CtrlK
BlogDocsLog inGet started
Tessl Logo

docs

ALWAYS use this when writing docs

46

Quality

48%

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 delivers tight, specific style directives that assume Claude's competence and are mostly actionable, but it is a flat unstructured list that violates its own sectioning guidance and leans on an external example path not present in the bundle.

Suggestions

Reorganize the rules under short imperative section titles separated by 3-dash dividers, practicing what the skill preaches.

Inline a small before/after example block so the rules are concrete without relying on the un-bundled /packages/web path.

Either move the example into ./references/ and link it relatively, or remove the external path reference.

DimensionReasoningScore

Conciseness

The body is a lean set of one-line directives with almost no padding and assumes Claude's competence; only minor caveats ("This might be unavoidable in some cases, but try to avoid it.") could be trimmed, fitting the efficient-but-slightly-trimmable anchor.

4 / 5

Actionability

Rules are concrete with measurable parameters ("5-10 words long", "divider of 3 dashes", "not more than 2 sentences", "prefix... with docs:"), giving mostly executable guidance; the only gap is no inline example illustrating the rules and the referenced example file is not in the bundle.

4 / 5

Workflow Clarity

This is a simple single-purpose skill whose single action (apply these style rules when writing docs) is unambiguous, but the rules are presented as a flat unstructured list rather than organized sections, a minor gap below the clean 5.

4 / 5

Progressive Disclosure

The body is under 50 lines and needs no separate files, but it has zero section headers or structure (not even following its own divider/title rules) and its one reference points to a non-bundle path (/packages/web/.../index.mdx) that cannot be resolved, matching "some structure but could be better organized; references present but not clearly signaled."

3 / 5

Total

15

/

20

Passed

Description

25%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 terse trigger-only sentence that tells Claude when to fire but not what the skill actually does, leaving it vague and overlapping with other doc skills. It needs a concrete capability clause to rise above the baseline.

Suggestions

Add a "what" clause listing concrete actions, e.g. "Drafts and styles technical documentation pages following house style rules. ALWAYS use this when writing or editing docs."

Include natural synonyms and file types users say (documentation, README, .mdx, guides) to improve trigger coverage.

Tighten the trigger to reduce overlap, e.g. "Use when writing docs for the /packages/web content tree."

DimensionReasoningScore

Specificity

"ALWAYS use this when writing docs" names the domain (docs) and a single generic action (writing) but lists no concrete capabilities, matching the "names the domain but actions are minimal or generic" anchor.

2 / 5

Completeness

The description gives a "when" ("when writing docs") but no explicit "what" — structurally identical to the score-2 example "Use when working with documents."

2 / 5

Trigger Term Quality

Only one generic keyword ("docs") is present with no synonyms or variations (documentation, README, .mdx), fitting "one or two generic keywords; missing the natural phrases users say."

2 / 5

Distinctiveness Conflict Risk

"writing docs" is very broad and would overlap with many documentation-related skills, matching "very broad; high overlap risk with many similar skills."

2 / 5

Total

8

/

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.

Validation16 / 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.