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

75%

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/documentation/SKILL.md

Quality

Content

75%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.

A tight, well-organized principles skill with concrete Good/Bad examples and explicit rules per documentation type. Minor redundancy and illustrative-rather-than-executable examples keep it just short of top marks.

Suggestions

Consolidate the repeated 'explain why, not what' framing into the opening so each section can assume it rather than restating it.

Make at least one Good example fully copy-paste-ready (e.g., a complete JSDoc block a user could drop in) to push actionability higher.

Consider extracting the per-section Rules into a single quick-reference checklist at the end for easier scanning.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence, but the 'explain why, not what' principle is restated across the Folder READMEs, JSDoc, and Code Comments sections, which could be consolidated.	4 / 5
Actionability	Concrete Good/Bad examples and explicit Rules lists ('Include @example blocks', 'Comment the why', 'Delete commented-out code') give actionable guidance, though examples are illustrative rather than copy-paste-ready.	4 / 5
Workflow Clarity	Three clearly delineated sub-tasks (Folder READMEs, JSDoc, Code Comments) each with Good/Bad/Rules make the guidance unambiguous; no validation loop is needed for this non-destructive, principles-based skill.	4 / 5
Progressive Disclosure	Well-organized into clear sections with one clearly-signaled, one-level-deep reference to ../writing-voice/SKILL.md; all content is appropriately inline for a principles skill with no bundle files to split out.	4 / 5
	Total	16 / 20 Passed

Description

75%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 well-structured description with explicit 'what' and 'when' guidance and natural trigger phrases. Its main weakness is moderate breadth that risks overlap with adjacent writing/explanation skills.

Suggestions

Tighten the 'what' clause with concrete verbs (e.g., 'Write and review in-code documentation, folder READMEs, and code comments') to lift specificity.

Narrow broad triggers like 'explain this code' to reduce overlap with general explanation/writing skills, or explicitly distinguish from writing-voice.

Add a couple of common synonyms (e.g., 'docstring', 'TSDoc') to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the documentation domain and three concrete artifact types ('In-code documentation, folder READMEs, code comments'), but these are categories rather than concrete actions like 'extract' or 'merge', leaving coverage incomplete.	3 / 5
Completeness	Explicitly answers both 'what' (the three documentation types) and 'when' via a 'Use when:' clause with concrete quoted trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users actually say ('document this', 'add JSDoc', 'write a README', 'explain this code') plus format mentions (README.md/JSDoc), though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	JSDoc and README triggers are fairly distinct, but 'explain this code' and 'document this' are broad and overlap with adjacent skills like the referenced writing-voice skill.	3 / 5
	Total	15 / 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: abe10f3

Reviewed: 5 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.