method-writing

Write and revise the Methods section of research papers to ensure reproducibility; use when preparing an IMRAD manuscript or responding to journal/reporting-guideline requirements (e.g., CONSORT/STROBE/PRISMA).

Quality

85%

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

75%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 a well-structured, actionable Methods-writing guide with real reference files backing its progressive disclosure. Its main weakness is conciseness: several generic boilerplate sections pad the skill without adding skill-specific value.

Suggestions

Remove or collapse the generic boilerplate sections (Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling, Input Validation, Quick Validation) into a few skill-specific lines; the "No local script validation step is required" block in particular adds nothing.

Convert reference mentions into proper markdown links (e.g. [imrad_structure.md](references/imrad_structure.md)) and drop the repeated "if available" hedges now that the files exist, to make navigation crisper.

Tighten the validation guidance in the Recommended Workflow into a concrete verify step tied to the reporting checklist (e.g. 're-check each CONSORT item is explicitly reported') rather than a generic 'final validation pass'.

Dimension	Reasoning	Score
Conciseness	The core (Key Features, the 10-step algorithm, the worked example) is efficient, but generic scaffolding sections — Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling, and a "Quick Validation" block stating "No local script validation step is required" — are padded boilerplate Claude does not need.	3 / 5
Actionability	For an instruction-only skill the guidance is highly actionable: a concrete 10-step Methods algorithm naming specific checks (Shapiro-Wilk, Cohen's d/η²/OR/RR, Holm/Bonferroni/FDR, IQR/Grubbs outliers) plus a near-copy-paste worked example covering the common RCT case.	5 / 5
Workflow Clarity	The IMRAD-aligned algorithm is a clearly ordered 10-step sequence with an explicit validation pass and user-checkpoint guidance; the checkpoints are somewhat generic rather than concrete verify-then-proceed loops, leaving a minor gap below the explicit-feedback-loop anchor.	4 / 5
Progressive Disclosure	Structure is sound: the body holds the overview/algorithm/example while deeper material (imrad_structure.md, reporting_guidelines.md, writing_principles.md — all present in ./references/) is one level deep and signaled inline; references are backtick paths hedged with "if available" rather than clean markdown links, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

95%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 specific, trigger-rich, and cleanly separates what the skill does from when to invoke it, with minimal conflict risk. It is a strong, concise description that would reliably fire on the right requests.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "Write and revise the Methods section of research papers to ensure reproducibility" and "responding to journal/reporting-guideline requirements" — with only minor coverage gaps, fitting the 'lists several specific actions' anchor above the 1-2-action midpoint.	4 / 5
Completeness	Explicitly answers both halves: the 'what' (write/revise the Methods section for reproducibility) and the 'when' via a concrete "use when preparing an IMRAD manuscript or responding to journal/reporting-guideline requirements" trigger clause.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage for the domain — "Methods section", "research papers", "IMRAD manuscript", "journal/reporting-guideline", and the CONSORT/STROBE/PRISMA acronyms researchers actually say — matching the comprehensive-synonyms anchor rather than the 'few terms missing' level below.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Methods sections of IMRAD manuscripts under reporting guidelines) with distinct triggers, so overlap with other skills is minimal; not a broad 'helps with documents' case.	5 / 5
	Total	19 / 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: scientific-skills/Academic Writing/method-writing/SKILL.md
Commit: 63c61d3

Reviewed: 12 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.