CtrlK
BlogDocsLog inGet started
Tessl Logo

mining-pubmed-literature

Searches and fetches PubMed and PMC via NCBI E-utilities (ESearch then EFetch/ESummary) to gather biomedical evidence and build text corpora. Use when the user wants citations for a condition or drug, abstracts to summarize, MeSH-based searches, or a corpus of literature to run NER over. Trigger keywords: PubMed, PMC, NCBI, E-utilities, ESearch, EFetch, ESummary, MeSH, PMID, literature search, abstracts, evidence. Pairs adjacent to OpenMed: fetched abstracts feed openmed.analyze_text for biomedical NER, and OpenMed-extracted diagnoses/drugs/genes become the search terms. E-utilities are public; an optional free API key raises rate limits from 3 to 10 requests/second.

74

Quality

91%

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

83%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.

The body is lean, assumes Claude's competence, and provides fully executable E-utilities code with concrete examples. The main gap is the batch-fetch workflow lacking an explicit validation/verification checkpoint (rate-limit/429 handling lives in Edge cases rather than the workflow steps), which caps workflow clarity per the rubric.

Suggestions

Add an explicit validation checkpoint to the Workflow steps — e.g., after ESearch verify the returned count against expectations, and after each EFetch page check for HTTP 429/errors with retry/backoff — so the batch operation has a built-in feedback loop.

Move the inline ESummary/PMC and edge-case detail into referenced files (e.g., references/advanced.md) to keep SKILL.md a concise overview and lift progressive disclosure toward 5.

Surface the NCBI-required tool= and email= parameters in the Quick start code (not only in Edge cases) so the canonical example is compliant by default.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: it assumes Claude's competence (no "what is PubMed/API" filler, no library-comparison padding) and every section — Quick start, ESummary, Workflow, Edge cases, references — earns its place.

5 / 5

Actionability

Fully executable, copy-paste-ready Python (esearch, efetch_abstracts, esummary) with real base URL, working parameters, a concrete MeSH query, and equivalent cURL — covering the common cases.

5 / 5

Workflow Clarity

The 5-step Workflow is clearly sequenced and concrete, but this is a batch fetch operation with no explicit validation/verification checkpoint (count check, 429/error retry step) embedded in the workflow; per the rubric's batch-operation cap, workflow_clarity is capped at 3.

3 / 5

Progressive Disclosure

Well-organized into clear sections with one-level external-link references and no nested file indirection, but the body (~130 lines) inlines ESummary/PMC detail and edge-case material that could be split into referenced files rather than kept in the overview.

4 / 5

Total

17

/

20

Passed

Description

100%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.

The description is exemplary: it states concrete capabilities, provides comprehensive natural trigger terms, explicitly covers both what and when, and carves out a distinct niche with clear boundary guidance. Third-person voice is used throughout with no first/second-person drift.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Searches and fetches PubMed and PMC", "ESearch then EFetch/ESummary", "gather biomedical evidence and build text corpora" — with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both "what" (searches/fetches via E-utilities to gather evidence and build corpora) and "when" ("Use when the user wants citations... abstracts to summarize, MeSH-based searches, or a corpus of literature to run NER over") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural terms including identifiers and synonyms: PubMed, PMC, NCBI, E-utilities, ESearch, EFetch, ESummary, MeSH, PMID, literature search, abstracts, evidence.

5 / 5

Distinctiveness Conflict Risk

Clear niche (PubMed/PMC published literature) with explicit boundary guidance (paired with OpenMed, distinguished from ClinicalTrials.gov in the body), giving minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
maziyarpanahi/openmed
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.