CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

taste-lens

Check a draft against the author's editorial taste as a pass/flag review, covering adverbs, hedges, AI transitions, corporate bloat, bullets in narrative, flat openings, and a preserve list that protects facts and the author's point. Quotes every hit and never scores. Use after the allergist and before guardrails-lens when reviewing a draft for publication.

Quality

97%

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%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.

Excellent instruction-only skill body: terse, concrete word-level kill lists, an explicit report format with examples, clear pipeline sequencing and loop-back rules, and a preserve list that guards against damaging fixes. No bundle files are needed and none are referenced.

DimensionReasoningScore

Conciseness

The body is lean and every token earns its place ('Adverbs propping up a weak verb. Pick a better verb.'; 'One precise adjective beats three vague ones.'). It assumes Claude's competence, explains nothing Claude already knows, and even the inlined allergist boundary list serves a functional purpose rather than padding — anchor 5.

5 / 5

Actionability

For an instruction-only skill the guidance is fully concrete: exact word lists ('utilize, facilitate, optimize, implement, strategize, synergy, alignment'), exact hedge phrases, a preserve list with precise rules, and a copy-paste report template with worked example flags ('Taste: 3 flags. - Adverb propping a verb: "the deploy failed spectacularly"'). This satisfies the anchor 5 bar of specific examples covering the common cases.

5 / 5

Workflow Clarity

The single review action is unambiguous (quote every hit, report in the given format), sequencing is explicit ('runs second, after the `allergist`'; 'edited passages go back through the allergist'), and error handling is specified ('Send the draft back rather than flagging it here'). It is a non-destructive single-pass review, so the destructive/batch validation cap does not apply — anchor 5.

5 / 5

Progressive Disclosure

There are no bundle files and none are needed for a single-pass review; all checks must be visible in one pass, so a single file is the appropriate split. Sections are well-organized and easy to navigate (sentence standard, flag checks at sentence/paragraph level, preserve list, report), matching the well-organized-structure standard for anchor 5.

5 / 5

Total

20

/

20

Passed

Description

92%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: concrete and comprehensive about what it checks, with an explicit use-when clause and clear pipeline positioning. The only gap is a handful of natural trigger synonyms (editing, prose, style) that users might say when they need this skill.

Suggestions

Add one or two natural synonyms users would say, e.g. 'Use ... when editing or reviewing a draft (post, essay, prose) for publication', to broaden trigger matching.

Consider naming the output artifact or consumer of the report (e.g., 'returns a pass/flag report for the drafting loop') to further distinguish it from generic editing/proofreading skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete, specific actions — 'covering adverbs, hedges, AI transitions, corporate bloat, bullets in narrative, flat openings, and a preserve list' — plus concrete behaviors ('Quotes every hit and never scores'). Coverage of the skill's checks is comprehensive rather than having minor gaps, matching the anchor 5 example's structure.

5 / 5

Completeness

It clearly answers both questions: what ('Check a draft against the author's editorial taste as a pass/flag review, covering...') and when ('Use after the allergist and before guardrails-lens when reviewing a draft for publication') — an explicit 'Use when' clause with a concrete trigger. This matches anchor 5; anchor 4 would require the 'when' to be less explicit.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'draft', 'reviewing a draft for publication', 'adverbs', 'hedges', 'corporate bloat', 'AI transitions'. A few natural terms a user might say are missing (e.g., 'editing', 'prose', 'style', 'writing'), which fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (editorial-taste pass/flag review) with distinct triggers, and explicit positioning within its skill pipeline ('Use after the allergist and before guardrails-lens') minimizes conflict with sibling review skills. Anchor 5 fits; it is not merely 'mostly distinct' as in anchor 4.

5 / 5

Total

19

/

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

shortrib-labs/content-loop

Path

plugins/review/skills/taste-lens/SKILL.md

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.