search-pubmed

An intelligent tool for precision medical literature search using PubMed's E-utilities API.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/search-pubmed/SKILL.md

Quality

Content

52%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 a sequenced, validated workflow and a real bundled script, but it is padded with generic boilerplate and lacks a concrete PubMed query example with real output. It reads more like a reusable template than PubMed-specific guidance.

Suggestions

Trim the generic boilerplate sections (Execution model, Output discipline, Implementation Details) that restate validation/deliverable ideas already covered in Workflow, Validation, and Failure Handling.

Add a concrete usage example with a real PubMed query and its JSON output (e.g., `python scripts/search_pubmed.py "diabetes metformin"` -> {"total": N, "text": ...}) to make the skill copy-paste actionable.

Document PubMed-specific guidance Claude would not infer: how to build effective search terms, E-utilities parameter usage, and retmax behavior, replacing the templated 'Parameters to clarify first' list.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several padded generic/templated sections ('Execution model', 'Output discipline', 'Implementation Details') that restate the same validate-then-deliver idea without adding PubMed-specific knowledge Claude lacks, matching the 'noticeably verbose; several unnecessary explanations or padded sections' anchor.	2 / 5
Actionability	Concrete commands are present (py_compile, --help, running the script) but there is no real example query, no shown API parameters or constructed search term, and the expected output block is templated rather than demonstrated, fitting 'some concrete guidance but incomplete; missing key details'.	3 / 5
Workflow Clarity	The Recommended Workflow is a clear 4-step sequence with validation at both ends (validate request in step 1, final validation pass in step 4) plus dedicated Validation and Failure Handling sections, matching 'clear sequence with most checkpoints present' though the steps remain generic rather than PubMed-specific.	4 / 5
Progressive Disclosure	Content is well-sectioned with one-level-deep references to the bundled scripts/search_pubmed.py (no nested reference chains; references/ and assets/ are empty), matching 'good structure; references mostly clear; minor organization gaps'.	4 / 5
	Total	13 / 20 Passed

Description

53%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 clearly communicates what the skill does around PubMed search but omits any 'Use when' trigger guidance and lacks synonym coverage, leaving it mid-band across most dimensions. It is distinct as a niche but generic in phrasing ('intelligent tool').

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when searching PubMed/MEDLINE for systematic reviews, meta-analyses, or evidence-based research').

Replace 'intelligent tool' buzzword with a concrete action list and include synonyms (MEDLINE, biomedical literature, abstracts) to lift trigger-term and specificity scores.

Mirror the body's richer phrasing ('systematic reviews, meta-analyses, evidence-based research, return total counts') into the frontmatter description so it answers both what and when.

Dimension	Reasoning	Score
Specificity	It names a well-specified domain ('precision medical literature search using PubMed's E-utilities API') and one concrete action ('search'), but the 'intelligent tool' phrasing is buzzword padding and only a single action is listed, matching the anchor that names a domain plus 1-2 actions without comprehensive coverage.	3 / 5
Completeness	It has a clear 'what' (precision medical literature search via PubMed E-utilities) but no 'Use when...' or equivalent trigger clause, so per the guidelines completeness is capped at 3 with 'when' missing.	3 / 5
Trigger Term Quality	'PubMed' and 'medical literature search' are natural terms a user would say, but common synonyms/variations (MEDLINE, biomedical, abstracts, systematic review) are absent, fitting the anchor for some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	PubMed medical literature search is a clear niche with distinct triggers and minimal conflict risk beyond minor overlap with general literature-search skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/search-pubmed/SKILL.md
Commit: 63c61d3

Reviewed: 4 hours ago

Table of Contents

Discovery Implementation Validation

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.