documentation

In-code documentation, folder READMEs, code comments. Use when: "document this", "add JSDoc", "write a README", "explain this code", or writing README.md/JSDoc.

Quality

89%

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

Quality

Content

96%Weight 40%Scale 1-5

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

An exemplary instruction-only skill body: every section is a tight set of principles backed by contrastive good/bad examples that show exactly what to produce. The only structural nit is that at its current length the JSDoc and comment example galleries could be split into a reference file, though nothing is poorly placed or buried.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence: 'Documentation explains why, not what', 'Exhaustive file listings that just duplicate `ls`', 'Delete commented-out code; that's what git is for'. Every good/bad example pair earns its place by demonstrating the standard, with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Concrete, near-copy-paste guidance throughout: a full README example with ASCII art, a complete JSDoc block with a realistic @example, a real 'why' comment about Y.Doc clientIDs, each paired with a bad counterexample and explicit rules. As an instruction-only skill its guidance is fully concrete, which the rubric's code-vs-instruction note says is not penalized for lacking runnable code.	5 / 5
Workflow Clarity	A simple single-purpose standards skill with no multi-step process and no destructive or batch operations, so the simple-skill exception applies: each documentation type (folder README, JSDoc, code comment) has unambiguous rules, good/bad contrasts, and a clear 'primary job' statement. No validation cap applies.	5 / 5
Progressive Disclosure	Well-organized sections with clear headers and one clean one-level external reference ('Follow [writing-voice](../writing-voice/SKILL.md))'). At ~117 lines it exceeds the 'under 50 lines' threshold for an automatic 5, and the JSDoc and code-comment example blocks could arguably live in a reference file — minor organization gaps rather than inlined content that clearly belongs elsewhere, which keeps it above anchor 3.	4 / 5
	Total	19 / 20 Passed

Description

78%Weight 40%Scale 1-5

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

A strong description with an explicit and well-phrased 'Use when' clause containing natural trigger terms and file-format keywords. The main weakness is the absence of action verbs — it enumerates deliverable types rather than what the skill does with them, which limits specificity and leaves its scope slightly implicit.

Suggestions

Add action verbs to the 'what' clause, e.g. 'Write and review in-code documentation, folder READMEs, and code comments' so capabilities are stated as actions rather than artifact types.

Add one or two common trigger variations such as 'add comments' or 'document the API' to widen natural keyword coverage.

Consider qualifying 'explain this code' (e.g. 'explain this code for documentation') to reduce overlap with general code-comprehension requests.

Dimension	Reasoning	Score
Specificity	Names the domain plus three concrete deliverable types ('In-code documentation, folder READMEs, code comments') but contains no action verbs, so it does not list 'specific actions' as anchor 4 requires. It is far more concrete than the anchor-2/3 generic examples, landing on the 'names domain and specifics but not comprehensive actions' fit.	3 / 5
Completeness	Explicitly answers both 'what' (in-code documentation, folder READMEs, code comments) and 'when' via an explicit 'Use when:' clause with multiple concrete quoted trigger phrases, matching the anchor-5 example pattern exactly. The 'when' is explicit and specific, not merely present as in anchor 4.	5 / 5
Trigger Term Quality	Excellent natural user phrases ('document this', 'add JSDoc', 'write a README', 'explain this code') with file-format terms (README.md, JSDoc). A few common variations like 'add comments', 'comment this code', or 'document the API' are missing, so it falls just short of the comprehensive-synonym anchor 5.	4 / 5
Distinctiveness Conflict Risk	Triggers are mostly niche-distinct ('add JSDoc', 'write a README'), but 'explain this code' is broad enough to fire on general code-comprehension requests, creating minor overlap risk with related skills. Not anchor 3, since it does not broadly overlap with many skills; not anchor 5, since one trigger is generic.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/documentation/SKILL.md
Commit: f9441c8

Reviewed: 3 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.