discussion-composer

Composes a Discussion around key findings, mechanisms, clinical relevance, and limitations. Use when writing or improving a Discussion section for any biomedical manuscript — including interpreting results, connecting to prior literature, addressing unexpected findings, framing limitations, and writing the conclusion. Also triggers on "write my discussion", "help me discuss my findings", "how do I compare to prior studies", "write the limitations paragraph", or "draft a discussion for my paper".

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

70%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 content is well-structured with a clear, validated workflow and concrete, actionable templates, but it suffers from repeated restatement of the fabrication rule and bundle files that exist on disk yet are never linked from the body. Tightening the redundancy and wiring up the existing references would lift the weaker dimensions.

Suggestions

Consolidate the no-fabrication rule into a single 'Hard Rules' section and remove its restatements from Input Validation, Step 2, and the checklist to reduce token redundancy (targets conciseness).

Link the bundle files from the body — e.g., add a line pointing to scripts/main.py for automated outline generation and to references/audit-reference.md for the audit/fallback boundary — so the existing references are actually discoverable (targets progressive_disclosure).

Add one short, complete worked-example Discussion paragraph (e.g., a 2–3 sentence interpretation + one hedged literature comparison) so the structural template is demonstrated end-to-end (targets actionability).

Dimension	Reasoning	Score
Conciseness	The body is mostly instruction-dense and avoids explaining concepts Claude already knows, but the no-fabrication rule is restated in four places (Input Validation out-of-scope, Step 2 rules, Hard Rules, the checklist) and the 6-part structure is shown in a code block then re-elaborated in Step 2, so it could be tightened — matching the mostly-efficient-but-could-be-tightened anchor rather than the minor-gaps anchor.	3 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill — sentence counts ('Opening 2–3 sentences', 'Conclusion 3–5 sentences'), an exact limitation format ('[Constraint] → [Impact on interpretation] → [How future work could address it]'), a worked data example ('HR 1.43, 95% CI 1.12–1.82'), and placeholder syntax — but a complete worked example paragraph would close the gap to fully copy-paste ready.	4 / 5
Workflow Clarity	A clear four-step sequence (Collect Inputs → Draft → Revise Checklist → Deliver) with an explicit verification checklist as the gate before delivery and an input-validation checkpoint ('If key results are not provided, ask before writing'), matching the clear-sequence-with-explicit-validation-and-checklist anchor.	5 / 5
Progressive Disclosure	Section headers organize the body well, but the bundle files (references/audit-reference.md and scripts/main.py) are never referenced or signaled from SKILL.md — they are orphaned — so references are present in the bundle but not clearly navigated, fitting the some-structure / references-not-clearly-signaled anchor.	3 / 5
	Total	15 / 20 Passed

Description

100%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 exemplary: third-person voice, concrete capability list, explicit 'Use when' guidance, and natural quoted trigger phrases that answer both what and when with low conflict risk. It hits the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'interpreting results, connecting to prior literature, addressing unexpected findings, framing limitations, and writing the conclusion' — giving comprehensive coverage of what the skill does, matching the score-5 anchor.	5 / 5
Completeness	It clearly states what it does ('Composes a Discussion around key findings, mechanisms, clinical relevance, and limitations') and when to use it ('Use when writing or improving a Discussion section for any biomedical manuscript') with concrete trigger phrases, satisfying both the what and the when at the top anchor.	5 / 5
Trigger Term Quality	Explicit quoted natural-language triggers ('write my discussion', 'help me discuss my findings', 'how do I compare to prior studies', 'write the limitations paragraph', 'draft a discussion for my paper') are phrases a user would naturally say, matching comprehensive coverage of natural terms.	5 / 5
Distinctiveness Conflict Risk	The niche is narrow and explicit — biomedical Discussion sections — and the triggers are discussion-specific (limitations, conclusions, findings discussion), giving a clear niche with minimal conflict risk against sibling writing skills.	5 / 5
	Total	20 / 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/discussion-composer/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.