reporting-guideline-compliance-checker

Checks biomedical manuscripts against reporting guidelines such as CONSORT, STROBE, PRISMA, and TRIPOD to identify missing or weak reporting elements before submission or revision.

Quality

62%

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 ./awesome-med-research-skills/Academic Writing/reporting-guideline-compliance-checker/SKILL.md

Quality

Content

60%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 skill is well-structured with clear references, an explicit sequenced workflow, and a concrete mandatory output structure, but it is substantially padded by triple-stating the same workflow and repeating the same guardrails across multiple sections. Collapsing the redundant sections and moving duplicated rule content fully into the reference files would meaningfully improve token efficiency.

Suggestions

Merge the 'Task', 'Core Function', and 'Execution' sections into a single canonical workflow — the three currently restate the same ~7-8 steps almost verbatim.

Consolidate overlapping guardrail lists ('Scope Boundary', 'What This Skill Should Not Do', 'Hard Rules', 'Quality Standard') into one section, referencing hard-rules.md instead of restating it inline.

Add one short worked example (a sample compliance-review output for a hypothetical manuscript) to lift actionability toward 5 without adding much length.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several padded, redundant sections — 'Task', 'Core Function', and 'Execution' restate the same ~7-step workflow three times, and 'Scope Boundary', 'Important Distinctions', 'What This Skill Should Not Do', 'Hard Rules', and 'Quality Standard' heavily overlap — without explaining concepts Claude does not already know, placing it above 1 but below 3.	2 / 5
Actionability	For an instruction-only skill it gives concrete, executable guidance — a mandatory A-I output structure, named framework mappings, a specific high-risk item list, and a severity taxonomy — but lacks a worked example showing the output in practice, so it stops at mostly-executable rather than fully copy-paste ready.	4 / 5
Workflow Clarity	An explicit 8-step Execution sequence with a front-loaded validation gate (Step 1 'Clarify before checking' plus Section A 'Input Match Check') and feedback loop (ask before producing a full review) is present, but validation is input-stage only with no mid-process error recovery, leaving a minor gap below 5.	4 / 5
Progressive Disclosure	Seven real reference files are clearly signaled one level deep in 'Reference Module Integration' with per-file 'Use to…' guidance, but content from those references (hard rules, severity levels, high-risk items) is also duplicated inline in SKILL.md, a minor organization gap below 5.	4 / 5
	Total	14 / 20 Passed

Description

65%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 and highly distinct, naming concrete reporting frameworks and a clear domain, but it lacks an explicit 'Use when…' trigger clause and only weakly implies when the skill should activate. Adding concrete trigger phrases would raise completeness and trigger-term coverage.

Suggestions

Add an explicit 'Use when…' clause with concrete triggers, e.g. 'Use when a user asks whether a manuscript complies with CONSORT, STROBE, PRISMA, or TRIPOD, or wants to find missing reporting items before submission.'

List one or two more distinct concrete actions (e.g. 'classifies omissions by severity' or 'produces a prioritized correction plan') to move specificity toward 4-5.

Include common synonyms such as 'checklist' or 'compliance review' alongside the guideline acronyms to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (biomedical manuscripts) and concrete frameworks (CONSORT, STROBE, PRISMA, TRIPOD) plus one to two actions ('Checks…to identify missing or weak reporting elements'), but does not list several distinct concrete actions, so it sits at the domain-plus-1-2-actions anchor rather than 4.	3 / 5
Completeness	The 'what' is clearly stated, but the 'when' is only weakly implied via 'before submission or revision' (a lifecycle stage, not a skill trigger) and there is no 'Use when…' clause, so per the cap guidance completeness cannot exceed 3.	3 / 5
Trigger Term Quality	Natural user-facing terms are present — the guideline acronyms, 'manuscripts', and 'submission or revision' — giving good keyword coverage, though a few common synonyms such as 'checklist' or 'compliance review' are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche — reporting-guideline compliance checking for biomedical manuscripts with named frameworks — yielding distinct triggers and minimal overlap with other skills.	5 / 5
	Total	15 / 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/reporting-guideline-compliance-checker/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.