find-paper-references

Automatically find references for academic paper Markdown files. Reads full paper text, identifies each knowledge point requiring citation (epidemiological data, mechanism descriptions, existing research conclusions, etc.), searches PubMed for 3-5 most relevant articles per kn...

Quality

83%

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

81%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.

A highly actionable, well-sequenced workflow with strong validation feedback loops for a batch operation. The main weakness is conciseness: the API-key guidance and the EndNote/Zotero handoff are each stated multiple times and could be deduplicated.

Suggestions

Consolidate the NCBI API Key guidance: keep it in one place (the dedicated section) and have Step 0 reference it, rather than repeating the full instructions in both locations.

State the EndNote/Zotero handoff once (Step 8) and have the Skill Boundary box and 'Next Step' section point to it, instead of re-describing the same downstream skills three times.

Consider moving the dense article-type citation-zone rules and target-count formulas into a short reference file, keeping SKILL.md as the orchestration overview.

Dimension	Reasoning	Score
Conciseness	The bulk is domain-specific and tight, but the NCBI API key is explained twice (Step 0 and a dedicated 'NCBI API Key (Optional)' section) and the EndNote/Zotero handoff is restated three times (Skill Boundary box, Step 8, and the 'Next Step' section), which could be consolidated.	3 / 5
Actionability	Fully executable: a copy-paste bash invocation ('python "SKILL_DIR/scripts/batch_search.py" "%TEMP%\ref_queries.json" --max 5'), a concrete JSON query schema with examples, specific file-naming rules (paper.md → paper_refs.md), and a before/after PMID-insertion example covering common cases.	5 / 5
Workflow Clarity	Steps 0-8 are clearly sequenced with explicit validation and feedback loops: PMID-count checks against the ≥30 (Research) and word-count target range (Review) thresholds that return to Step 2, plus empty-result re-search — satisfying the batch-operation validation requirement.	5 / 5
Progressive Disclosure	A clear Tools section lists the three scripts one level deep with paths referenced in the workflow, and navigation is easy via numbered steps; minor gaps are the dense inline article-type citation rules and the duplicated API-key/handoff sections that could be externalized or consolidated.	4 / 5
	Total	17 / 20 Passed

Description

86%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 strong, specific description that names the domain and concrete actions and provides an explicit 'Use when' trigger. Its only gap is trigger-term breadth: adding synonyms (cite, bibliography, literature) and the .md extension would make matching more robust.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions ('Reads full paper text', 'identifies each knowledge point requiring citation', 'searches PubMed for 3-5 most relevant articles', 'inserts [PMID:XXXXXXXX] markers') with comprehensive workflow coverage matching the anchor-5 example.	5 / 5
Completeness	Explicitly answers both 'what' (full read-identify-search-insert action chain) and 'when' ('Use when an academic paper Markdown file needs citations added') with concrete trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Good natural-term coverage (citation, references, academic paper, PubMed, PMID) plus an explicit trigger ('Use when an academic paper Markdown file needs citations added'), but missing common synonyms like 'cite', 'bibliography', 'literature search' and explicit file extensions.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (academic-paper PubMed citation finding) with distinct triggers and minimal overlap risk versus generic document or reference skills.	5 / 5
	Total	19 / 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: scientific-skills/Academic Writing/find-paper-references/SKILL.md
Commit: 63c61d3

Reviewed: 7 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.