CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-guidelines

Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

65

Quality

78%

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 ./skills/writing-guidelines/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 well structured with excellent progressive disclosure — a lean overview deferring all rule detail to a real one-level-deep reference file. The main weakness is redundancy: the workflow is stated twice in near-identical form and the pinned-default point is repeated three times, costing token efficiency without adding clarity.

Suggestions

Merge 'How It Works' and 'Usage' into a single workflow section; they currently repeat the same five steps nearly verbatim.

State the pinned-vs-upstream distinction once; it currently appears in 'How It Works', 'Guidelines Source', and again in 'Usage'.

Add a one-line example of the expected output (e.g., 'docs/getting-started.mdx:42: title is feature-shaped, not user-shaped') to make the findings format concrete.

DimensionReasoningScore

Conciseness

'How It Works' and 'Usage' repeat the same five steps nearly verbatim (load guidelines, optionally fetch upstream, read files, apply rules, output findings), and the pinned-is-default point is stated three times across sections. This is more than 'minor instances of over-explanation' (the 4 anchor), but the body is not padded with concepts Claude already knows either, placing it at the 'could be tightened' 3 anchor.

3 / 5

Actionability

Concrete guidance throughout: the exact reference file to load (references/guidelines.md), the exact upstream URL, a defined output format ('terse file:line format'), and a fallback when no files are given. Not 5 because 'Check against all rules in the guidelines' delegates without a concrete example finding, leaving a minor gap.

4 / 5

Workflow Clarity

A clear numbered sequence with an explicit fallback checkpoint ('If no files specified, ask the user'), and this read-only review task is not destructive/batch, so no validation cap applies. Not 5 because there is no error-recovery guidance (e.g., what to do if the optional upstream fetch fails or the diff diverges), which the top anchor expects.

4 / 5

Progressive Disclosure

A short, well-sectioned overview body with a clearly signaled, one-level-deep link to a real, substantive bundle file (references/guidelines.md, 14KB of rules). Content is appropriately split: the overview stays lean while all rule detail lives in the reference, exactly matching the top anchor; nothing is buried or nested further.

5 / 5

Total

16

/

20

Passed

Description

86%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 what and when, third-person voice, and comprehensive natural trigger phrases including synonym variants. The only weakness is that the capability statement is compressed to a single action, leaving the specific check dimensions (voice, tone, formatting) implied by triggers rather than stated in the what-clause.

DimensionReasoningScore

Specificity

The what-clause 'Review docs/prose for Writing Guidelines compliance' names the domain plus a single review action, but does not enumerate the concrete capability areas (voice, tone, formatting, structure) in the description itself. It sits squarely on the 'names domain and 1-2 concrete actions, but not comprehensive' anchor, not the level above, which requires several specific listed actions.

3 / 5

Completeness

Explicitly answers what ('Review docs/prose for Writing Guidelines compliance') and when ('Use when asked to...') with concrete trigger phrases, mirroring the top anchor's what+when structure. It is not the level below because the 'when' is explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Five natural quoted phrases users would plausibly say ('review my docs', 'check writing style', 'audit prose', 'review docs voice and tone', 'check this page against the writing handbook'), covering synonyms and phrasing variants, matching the comprehensive-coverage anchor. File extensions are not applicable to this docs-review domain, so their absence does not lower the score.

5 / 5

Distinctiveness Conflict Risk

The writing-guidelines/docs-prose niche is clear and mostly distinct, but 'review my docs' has minor overlap risk with general code-review or docs-authoring skills. It is not 5 because that trigger could plausibly route to a different skill; not 3 because the overall framing is specific to prose/style compliance.

4 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.