CtrlK
BlogDocsLog inGet started
Tessl Logo

docs

ALWAYS use this when writing docs

44

Quality

45%

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

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/docs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The body is a compact, specific set of house-style rules that respects the token budget and points to a concrete example file, which is its main strength. Its weaknesses are the complete absence of section organization and any example of the target format inline, so the reader must open the referenced .mdx file to see what the rules produce.

Suggestions

Group the flat rule list into short sections (e.g. "## Page structure", "## Section titles", "## Code snippets", "## Commits") so rules are scannable and navigable.

Inline one short before/after example of a page title, description, and a section with the 3-dash divider so the target format is visible without opening the referenced file.

Add a brief ordering cue such as "Read the example .mdx first, then draft the page, then check the draft against these rules" to give the single task an explicit validation step.

DimensionReasoningScore

Conciseness

The body is a lean rule list with no explanation of concepts Claude already knows and concrete numeric constraints ("5-10 words long", "2-3 word phrase", "divider of 3 dashes"), matching "Efficient; minor instances of over-explanation that could be trimmed". Small redundancies — "You are not verbose" duplicates the 2-sentence chunk rule, and "This might be unavoidable in some cases, but try to avoid it" is hedging filler — keep it below the "every token earns its place" anchor.

4 / 5

Actionability

Guidance is mostly executable for an instruction-only skill: specific rules (title length, description constraints, divider format, "remove trailing semicolons") plus a concrete example file ("Check out the /packages/web/src/content/docs/docs/index.mdx as an example"). It falls short of 5 because no inline example of a correctly formatted section or snippet is given, leaving minor gaps the example file must fill.

4 / 5

Workflow Clarity

This is a simple single-task skill (write a docs page to house style), and the action is largely unambiguous, so the simple-skill exception applies; however no ordering or verification is given (e.g. read the example file first, then verify the draft against the rules), matching "Clear sequence with most checkpoints present; minor validation gaps" rather than a fully unambiguous single action.

4 / 5

Progressive Disclosure

The body is short (under 50 lines) so inline placement of the rules is appropriate, and the single reference to the example .mdx file is one level deep and clearly signaled. But there are no section headers at all — tone, page metadata, section formatting, code style, and commit conventions sit in one unstructured list — matching "Some structure but could be better organized" rather than 4, which requires good structure throughout.

3 / 5

Total

15

/

20

Passed

Description

20%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.

The description is a bare trigger statement with no capability information. It tells Claude when to fire but not what it will find, and its vague, over-claiming "ALWAYS" phrasing creates conflict risk with any documentation-related skill.

Suggestions

State the concrete capabilities in the description, e.g. "Write MDX documentation pages for this repo following its house style (short sections, 3-dash dividers, imperative titles, semicolon-free snippets)."

Replace the imperative over-claim "ALWAYS use this" with a specific trigger clause naming what kind of docs (e.g. "Use when creating or editing pages under packages/web/src/content/docs/").

Include natural trigger terms users would actually say — "documentation", "doc page", "MDX", "user guide" — so the skill is discoverable and distinguishable from generic writing skills.

DimensionReasoningScore

Specificity

"ALWAYS use this when writing docs" names no concrete actions or capabilities whatsoever — it is pure abstract language comparable to "Helps with documents". It does not even reach the level of naming minimal generic actions like "Processes PDF files".

1 / 5

Completeness

A 'when' is present ("when writing docs") but there is no 'what' — the description never states what the skill does, exactly matching the anchor example "Use when working with documents". It cannot score 3 because that anchor requires a clear 'what'; it cannot score 1 because an explicit trigger condition is stated.

2 / 5

Trigger Term Quality

The only keyword is "docs" (plus "writing"), a single generic term missing the natural phrases users say such as "documentation", "doc pages", "user guide", "MDX", or "readme". This matches the anchor "one or two generic keywords; missing the natural phrases users say" rather than 3, which requires a relevant domain keyword with only some variations missing.

2 / 5

Distinctiveness Conflict Risk

"docs" is very broad and the "ALWAYS" directive makes it claim every documentation-writing task, creating high overlap risk with many similar skills (API docs, READMEs, user guides), matching "Very broad; high overlap risk with many similar skills". It edges above 1 only because it is confined to docs rather than being entirely generic across domains.

2 / 5

Total

7

/

20

Passed

Validation

100%

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
revokslab/ShipFree
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.