CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

67

Quality

84%

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

75%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 skill body: concrete executable commands in every phase, a clear sequenced workflow with validation checkpoints, and well-signaled one-level references. Its weaknesses are confined to padding — a redundant Summary, generic Integration filler, duplicated resource listings — and the absence of an explicit fix-and-re-validate loop tying the checklist asset into the workflow.

Suggestions

Delete the closing Summary section and the generic Integration bullets — they restate capabilities and add no actionable content.

Merge the 'Reference Files' and 'Bundled Resources' sections into a single complete listing so resources are described once with consistent groupings.

Close the workflow feedback loop in Phase 4: state 'fix the reported errors and re-run validate_citations.py until it passes' and link assets/citation_checklist.md as the final pre-submission checklist.

DimensionReasoningScore

Conciseness

The phase sections are lean and command-driven, but the closing Summary restates all capabilities verbatim, the Integration sections carry generic filler ('Different venues require different citation styles'), and resources are listed twice — several sections could be cut or tightened.

3 / 5

Actionability

Every phase provides copy-paste-ready invocations with real flags and arguments (e.g. 'search_openalex.py "CRISPR gene editing" --limit 50 --output results.json', 'format_bibtex.py references.bib --rekey --deduplicate'), plus install commands and documented exit behavior — fully executable coverage of the common cases.

5 / 5

Workflow Clarity

The five phases are clearly sequenced with a mandatory enrichment checkpoint before formatting and an explicit validation phase that 'exits non-zero on high-severity errors'. It falls short of the top anchor because no fix-and-re-validate feedback loop is stated in the workflow and the bundled QA checklist (assets/citation_checklist.md) is never wired into Phase 4.

4 / 5

Progressive Disclosure

Each phase shows the canonical command and points to a specific one-level-deep reference file, and all referenced files exist in the bundle. The 'Reference Files' and 'Bundled Resources' sections duplicate each other with inconsistent groupings, a minor organization gap that keeps it below the top anchor.

4 / 5

Total

16

/

20

Passed

Description

88%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 with concrete multi-action coverage and an explicit, specific use-when clause. Its only weakness is moderate trigger-term coverage — it omits 'bibliography' and '.bib' — and slight overlap risk with literature-search skills on the generic 'find papers' trigger.

DimensionReasoningScore

Specificity

Lists four concrete actions covering the full workflow — 'Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries' — with no coverage gaps, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Both what and when are explicit: the multi-action capability sentence is followed by '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' — concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'find papers', 'verify citation information', 'convert DOIs to BibTeX' are present, but common variations such as 'bibliography' and the '.bib' file extension are missing, so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The BibTeX/DOI/citation-validation niche is distinct, but 'find papers' and database searching overlap with literature-review type skills, leaving minor conflict risk with closely related skills rather than minimal.

4 / 5

Total

18

/

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.

Validation — 15 / 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

Path

skills/citation-management/SKILL.md

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.