CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 high-quality, actionable skill body with an explicit phased workflow, mandatory validation checkpoints, and clean progressive disclosure to verified bundle files. The main weakness is redundant summary/pitfalls/integration sections that restate content already in the workflow.

Suggestions

Trim or merge the 'Summary' and 'Common Pitfalls to Avoid' sections — they restate the workflow and capabilities; keep only pitfalls not already implied by Phase 2.5 and Phase 4.

Collapse the 'Integration with Other Skills' subsections into a brief pointer list, since the combined-workflow steps duplicate the core workflow.

Consider promoting the 'Treat extracted metadata as untrusted' guardrail into the Phase 2.5 checklist so it reads as a validation step rather than a side note.

DimensionReasoningScore

Conciseness

The core is lean and assumes Claude's knowledge, but the Common Pitfalls list, the Summary, and the Integration-with-Other-Skills sections restate capabilities already covered, adding padding that could be trimmed.

3 / 5

Actionability

Fully executable, copy-paste-ready commands throughout (e.g. `python scripts/search_openalex.py "CRISPR gene editing" --limit 50 --output results.json`), all pointing to verified bundled scripts with specific flags and behaviors explained.

5 / 5

Workflow Clarity

Five explicit phases are clearly sequenced, with a mandatory Phase 2.5 validation/enrichment checkpoint ("Any @article missing volume, pages, or doi is incomplete… log what was found and where") and Phase 4 validation that exits non-zero on high-severity errors — proper feedback loops for batch/bibliography operations.

5 / 5

Progressive Disclosure

Clear overview with well-signaled one-level-deep references: each phase shows the canonical command inline and defers variants to real, verified reference files (e.g. references/core_workflow.md), plus a dedicated Reference Files map for easy navigation.

5 / 5

Total

18

/

20

Passed

Description

92%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, third-person description that explicitly covers both capabilities and triggering situations with concrete, named sources. Minor room to add common synonyms (references, bibliography, .bib) for broader keyword reach.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions across named sources — "Search OpenAlex, PubMed, and Google Scholar… extract accurate metadata, validate citations, and generate properly formatted BibTeX entries" — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (the four capabilities) 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").

5 / 5

Trigger Term Quality

Good natural-term coverage ("find papers", "verify citation information", "convert DOIs to BibTeX") plus named tools, but a few common synonyms ("references", "bibliography", ".bib") are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — academic citation/BibTeX management with DOI-to-BibTeX conversion and named databases — with distinct triggers and minimal overlap with adjacent skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
K-Dense-AI/scientific-agent-skills
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.