CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A tight, example-driven conventions skill that avoids explaining concepts Claude already knows and grounds every rule in concrete Good/Bad pairs. Organization is clean with a single one-level external reference, and the absence of risky multi-step operations means no validation checkpoints are required.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it states the 'why not what' principle and immediately grounds it in concrete Good/Bad examples for READMEs, JSDoc, and code comments, with no padded library or format explanations. The minor thematic repetition of 'why not what' across sections is reinforcing a core rule in distinct contexts, so it stays level-3 rather than dropping to the 'could be tightened' level-2 anchor.

3 / 3

Actionability

Each subsection supplies concrete, executable guidance: realistic Good/Bad markdown and TypeScript/JSDoc examples plus explicit Rules lists (e.g., 'Include @example blocks', 'Comment the why when it's not obvious'). It is not a 2 because the examples are complete and copy-pasteable rather than pseudocode or abstract description.

3 / 3

Workflow Clarity

This is a single-purpose conventions skill with no destructive or batch operations requiring validation checkpoints, so per the simple-skill scoring note an unambiguous, well-sequenced structure scores 3. Each section follows a clear Good → Bad → Rules sequence, so it is not a 2 with implicit checkpoints.

3 / 3

Progressive Disclosure

The body is self-contained and well-organized into Folder READMEs, JSDoc Comments, and Code Comments, with a single clearly-signaled one-level reference to a sibling skill (writing-voice). No bundle files exist and there is no nested-reference indirection, matching the level-3 anchor for well-organized skills without deep external references.

3 / 3

Total

12

/

12

Passed

Description

100%

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, concise description that names concrete documentation artifacts, includes an explicit third-person 'Use when' trigger clause with natural user phrasing, and carves out a distinct niche. It satisfies the highest anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions/artifacts — 'In-code documentation, folder READMEs, code comments' — rather than vague language. It is not a 2 because it enumerates several distinct concrete targets instead of naming only a domain and a single action.

3 / 3

Completeness

It explicitly answers both 'what' (in-code documentation, folder READMEs, code comments) and 'when' via an explicit 'Use when' trigger clause. The presence of the explicit trigger guidance satisfies the level-3 anchor and avoids the cap at 2 for a missing 'Use when' clause.

3 / 3

Trigger Term Quality

The 'Use when' clause quotes natural phrases users actually say: 'document this', 'add JSDoc', 'write a README', 'explain this code', 'writing README.md/JSDoc'. Coverage of natural terms is broad, not just jargon, so it exceeds the level-2 'some relevant keywords' anchor.

3 / 3

Distinctiveness Conflict Risk

It occupies a clear niche — writing documentation — with distinct triggers unlikely to fire for unrelated skills. It is not a 2 because the triggers ('add JSDoc', 'write a README', 'document this') are specific enough to avoid meaningful overlap with general code skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
EpicenterHQ/epicenter
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.