CtrlK
BlogDocsLog inGet started
Tessl Logo

write

Rewrites and polishes prose in Chinese or English, removes AI-like wording, and reviews product localization copy while preserving intent for drafts, docs, release notes, launch copy, and social posts. Use when users ask in any language to draft, rewrite, proofread, localize, polish release notes, remove AI-like wording, or prepare launch and social copy. Not for code comments, commit messages, or inline docs.

68

Quality

83%

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

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 strong progressive disclosure and an actionable Punctuation Gate workflow, but several principle sections and Gotchas are verbose relative to what Claude already knows and could be tightened without losing clarity.

Suggestions

Tighten the multi-sentence Hard Rules (e.g. 'Material gate before drafting long-form', 'No silent restructuring') into one-line rules with the rationale moved to a reference, to reduce tokens without losing the constraint.

Consolidate the Gotchas table: several rows restate Hard Rules already covered above (restructure, change-list, padding), so keep only the rows that add a new smell not already enforced.

Make the language-detection Pre-flight step into a short decision table or code block so the branch logic is scannable rather than buried in nested prose.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence, but several Hard Rules and Gotchas are long and restate overlapping principles (e.g., the 'Material gate' and 'Stop after output' rules run to multi-sentence paragraphs that could be tightened).

3 / 5

Actionability

Provides an executable Punctuation Gate bash snippet, a real script, and concrete mode workflows with specific steps; minor gaps remain where guidance is principle-level rather than a runnable command.

4 / 5

Workflow Clarity

A clear Pre-flight sequence, Mode Picker table, and Hard Rules give an ordered process with a verification checkpoint (the Punctuation Gate must run before returning text); the long-form exception is the only place feedback loops are fully spelled out.

4 / 5

Progressive Disclosure

SKILL.md is a clear overview that signals one-level-deep references via a Mode Picker table and inline links; all ten referenced files and the gate script exist, and the large pattern catalogs are correctly split into references/.

5 / 5

Total

16

/

20

Passed

Description

96%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 concrete, bilingual, and explicitly states both capabilities and trigger conditions with a clear exclusion clause. It is strong on specificity, trigger coverage, and completeness, with only minor overlap risk on the generic 'draft/rewrite' verbs.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Rewrites and polishes prose', 'removes AI-like wording', 'reviews product localization copy while preserving intent' — across named output types (drafts, docs, release notes, launch copy, social posts), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (rewrites/polishes prose, removes AI-like wording, reviews localization) and 'when' with a concrete 'Use when users ask in any language to draft, rewrite, proofread, localize...' clause, plus a 'Not for...' exclusion.

5 / 5

Trigger Term Quality

Includes natural user phrasings in both Chinese (改稿, 润色, 去AI味, 审稿) and English (proofread, localize, polish, rewrite, draft) plus surface-specific terms (release notes, launch copy, social post, tweet), covering synonyms and common variations.

5 / 5

Distinctiveness Conflict Risk

The prose/localization/social-copy niche with explicit triggers is largely distinct, but the broad 'draft, rewrite, proofread' verbs create minor overlap risk with general writing or doc-editing skills.

4 / 5

Total

19

/

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.

Validation15 / 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
tw93/Waza
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.