Name: citation-management
Rating: 68.8 (1 reviews)
Author: K-Dense-AI

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

84%

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

The canonical home for this skill is citation-management in K-Dense-AI/scientific-agent-skills

Quality

Content

85%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-engineered skill body: canonical executable commands per phase, explicit ordering and validation checkpoints, and a clean one-level-deep reference structure that was verified against the actual bundle. The one real weakness is redundancy — the Summary and Bundled Resources sections restate content already covered, and the Integration sections read as filler.

Suggestions

Delete or compress the Summary section; it restates the Overview and the phase list almost verbatim.

Drop the "Bundled Resources" subsection and fold any non-duplicate details (assets, external URLs) into the existing Reference Files section to eliminate the double listing.

Replace the generic prose in the three Integration subsections with a single short list of the concrete hand-off commands (e.g. the literature-review and pyzotero export paths already documented in example_workflows.md).

Dimension	Reasoning	Score
Conciseness	The core workflow phases are lean and command-dense, but the Summary section restates the Overview in seven bullets, "Bundled Resources" duplicates the "Reference Files" listing, and the three Integration sections are generic prose that adds little, fitting 'mostly efficient but could be tightened' rather than the noticeably-padded anchor 2, since no space is spent explaining concepts Claude already knows.	3 / 5
Actionability	Every phase gives copy-paste-ready commands covering the common cases (e.g. "python scripts/search_openalex.py \"CRISPR gene editing\" --limit 50 --output results.json", "format_bibtex.py references.bib --output clean.bib --rekey --deduplicate", "validate_citations.py references.bib --venue nature"), and all referenced scripts exist in the bundle, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Five phases are explicitly sequenced with ordering constraints ("Run this after extraction and before formatting"), a dedicated validation phase documents that the script "exits non-zero on high-severity errors", and the pitfalls section supplies per-failure fixes, matching the anchor for clear sequencing with explicit validation and error-recovery feedback loops.	5 / 5
Progressive Disclosure	The body is a well-signaled overview with one-level-deep references: each phase links its detail file ("every variant, option, and metadata-source detail is in references/core_workflow.md"), a Reference Files section indexes all ten reference files with one-line descriptions, and every referenced path in references/, scripts/, and assets/ exists on disk, matching the top anchor for easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

83%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 pairs a concrete multi-action capability statement with an explicit use-when clause and natural trigger phrases. Its main weaknesses are the second-person voice in the trigger clause (which the rubric penalizes) and missing common synonyms like "bibliography" or ".bib" that users would naturally say.

Suggestions

Rewrite the trigger clause in third person to avoid the second-person penalty, e.g. "Use when finding papers, verifying citation information, converting DOIs to BibTeX, or ensuring reference accuracy in scientific writing."

Add natural synonyms users would say, such as "bibliography", ".bib files", or "citation style", to broaden trigger coverage.

Narrow the generic "find papers" trigger toward citation-specific contexts (e.g. "building or verifying a bibliography") to reduce overlap with a literature-review skill.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions with named systems ("Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries"), matching the comprehensive anchor, but the second-person trigger clause "when you need to find papers" triggers the rubric's explicit voice penalty, reducing it by one point.	4 / 5
Completeness	It clearly answers both what ("Search... extract accurate metadata, validate citations, and generate properly formatted BibTeX entries") and when ("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") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural user phrases are present ("find papers", "verify citation information", "convert DOIs to BibTeX", "reference accuracy", "BibTeX"), but common variations users would say such as "bibliography", ".bib", or "citation style" are missing, fitting the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive one.	4 / 5
Distinctiveness Conflict Risk	"Citation management", "BibTeX", "DOI", and the named databases carve a mostly distinct niche, but "find papers" and "verify citation information" could also plausibly trigger a literature-review skill, so it fits the 'minor overlap risk with closely related skills' anchor rather than minimal-conflict anchor 5.	4 / 5
	Total	17 / 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/claude-scientific-writer
Path: .claude/skills/citation-management/SKILL.md
Commit: 529b9f7

Reviewed: 12 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.