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.

61

Quality

72%

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 ./scientific-skills/Evidence Insight/pubmed-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 thorough, well-structured skill body with concrete code and query examples and clearly signaled reference files. It is held back by verbosity and by workflows that omit explicit validation feedback loops for batch operations.

Suggestions

Tighten the body by moving the MeSH subheading glossary, publication-type list, and NLM overview into the reference files, keeping only the field-tag syntax and a few canonical examples inline.

Add explicit validation checkpoints to the programmatic workflows (e.g., check HTTP status and rate-limit headers after each E-utilities call, retry with backoff on 429, verify retmax/uid count before EFetch) so batch operations include a validate→fix→retry loop.

Replace placeholder "YOUR_API_KEY" with a concrete env-var pattern (e.g., os.environ.get('NCBI_API_KEY')) and show a minimal rate-limit/backoff helper so the API examples are copy-paste runnable.

DimensionReasoningScore

Conciseness

The body is long and inlines material Claude partly already knows (the NLM overview, MeSH subheading glossary, publication-type list) plus overlaps with the reference files, though much of the field-tag and API syntax detail genuinely earns its place.

3 / 5

Actionability

Provides executable Python (ESearch/EFetch), concrete query examples with real field tags, and grep patterns for discovery; minor gaps such as placeholder "YOUR_API_KEY" and partial batch examples keep it just below fully copy-paste ready.

4 / 5

Workflow Clarity

Five workflows are sequenced, but batch/destructive operations (EPost batch, history server) lack explicit validate→fix→retry checkpoints, so per the rubric cap workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

Three real reference files are well signaled via "When to consult X.md" sections and grep patterns at one level deep, but the body still inlines substantial detail (API endpoint list, MeSH subheadings) that overlaps those references.

4 / 5

Total

14

/

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 a clear PubMed niche with an explicit "Use this for" trigger. The main weakness is the trigger guidance being narrowly technical rather than phrased around natural user needs.

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

Answers both "what" (the five capabilities) and "when" ("Use this for direct HTTP/REST work or custom API implementations"), but the "when" is narrow and technical rather than user-need oriented.

4 / 5

Trigger Term Quality

Includes the dominant natural term "PubMed" plus "REST API" and "biopython", but lacks common user phrasings like "search PubMed" or "find articles" and offers few synonyms.

4 / 5

Distinctiveness Conflict Risk

Targets a clear PubMed-specific niche and explicitly redirects Python workflows to biopython, minimizing overlap with adjacent skills.

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-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.