citation-management

Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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 well-structured, highly actionable multi-phase skill with excellent progressive disclosure and concrete commands throughout. The main improvements are trimming the redundant closing Summary/Resources recap and making the validation feedback loop explicit.

Suggestions

Add an explicit validate→fix→re-validate loop in Phase 4 (e.g. 'If validation exits non-zero, fix the flagged entries and re-run until it passes') to reach the workflow-clarity anchor 5.

Remove or merge the 'Summary' section and the duplicate reference listing under 'Resources' with the 'Reference Files' section to tighten token efficiency.

Consider folding the 'Integration with Other Skills' section into a brief pointer, since much of it restates capabilities already covered in the phases.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — canonical commands, the mandatory Phase 2.5 enrichment rule, and the shell-injection security warning all earn their tokens — but the trailing 'Summary' recap and the 'Resources' section re-list reference files already enumerated under 'Reference Files', which could be trimmed. Not 5 because of this redundancy; not 3 because the bulk is tight and adds genuine, non-obvious value.	4 / 5
Actionability	Fully executable, copy-paste-ready commands with real flags throughout (e.g. `python scripts/search_openalex.py "CRISPR gene editing" --limit 50 --output results.json`, `python scripts/doi_to_bibtex.py 10.1038/s41586-021-03819-2`) covering all five phases — matches the anchor for comprehensive executable examples.	5 / 5
Workflow Clarity	Five clearly sequenced phases with a mandatory Phase 2.5 enrichment step and a Phase 4 validation step that 'exits non-zero on high-severity errors', plus a QA checklist asset — but the explicit validate→fix→re-validate feedback loop is only implied rather than spelled out as a loop, so it sits just below the anchor-5 bar that requires explicit feedback loops.	4 / 5
Progressive Disclosure	SKILL.md is a clean overview with well-signaled, one-level-deep markdown links to real reference files (all 10 references, 8 scripts, and 2 assets verified present), keeping canonical commands inline while offloading variants and detail to references — matches the clear-overview anchor.	5 / 5
	Total	18 / 20 Passed

Description

87%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 description that clearly states capabilities and explicit use-when triggers with concrete, natural phrasing. The only weakness is second-person voice in the trigger clause, which costs it a specificity point.

Suggestions

Rewrite the trigger clause in third person to match the voice rule: e.g. 'Use when finding papers, verifying citation information, converting DOIs to BibTeX, or ensuring reference accuracy in scientific writing.'

Add a common synonym or file extension (e.g. '.bib', 'BibTeX files', 'bibliography') to round out natural trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries') with named databases — comprehensive coverage that would score 5, but the second-person 'when you need to find papers' trigger clause violates the third-person-voice rule, reducing specificity by 1 per the judging guidelines.	4 / 5
Completeness	Explicitly answers both 'what' (comprehensive citation management: search, extract, validate, generate BibTeX) and 'when' ('This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('find papers, verify citation information, convert DOIs to BibTeX, ensure reference accuracy in scientific writing') plus named sources, but missing common synonyms and file extensions like '.bib', so it falls just below the comprehensive-synonym anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche — academic citation management with named databases (OpenAlex, PubMed, Google Scholar) and BibTeX output — giving distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	18 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/citation-management/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.