methods-section-writer

Turns your protocol and analysis workflow into publication-ready Methods text. Use when writing or revising the Methods section of a biomedical manuscript, ensuring it complies with reporting guidelines (CONSORT, STROBE, PRISMA, TRIPOD), matches what is in the Results section, and satisfies journal-specific word limits and declarations. Also triggers on "write my methods", "revise my methods section", "how to report my statistics", "what do I need to include in methods for [study type]", or "make my methods CONSORT-compliant".

Quality

84%

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

Quality

Content

78%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 Methods-writing skill with a clear five-step workflow and excellent progressive disclosure into real reference files. The main gaps are minor: duplicated guideline listings, no full worked example of finished prose, and a single-pass rather than iterative validation check.

Suggestions

De-duplicate the reporting-guideline mappings: CONSORT/STROBE/PRISMA/TRIPOD appear in both Step 1 and the Quick Reference table — keep only the table and reference it from Step 1 to tighten conciseness.

Add one short worked example of a finished Methods subsection (e.g., a sample 'Statistical analysis' paragraph) so the guidance is copy-paste-ready and actionability reaches 5.

Turn the Step 4 guideline check into an explicit validate→fix→re-check loop (flag missing item → request or placeholder it → re-verify coverage) to strengthen the workflow's feedback checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no padding about what CONSORT or IMRAD are), but the reporting-guideline mappings are listed twice — once in Step 1 and again in the Quick Reference table — which is a minor removable redundancy.	4 / 5
Actionability	Highly concrete, actionable guidance: per-study-type required inputs, eight named IMRAD subsections with their contents, and an explicit placeholder syntax ('[AUTHOR TO SPECIFY: randomization method]'). It stops short of a full worked example of finished Methods prose, the instruction-skill analog of copy-paste-ready code.	4 / 5
Workflow Clarity	Five clearly sequenced steps with input-gating checkpoints ('If the study type is unclear, ask…', 'If critical items are missing, ask…') and an explicit validation step (Step 4 guideline check) plus a coverage-note deliverable. It is not a destructive/batch operation so the cap does not apply; it lacks a true validate→fix→re-check feedback loop, keeping it below 5.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview that pushes detail one level deep to three real, well-signaled files ('→ IMRAD structure', '→ Reporting guidelines detail', '→ Writing principles'), each verified to exist in references/. Navigation is easy and the split is appropriate.	5 / 5
	Total	17 / 20 Passed

Description

90%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, complete description with explicit what/when structure and excellent natural trigger phrases. Its only real weakness is second-person voice ('your', imperative 'Use'), which the rubric penalizes on specificity.

Suggestions

Rewrite in third person to remove the second-person 'your' and imperative 'Use' (e.g., 'Turns a protocol and analysis workflow into publication-ready Methods text. Triggers when the user is writing or revising…') — the rubric explicitly penalizes second-person voice on specificity.

Lead with concrete deliverable verbs ('drafts, revises, and restructures Methods prose') rather than process/constraint verbs like 'complies' and 'satisfies' to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('writing or revising the Methods section', 'complies with reporting guidelines (CONSORT, STROBE, PRISMA, TRIPOD)', 'matches what is in the Results section', 'satisfies journal-specific word limits and declarations'), which is a base of 4; the rubric penalizes second-person voice, and 'Turns your protocol…' plus the imperative 'Use when…' trigger a -1 reduction.	3 / 5
Completeness	It explicitly answers both 'what' ('Turns your protocol and analysis workflow into publication-ready Methods text') and 'when' ('Use when writing or revising the Methods section… Also triggers on…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases a user would actually say are listed verbatim: 'write my methods', 'revise my methods section', 'how to report my statistics', 'what do I need to include in methods for [study type]', and 'make my methods CONSORT-compliant'.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche — biomedical Methods sections bound to named reporting guidelines (CONSORT/STROBE/PRISMA/TRIPOD) — with distinct triggers, so conflict with other skills is minimal.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Academic Writing/methods-section-writer/SKILL.md
Commit: f5ef65b

Reviewed: ~8 hours 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.