results-section-writer

Writes the full Results section of a biomedical manuscript from a sufficiently clear result structure, figure inventory, or analysis summary while preserving evidence boundaries and result hierarchy.

Quality

55%

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/results-section-writer/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 body is a well-structured, discipline-focused instruction skill with a clear multi-step workflow, a real input-sufficiency checkpoint, and eight genuine one-level-deep reference files that are actively integrated. It loses points mainly for repetition across overlapping sections and for limited concrete output examples (marker format, PubMed query syntax, sample prose).

Suggestions

De-duplicate the refusal/clarification guidance that recurs in Task, Input Validation, Execution Steps 1-2, Hard Rules, and 'What This Skill Should Not Do'; consolidate to a single authoritative statement and reference it.

Add a concrete example of the citation-support marker format and an example PubMed search query string in section E or in citation-support-annotation-rules.md so the action is executable rather than described.

Link the eight reference files as clickable markdown links (e.g. `[clarification-first-rule](references/clarification-first-rule.md)`) rather than plain backtick paths to improve navigation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and instruction-oriented, but it restates the same refusal/clarification guidance across Task, Input Validation, Execution Steps 1-2, Hard Rules, and 'What This Skill Should Not Do', producing noticeable repetition that could be tightened.	3 / 5
Actionability	Guidance is concrete in structure (named output sections A-I, a 9-step execution sequence, a hard-rule list) but, as an instruction-only writing skill, it gives few concrete examples of actual prose output, citation marker format, or PubMed query syntax, leaving the 'how exactly' somewhat abstract.	3 / 5
Workflow Clarity	A clear 9-step sequence with an upfront input-sufficiency checkpoint, a readiness decision, and a final uncertainty-flagging step; minor gaps only — it lacks an explicit 're-clarify on insufficient answer' feedback loop after asking follow-up questions.	4 / 5
Progressive Disclosure	The body is well organized into overview-style sections that actively signal and describe each of the eight one-level-deep reference files (all confirmed present in references/), keeping navigation clear; minor gap is that body headers reference files by path rather than as clickable links.	4 / 5
	Total	14 / 20 Passed

Description

51%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 distinct, naming the domain and several concrete actions with third-person voice, but it lacks any explicit 'Use when...' trigger guidance and omits the natural user phrases that appear only in the body. This caps completeness and trigger-term quality at the mid range.

Suggestions

Append an explicit trigger clause such as 'Use when the user asks to write, draft, or expand the full Results section from a clear figure order or result hierarchy.'

Surface natural trigger phrases a user would actually say (e.g. 'write the Results section', 'turn these result blocks into prose', 'expand this Results outline') into the description rather than leaving them in the body's Sample Triggers.

Mention the supporting concrete actions already in the body — marking citation-needed statements with PubMed queries and explaining writing logic — to broaden capability coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions such as writing 'the full Results section', converting a result hierarchy 'into full prose', and 'preserving evidence boundaries and result hierarchy', though it stops short of enumerating the supporting actions (citation marking, PubMed queries, logic reporting) that appear in the body.	4 / 5
Completeness	It clearly states what the skill does (write the full Results section from a clear structure) but never gives an explicit 'Use when...' clause, capping completeness at 3 per the rubric's missing-trigger-guidance rule.	3 / 5
Trigger Term Quality	The phrase 'Results section of a biomedical manuscript' is domain-appropriate but it omits the natural trigger phrases a user would actually say ('write the Results section', 'turn result blocks into prose', 'draft the Results'), which only appear later in the body's Sample Triggers rather than the description.	2 / 5
Distinctiveness Conflict Risk	The niche is fairly specific ('full Results section ... preserving evidence boundaries and result hierarchy') and distinct from the sibling 'Results Section Structurer', with only minor overlap risk against closely related biomedical writing skills.	4 / 5
	Total	13 / 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/results-section-writer/SKILL.md
Commit: f5ef65b

Reviewed: ~10 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.