CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-polish

Polishes existing academic prose while preserving the author's meaning: grammar and flow repair, tone calibration against evidence strength, AI-tone removal, and Chinese-to-English rewriting at submission quality. Never fabricates data, citations, or claims, and flags any edit that could change scientific meaning. Use when the user asks to polish a draft, fix awkward wording, remove AI flavor, translate a Chinese manuscript into publishable English, or tone down overclaiming.

71

Quality

89%

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

85%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.

A well-structured, actionable instruction skill with a clear multi-step workflow, validation feedback loops, and properly split one-level-deep references. Minor conciseness trimming and a worked before/after example would lift the lower dimensions.

Suggestions

Trim the Overview section, which restates the frontmatter description, and tighten the section-convention summary that edges toward common knowledge to improve conciseness.

Add one short worked before/after polishing example showing the light-touch edit in action to raise actionability from concrete-but-instructed to fully demonstrated.

Consolidate the routing-to-other-skills notes (currently scattered across 'When NOT to use', 'One polishing pass', and 'When the problem is deeper than language') into a single decision point to reduce repetition.

DimensionReasoningScore

Conciseness

Largely efficient, domain-specific guidance that assumes Claude's competence (verb ladders, overclaim wordlists, Chinese-English residue fixes), but the Overview restates the description and a few section-convention remarks edge toward common knowledge.

4 / 5

Actionability

Highly concrete instruction-only guidance — named overclaim words, a verb ladder mapped to evidence strength, specific residue rewrites ('carry out research on becomes study'), and a defined delivery format — though no worked before/after polishing example is shown.

4 / 5

Workflow Clarity

The 'One polishing pass' sequence has explicit checkpoints and routing (structural problems to paper-writer, claim concerns to pre-submission-reviewer) plus a validation feedback loop — the sentence-by-sentence meaning self-check with author flagging.

5 / 5

Progressive Disclosure

A clear overview signals three one-level-deep references (section-conventions.md, academic-phrasebank.md, ai-tone-guardrails.md), all confirmed to exist, with detailed conventions/phrasebanks/checklists appropriately split out of the main body.

5 / 5

Total

18

/

20

Passed

Description

88%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, specific description that clearly states both what the skill does and when to use it, with natural trigger phrases. Minor overlap risk with generic editing skills and a few missing synonyms prevent a perfect score.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'grammar and flow repair, tone calibration against evidence strength, AI-tone removal, and Chinese-to-English rewriting at submission quality' — giving comprehensive coverage of the domain's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (polishes academic prose while preserving meaning, with the listed actions) and 'when' ('Use when the user asks to polish a draft, fix awkward wording, remove AI flavor...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrases like 'polish a draft', 'fix awkward wording', 'remove AI flavor', 'tone down overclaiming' are present and varied, but common synonyms such as 'proofread' or 'edit my paper' are missing, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The faithfulness/no-fabrication framing and Chinese-to-English rewriting carve a clear niche, but generic triggers like 'fix awkward wording' create minor overlap with general prose-editing skills.

4 / 5

Total

18

/

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
HKUSTDial/Supervisor-Skills
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.