CtrlK
BlogDocsLog inGet started
Tessl Logo

pubmed-database

Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/pubmed-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 reference-dense, highly actionable skill body with excellent progressive disclosure and executable examples. Its weak spots are mild verbosity/redundancy and batch workflows that lack explicit validation checkpoints.

Suggestions

Add explicit validation feedback loops to the programmatic workflows (e.g., check HTTP status and retry with backoff, verify PMID count before EFetch), so batch operations clear the workflow_clarity cap.

Remove the duplicate reference-file descriptions in "Working with Reference Files" or consolidate them with the earlier "When to consult" callouts to reduce redundancy.

Trim the generic PubMed background in the Overview, since Claude already knows what PubMed is.

DimensionReasoningScore

Conciseness

Mostly efficient operational detail (field tags, endpoints, rate limits, code), but the generic Overview background, the duplicate "Working with Reference Files" descriptions of files already introduced via "When to consult" sections, and the somewhat high-level workflow prose could be tightened.

3 / 5

Actionability

Provides copy-paste-ready Python E-utilities code, concrete query examples with real field tags, exact endpoint URLs, and grep patterns — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Five numbered workflows give clear sequences, but batch/API operations lack explicit validate-then-proceed feedback loops; error handling and rate limiting are mentioned only implicitly, capping batch-operation workflows at 3 per the rubric.

3 / 5

Progressive Disclosure

Three real one-level-deep reference files (api_reference.md, search_syntax.md, common_queries.md) are clearly signaled via inline "When to consult" guidance and grep patterns, with content appropriately split for easy navigation.

5 / 5

Total

16

/

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, specific description that names concrete capabilities and includes explicit trigger guidance plus a useful biopython boundary. The main gap is a narrow "when" clause that omits the biomedical literature-search use cases.

Suggestions

Broaden the "Use this for..." clause to include natural triggers like searching biomedical literature, MEDLINE, or conducting systematic reviews, not only HTTP/REST work.

Add a common synonym (e.g., MEDLINE or NCBI Entrez) so users who phrase the request differently still surface this skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Direct REST API access", "Advanced Boolean/MeSH queries", "E-utilities API", "batch processing", "citation management" — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Both "what" (the listed capabilities) and "when" ("Use this for direct HTTP/REST work or custom API implementations") are present and explicit, but the "when" clause is fairly narrow and does not surface the biomedical-search / literature-review use cases.

4 / 5

Trigger Term Quality

Good natural keyword coverage ("PubMed", "REST API", "E-utilities API", "MeSH") that practitioners would say, but missing common synonyms like MEDLINE, biomedical literature, or NCBI.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (direct HTTP/REST access to PubMed) and explicitly disambiguates from biopython ("For Python workflows, prefer biopython (Bio.Entrez)"), minimizing conflict risk.

5 / 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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-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.