outcome-extraction-for-clinical-trials

Clinical research outcome extraction for meta-analysis. Use when users need to extract outcome measures (binary, continuous, or survival data) from clinical research papers for systematic review and meta-analysis. Handles both database lookup by PMID and real-time LLM extraction.

Quality

71%

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/outcome-extraction-for-clinical-trials/SKILL.md

Quality

Content

50%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 delivers concrete, actionable extraction guidance with a clear workflow and output schema, but is padded with duplicated description text and generic boilerplate, lacks a validation checkpoint, and signals its reference file with a typo'd path. Tightening the redundant sections and fixing the reference path would materially improve it.

Suggestions

Remove the verbatim repetition of the frontmatter description in the "When to Use" and "Key Features" sections, and delete the generic "Implementation Details" boilerplate in favor of skill-specific guidance.

Add an explicit validation/verification step to the workflow (e.g., confirm extracted JSON is well-formed and that group sample sizes and event counts reconcile) before final output, creating a validate → fix → retry loop.

Fix the reference path typo from "extraction-promots.md" to "extraction-prompts.md" and surface it as a clean inline link ("See references/extraction-prompts.md for detailed JSON structures") rather than an emoji-buried line.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the "When to Use" and "Key Features" sections repeat the frontmatter description verbatim, and "Implementation Details" is generic boilerplate ("validate the request, choose the packaged workflow, and produce a bounded deliverable") that adds no skill-specific value.	2 / 5
Actionability	Provides concrete commands ("python scripts/extract_pdf.py --help"), exact per-type field lists (n, event, mean, sd, HR, 95% CI), and a full JSON output schema, with only minor gaps in showing the extraction logic itself.	4 / 5
Workflow Clarity	A clear five-step sequence is present, but it lacks any validation or verification checkpoint for the batch multi-outcome extraction, which the rubric caps at 3 for batch operations without feedback loops.	3 / 5
Progressive Disclosure	A real one-level-deep reference bundle exists, but the signaled path is typo'd ("extraction-promots.md" vs the actual extraction-prompts.md) and buried under emoji markup, so navigation is broken and the reference is not cleanly signaled.	3 / 5
	Total	12 / 20 Passed

Description

92%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 specific, complete, and clearly distinct, explicitly covering what it does and when to use it with concrete trigger phrases. Its only weakness is slightly incomplete synonym coverage for trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "extract outcome measures (binary, continuous, or survival data)", "database lookup by PMID", and "real-time LLM extraction" — with comprehensive coverage of the extraction workflow.	5 / 5
Completeness	Explicitly answers both what ("outcome extraction... database lookup by PMID and real-time LLM extraction") and when ("Use when users need to extract outcome measures... for systematic review and meta-analysis") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms ("clinical research papers", "outcome measures", "systematic review and meta-analysis", "PMID") but missing common synonyms a user might say, such as RCT, trial data, or hazard ratio.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear clinical-meta-analysis niche with PMID lookup and binary/continuous/survival classification triggers, giving it minimal overlap with other skills.	5 / 5
	Total	19 / 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/Data Analysis/outcome-extraction-for-clinical-trials/SKILL.md
Commit: f5ef65b

Reviewed: ~5 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.