CtrlK
BlogDocsLog inGet started
Tessl Logo

scholarly-writing-refiner

Polishes academic English paragraph by paragraph, reviewing grammar, word choice, voice, coherence, and sentence structure. Outputs revision suggestions alongside polished text. Triggered by phrases like 'polish this paragraph,' 'check the grammar,' 'rewrite in academic English,' or keywords like manuscript editing, SCI polishing, and journal submission editing.

67

Quality

80%

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/scholarly-writing-refiner/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 highly actionable and well-sequenced for an instruction-only skill, with concrete rule tables and a precise output format. Its main weaknesses are token inefficiency from restating basic English grammar knowledge and a monolithic structure that inlines large reference tables that would be better split into separate files.

Suggestions

Trim or remove sections restating knowledge Claude already has — e.g., the basic grammar error checklist (2.1) and the redundancy table (3.3) — keeping only the genuinely skill-specific rules such as the tense-by-section table and field conventions.

Move the large substitution tables (3.1-3.3), section-specific polishing guide (section 7), and domain-specific notes (section 9) into reference files (e.g., references/word-choice.md, references/sections.md) and keep SKILL.md as a lean overview with one-level-deep, clearly signaled links.

Add a final validation checkpoint to the Section 10 workflow, e.g., re-reading the polished paragraph against the original to confirm meaning and technical content are preserved before delivering the output.

DimensionReasoningScore

Conciseness

The table format is dense and reference-like, but large portions restate knowledge Claude already has — basic grammar errors (subject-verb agreement, that/which, run-ons), redundancy pairs ("in order to" → "to", "due to the fact that" → "because"), and Oxford comma rules — that could be cut or heavily trimmed.

3 / 5

Actionability

Guidance is highly concrete and executable: error→correction→explanation tables, a copy-paste output format template with a rating scheme, section-by-section structures with pattern sentences, and explicit core principles (minimize changes, preserve meaning, defer to author terminology).

5 / 5

Workflow Clarity

Section 10 provides a clear six-step sequence (confirm details → identify section → five-dimension review → annotate with cited rules → output → summarize) with an upfront confirm-details checkpoint and an uncertainty-handling principle, but there is no final checkpoint verifying the polished output before delivery.

4 / 5

Progressive Disclosure

The body is a ~345-line monolith with no bundle files at all; the substitution tables, section-specific guides, and field-convention notes are inline reference material that clearly belongs in separate files, though the numbered section headers keep it navigable.

3 / 5

Total

15

/

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 description: it uses third person, names concrete actions covering all five review dimensions, and pairs them with an explicit trigger clause containing natural user phrases. Its only weaknesses are a few missing common synonyms (e.g., "proofread") and slight overlap risk on generic grammar-editing triggers.

DimensionReasoningScore

Specificity

The description enumerates the complete set of concrete review dimensions ("grammar, word choice, voice, coherence, and sentence structure") plus both concrete outputs ("revision suggestions alongside polished text"), giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

It explicitly answers both questions: the "what" is stated as concrete polishing actions with named outputs, and the "when" is stated as "Triggered by phrases like 'polish this paragraph'..." with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases ("polish this paragraph," "check the grammar," "rewrite in academic English") and domain keywords (manuscript editing, SCI polishing, journal submission editing) are provided, but common user variations such as "proofread," "edit my paper," or "improve my writing" are missing.

4 / 5

Distinctiveness Conflict Risk

The academic-manuscript polishing niche (SCI polishing, journal submission editing) is mostly distinct, but generic triggers like "check the grammar" create minor overlap risk with general writing/grammar-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
zebbern/claude-code-guide
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.