CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

60

Quality

76%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/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.

The body is well-structured with highly actionable query syntax and API examples, and it models progressive disclosure better than most (consult-when sections, grep patterns, loading strategy). Weaknesses are verbosity in user-interface and support sections, workflows lacking validation checkpoints for batch API operations, and reference files that are signaled but not actually present in the bundle.

Suggestions

Trim or move to reference files the My NCBI/RSS/clipboard UI features, Support Resources (reversed email, phone number), and Limitations sections — they consume context without adding executable guidance.

Add validation checkpoints to the workflows: check the ESearch result count before fetching, verify HTTP status codes and XML/JSON parse success, and include a rate-limit backoff/retry loop in the API example rather than describing it as a best practice.

Ensure the three cited reference files (references/api_reference.md, references/search_syntax.md, references/common_queries.md) actually ship with the skill, since the body's navigation depends on them.

DimensionReasoningScore

Conciseness

Core sections (query syntax, MeSH, API access, workflows) are dense and concrete, but padding is scattered throughout: the overview explains what PubMed is, sections 7/9/Support/Limitations cover My NCBI UI features, clipboard limits, a reversed support email, and a phone number — content Claude doesn't need or that belongs in reference files.

3 / 5

Actionability

Provides an executable ESearch/EFetch Python example with real URLs and parameters, copy-paste-ready query examples with field tags, endpoint names, rate limits, and the ECitMatch citation format. Minor gaps: the elink and batch-export examples are bare URL fragments rather than executable code, and no error-handling implementation is shown.

4 / 5

Workflow Clarity

Five workflows present coherent numbered sequences, but none include validation checkpoints — 'Implement rate limiting and error handling' is a final step mention, not a verify/retry loop. Batch API operations without validation cap this dimension at 3 per the rubric.

3 / 5

Progressive Disclosure

Excellent signaling: per-section 'When to consult X.md' guidance, grep patterns for discovery, one-level-deep references, and an explicit loading strategy. However, the three referenced files (api_reference.md, search_syntax.md, common_queries.md) are absent from the bundle, and sections 7, 9, Support, and Limitations inline content that belongs in those files.

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 description: concrete, multi-action 'what' plus an explicit 'Use this for...' clause and useful routing guidance away from biopython. Main gap is trigger breadth — the when-clause targets API implementation work while omitting the literature-search and systematic-review scenarios the skill substantially covers.

DimensionReasoningScore

Specificity

Names five concrete capability areas — 'Direct REST API access', 'Advanced Boolean/MeSH queries', 'E-utilities API', 'batch processing', 'citation management' — comprehensively covering the skill's actions in concrete, verb-led form.

5 / 5

Completeness

Explicitly answers both 'what' (REST access, queries, batch, citations) and 'when' ('Use this for direct HTTP/REST work or custom API implementations'), but the when-clause covers only programmatic work and omits the literature-search and systematic-review use cases that dominate the skill body.

4 / 5

Trigger Term Quality

Includes natural terms users would say ('PubMed', 'REST API', 'MeSH', 'citation management', 'biopython') but misses common variations like 'biomedical literature', 'medical articles', 'MEDLINE', 'PMID', or 'systematic review'.

4 / 5

Distinctiveness Conflict Risk

'PubMed' is a clear niche with distinct triggers, and the description even draws an explicit boundary against a sibling tool ('For Python workflows, prefer biopython (Bio.Entrez)'), minimizing conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

13

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/pubmed-database/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.