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.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a narrow, well-scoped capability with strong trigger terms from the academic publishing domain. It uses proper third-person voice, includes an explicit 'Use when' clause with multiple manuscript type variations, and is highly distinctive. The description is concise yet comprehensive, covering input formats, output format, and use cases.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Generates submission-ready Elsevier/SCI Highlights', 'from manuscript text or extracted PDF/DOCX/TXT content', '3-5 concise, evidence-grounded highlight bullets'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (generates submission-ready Elsevier/SCI Highlights from manuscript content) and 'when' (explicit 'Use when' clause specifying user needs 3-5 highlight bullets for various manuscript types). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Elsevier', 'SCI', 'Highlights', 'manuscript', 'PDF/DOCX/TXT', 'research paper', 'review', 'meta-analysis', 'case report', 'bioinformatics'. Good coverage of domain-specific terms a researcher would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: Elsevier/SCI Highlights generation is a very specific academic publishing task. The combination of 'Elsevier', 'SCI', 'Highlights', and 'submission-ready' makes it extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with strong actionability and workflow clarity. It provides precise output contracts, clear validation checkpoints, and detailed type-specific guidance that Claude wouldn't inherently know. The main weakness is moderate verbosity—some sections are redundant (Supported Execution Paths largely duplicates the Workflow), and the skill could be tightened by about 20-30% without losing information.
Suggestions
Merge the 'Supported Execution Paths' section into the Workflow steps to eliminate redundancy—Path A and Path B are already covered in steps 1-2.
Consider condensing 'When to Use' and 'When Not to Use' into a single brief scope statement, as the refusal contract already handles edge cases.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity, such as the 'When to Use' and 'When Not to Use' sections that partially overlap with the workflow, and the 'Supported Execution Paths' section that is largely redundant with the workflow steps. Some sections like 'Deterministic Rules' and 'Quality Checklist' have overlap. However, most content is domain-specific and not something Claude would inherently know (e.g., character limits, coverage priorities by article type). | 2 / 3 |
Actionability | The skill provides concrete, executable commands (e.g., `python scripts/extract_text.py <file_path>`), exact output format templates, specific character limits (85 chars), precise bullet count constraints (3-5), detailed coverage priorities per article type, and copy-paste-ready refusal templates. The guidance is highly specific and leaves little ambiguity about what to produce. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced in 5 numbered steps with explicit validation at step 1 (source sufficiency check with a refusal template), error handling at step 2 (extraction failure protocol), and a thorough self-critique step 5 with specific verification criteria. The fallback/refusal contract provides a clear feedback loop for insufficient inputs, and the quality checklist serves as a final validation checkpoint. | 3 / 3 |
Progressive Disclosure | The skill references `references/prompts.md` and `scripts/extract_text.py` appropriately, suggesting content is split across files. However, no bundle files were provided to verify these references exist, and the SKILL.md itself is quite long (~150+ lines) with some content (like the 'Supported Execution Paths' section) that could be consolidated. The 'When to Use'/'When Not to Use' sections add length that could be trimmed. The structure is decent but the inline content is heavier than ideal. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
014e0b2
- Reviewed
Table of Contents
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.