve documentation") with good coverage of common variations, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (CLAUDE.md/README documentation) with distinct, specific triggers that are unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	11 / 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: provectus/awos-recruitment
Commit: 4596913

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.