scientific-writing

Academic manuscript writing with IMRAD structure, citation formatting, and reporting guidelines. Use when drafting or revising research papers.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/scientific-writing/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-organized instruction-only skill that delivers specific quantified writing rules. It is held back by a lack of worked examples and an explicit drafting/revising workflow with validation checkpoints, which leave actionability and workflow clarity at the mid level.

Suggestions

Add 1-2 short worked examples (e.g., a before/after abstract or a corrected citation string) to lift actionability from rules to copy-paste-ready guidance.

Convert the IMRAD sections plus Revision Checklist into an explicit end-to-end workflow (draft → self-check against checklist → revise → re-check) with validation checkpoints to improve workflow clarity.

Include a couple of concrete trigger phrasings or a one-line "When the user says 'write my paper', 'fix my abstract', or 'format my citations'…" note to bridge the guidance to natural requests.

Dimension	Reasoning	Score
Conciseness	Lean bullet-pointed guidance with no padding and no over-explanation of concepts Claude already knows; every line delivers a concrete rule. Not score 2 because there is no unnecessary explanation to trim.	3 / 3
Actionability	Provides concrete quantified rules ("150-300 words", "15-25 words per sentence", "select the most relevant 2-3") and a few before/after pairs, but lacks worked manuscript examples and some directives stay abstract ("Move from broad context to specific gap"). Not score 3 because it is not copy-paste-ready with concrete worked examples; not score 1 because much of the guidance is specific and actionable.	2 / 3
Workflow Clarity	IMRAD is sequenced and a Revision Checklist supplies verification steps, but there is no explicit draft-to-revision workflow with validation feedback loops tying the sections together. Not score 3 because checkpoints are implicit rather than a clear validate-fix-retry loop; not score 1 because steps and a checklist are present.	2 / 3
Progressive Disclosure	Under 50 lines with no need for external references, organized into clearly labeled sections (IMRAD, Paragraph-Level, Citations, Pitfalls, Reporting, Revision). Per the simple-skills note, this earns a 3 with well-organized sections alone. Not score 2 because organization is clean and no nested references exist.	3 / 3
	Total	10 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 well-constructed description that explicitly covers what the skill does and when to use it, with concrete domain actions and a distinct academic niche. The main gap is trigger-term coverage, which omits several natural variations a user might say.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and areas — "manuscript writing", "citation formatting", "reporting guidelines", "drafting or revising research papers" — rather than vague language. Not score 2 because it lists several specific concrete actions, not just a domain with one or two actions.	3 / 3
Completeness	Clearly states what ("Academic manuscript writing with IMRAD structure, citation formatting, and reporting guidelines") and an explicit when ("Use when drafting or revising research papers"). Not score 2 because the when clause is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes natural terms a user would say ("manuscript", "research papers", "drafting", "revising") but misses common variations like "article", "journal", "thesis", or "abstract", and "IMRAD" is technical jargon. Not score 3 because coverage of natural phrasings is incomplete.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (academic manuscripts, IMRAD, reporting guidelines) with distinct triggers unlikely to fire for general writing skills. Not score 2 because the IMRAD/citation/reporting framing makes it clearly distinguishable.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: aiming-lab/AutoResearchClaw
Path: .claude/skills/scientific-writing/SKILL.md
Commit: e2e23c9

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.