baseline-extraction-for-clinical-trials

Extracts clinical trial baseline data (study, region, participants, etc.) from article text or PMID. Checks PubMed for metadata; always falls back to LLM extraction for full details.

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/baseline-extraction-for-clinical-trials/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 has a clear, well-sequenced hybrid workflow and correctly signals its real reference file, but it is weighed down by templated boilerplate and undermined by a core Step 1 that references a script (baseline_extractor.py) and a CONFIG block that are not present in the bundle. Tightening the filler and fixing the broken references would materially improve it.

Suggestions

Remove the templated boilerplate in 'When to Use', 'Key Features', and 'Implementation Details' that does not add skill-specific value; keep only the concrete workflow and schema/script references.

Fix Step 1: either ship scripts/baseline_extractor.py (the PubMed lookup script the workflow depends on) or rewrite the step to use the actual bundled files.

Delete the 'Edit the in-file CONFIG block' instruction in the run plan — extract_pdf.py has no CONFIG block.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the 'When to Use', 'Key Features', and 'Implementation Details' sections are largely templated boilerplate (e.g. 'when a data analytics task needs a packaged method instead of ad-hoc freeform output', 'Execution model: validate the request, choose the packaged workflow') that restates the description and adds generic process advice Claude already knows.	2 / 5
Actionability	Step 1 provides concrete subprocess code, but it invokes scripts/baseline_extractor.py which does not exist in the bundle (only extract_pdf.py is present), and the run plan tells the user to edit an in-file CONFIG block that is absent from extract_pdf.py — so the core guidance is not actually executable as written.	3 / 5
Workflow Clarity	The two-step workflow is clearly sequenced with an explicit decision checkpoint (on status 'success' stop, else proceed to LLM fallback), matching the anchor for a clear sequence with most checkpoints present; only minor validation gaps (no error-retry guidance).	4 / 5
Progressive Disclosure	Good structure with a real one-level-deep reference (references/extraction_schema.md, clearly signaled in Step 2) and a real helper script (extract_pdf.py); the main gap is the dead reference to the missing baseline_extractor.py.	4 / 5
	Total	13 / 20 Passed

Description

66%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 conveys what the skill does via a concrete hybrid PubMed + LLM workflow, but it omits any explicit "Use when..." trigger guidance, which limits its discoverability and completeness. It is third-person and specific, with only minor gaps in trigger synonyms.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when extracting baseline characteristics (Table 1) from a clinical trial article given a PMID or full text.'

Include common synonyms users would actually say — 'RCT', 'baseline characteristics', 'Table 1' — alongside 'clinical trial baseline data'.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "Extracts clinical trial baseline data (study, region, participants, etc.)", "Checks PubMed for metadata", "always falls back to LLM extraction" — covering the hybrid workflow with only minor gaps from the "etc." abbreviation.	4 / 5
Completeness	The "what" is clearly stated but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Good coverage of natural domain terms a researcher would say ("clinical trial baseline data", "PMID", "PubMed", "article text"), but misses common synonyms like "RCT", "baseline characteristics", or "Table 1".	4 / 5
Distinctiveness Conflict Risk	The clinical-trial baseline extraction niche with PMID/PubMed triggers is mostly distinct, with only minor overlap risk against broader medical-literature skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/baseline-extraction-for-clinical-trials/SKILL.md
Commit: f5ef65b

Reviewed: ~23 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.