academic-highlight-generator

Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content. Use when a user needs 3-5 concise, evidence-grounded highlight bullets for a research paper, review, meta-analysis, case report, or bioinformatics manuscript.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands, exact templates, and a well-validated workflow backed by real one-level-deep references. Its main weakness is redundancy: the same length/count constraints and the extraction command are repeated across multiple sections.

Suggestions

Consolidate the repeated 3-5 bullet and 85-character limits into the Output Contract and reference it from Deterministic Rules, Self-critique, and the Quality Checklist instead of restating each constraint.

State the `python scripts/extract_text.py <file_path>` invocation once (e.g. in Supported Execution Paths) and reference it from the Workflow rather than reprinting the full command three times.

Merge the largely overlapping Deterministic Rules and Quality Checklist into a single pre-return verification section to reduce duplicated guidance.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and stays directive, but it repeats the same constraints across sections (the 3-5 bullet and 85-char limits appear in Output Contract, Deterministic Rules, Self-critique, and Quality Checklist) and reprints `python scripts/extract_text.py <file_path>` three times, so it could be tightened.	2 / 3
Actionability	Guidance is copy-paste ready: an executable extraction command, an exact output-contract template, a literal refusal template, and concrete per-type coverage priorities, matching the score-3 anchor for fully executable, specific examples.	3 / 3
Workflow Clarity	The five-step workflow is clearly sequenced with explicit validation checkpoints (source-sufficiency gate in step 1, extraction-failure handling in step 2, a critique→refine feedback loop and final checklist in step 5), matching the score-3 anchor's validation and feedback-loop criteria.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points to real, one-level-deep bundle files (`references/prompts.md` for the detailed prompts, `scripts/extract_text.py` for extraction), both verified to exist, with content appropriately split and clearly signaled paths.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 concrete, trigger-rich, and clearly scoped to the academic Highlights niche with an explicit 'Use when' clause. Its only weakness is that it centers on a single primary action rather than enumerating multiple distinct capabilities.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and inputs ('submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content') but revolves around a single primary action (generate highlights), so it does not list multiple distinct concrete actions like the score-3 anchor.	2 / 3
Completeness	Explicitly answers what ('Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content') and when ('Use when a user needs 3-5 concise, evidence-grounded highlight bullets...'), satisfying the score-3 anchor's requirement for both with explicit triggers.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered ('Highlights', 'research paper', 'review', 'meta-analysis', 'case report', 'PDF/DOCX/TXT'), matching the score-3 anchor's breadth of how a user would phrase the need.	3 / 3
Distinctiveness Conflict Risk	The Elsevier/SCI Highlights niche with manuscript-type triggers is distinct and unlikely to fire for unrelated skills, matching the score-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 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
Commit: d924410

Reviewed: 13 days 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.