title-and-abstract-optimizer

Optimizes manuscript titles and abstracts for information density, factual accuracy, and submission fit in biomedical research writing.

Quality

67%

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/title-and-abstract-optimizer/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 delivers a genuinely actionable instruction skill: a clear 8-step workflow, an exact A–I output contract, strong claim-discipline rules, and well-signaled references that all exist. Its main weakness is redundancy — at least four sections restate each other or duplicate the reference files, inflating token cost for a hub document. A worked before/after example and a de-duplicated structure would raise both conciseness and actionability.

Suggestions

Merge 'Task' into 'Core Function' and 'Input Validation' into Step 1, and collapse 'Scope Boundary' and 'What This Skill Should Not Do' into a single section to eliminate restated content.

Replace the inline 10-rule 'Hard Rules' section with a pointer to references/hard-rules.md (keeping only the 2–3 non-negotiables inline), since the reference file already carries the full list.

Add one compact before/after title-optimization example (vague title → optimized title with one-line rationale) to make the diagnosis and rewrite steps concrete.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose through redundancy: 'Task' and 'Core Function' enumerate the same duties, 'Input Validation' restates 'Step 1 — Clarify before optimizing', 'Scope Boundary' is repeated by 'What This Skill Should Not Do', and the inline 10-rule 'Hard Rules' section duplicates references/hard-rules.md. For a hub file whose details live in five reference files, several sections are padded restatements rather than lean guidance, which matches the 'noticeably verbose' anchor rather than 'could be tightened'.	2 / 5
Actionability	The guidance is concrete and executable for an instruction-only skill: an exact mandatory output structure ('Use the section headers exactly as above', sections A–I), an 8-step execution sequence, a specific input-validation checklist, and precise prohibitions ('Do not convert association into causation, prediction into mechanism'). It falls short of a 5 because there is no worked before/after example showing a diagnosis and rewrite in action.	4 / 5
Workflow Clarity	Steps 1–8 are clearly sequenced with explicit checkpoints: the Step 1 gate ('do not immediately produce a full optimized title and abstract'), output section A 'Input Match Check', and section H 'Claim Boundary Check'. The minor gap versus a 5 is the absence of an explicit feedback loop that re-validates the optimized text against the hard rules before finalizing.	4 / 5
Progressive Disclosure	All five referenced files exist in references/ and are one level deep, each signaled with a usage cue ('Use before any long-form optimization', 'Apply throughout the entire response'). The split is not fully clean, however: inline content such as the 10 'Hard Rules' and the clarify-first guidance duplicates what the reference files already carry, which is exactly the organization gap the anchor at 4 describes.	4 / 5
	Total	14 / 20 Passed

Description

61%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 clear, domain-specific description that states what the skill does and for whom, with good natural keywords around titles, abstracts, and submission. Its main gaps are the absence of any 'Use when...' trigger clause (capping completeness) and reliance on a single action verb instead of enumerating the concrete operations performed. Adding explicit triggers and one or two more concrete actions would lift it substantially.

Suggestions

Append a 'Use when...' clause with concrete triggers, e.g. 'Use when the user asks to optimize, tighten, or make a manuscript title or abstract submission-ready, or mentions polishing a title/abstract for a biomedical journal.'

Replace the single verb 'Optimizes' with the distinct actions performed: e.g. 'Diagnoses wording-vs-design mismatches, rewrites titles for information density, restructures abstracts, and explains each change.'

Add natural synonyms users would say, such as 'paper', 'journal', 'polish', or 'revise', to broaden trigger matching.

Dimension	Reasoning	Score
Specificity	The description names the domain ('manuscript titles and abstracts' in biomedical research) and one concrete action ('Optimizes') with named quality targets ('information density, factual accuracy, and submission fit'), but does not list several distinct actions like diagnose, restructure, or rewrite. It sits at the 'domain plus 1-2 concrete actions' level rather than comprehensive coverage, so it is not a 4.	3 / 5
Completeness	It answers 'what' clearly (optimizes titles and abstracts for density, accuracy, and submission fit) but contains no 'Use when...' clause or equivalent explicit trigger guidance; 'in biomedical research writing' only weakly implies when. Per the guidelines, a missing 'when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms users would say are present: 'titles', 'abstracts', 'manuscript', 'submission', 'biomedical research'. Common variations are still missing — 'paper', 'polish', 'revise', 'journal article' — which keeps it below the comprehensive-synonym coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	The biomedical title/abstract optimization niche is mostly distinct with minor overlap risk against general academic-writing or editing skills. It lacks the explicit distinct triggers needed for a 5, but is far more specific than the broad-domain examples at 3.	4 / 5
	Total	14 / 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/title-and-abstract-optimizer/SKILL.md
Commit: 686e09d

Reviewed: 13 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.