meta-screening-fulltext

Screen full-text papers against inclusion/exclusion criteria, with optional PubMed metadata check using PMID. Use when the user needs to evaluate a paper for a meta-analysis.

Quality

60%

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/Data Analysis/meta-screening-fulltext/SKILL.md

Quality

Content

42%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 contains a genuinely useful Workflow and Quality Rules core, but it is buried under generic templated boilerplate and references helper scripts and prompt files that are not present in the bundle. The PDF-extraction helper is left unfinished, and the workflow lacks an explicit output-validation checkpoint.

Suggestions

Remove the generic templated sections ('When to Use' bullets, 'Key Features', 'Implementation Details') that restate packaged-skill boilerplate, and keep only the description, Workflow, Quality Rules, and Error Handling.

Complete the 'Helper Scripts / PDF Text Extraction' section with an actual command for extract_pdf.py, or drop the section if PDF handling is out of scope.

Add an explicit validation step in the Workflow (e.g. 'Verify the output is parseable JSON with Result set to Include/Exclude') before returning the result, and either ship the referenced scripts/screening_prompts.md files or stop referencing them.

Dimension	Reasoning	Score
Conciseness	Large templated boilerplate sections ('When to Use' with five generic bullets, 'Key Features', 'Implementation Details') restate packaged-skill platitudes Claude already knows, fitting 'noticeably verbose; several unnecessary explanations or padded sections' rather than 'mostly efficient'.	2 / 5
Actionability	Concrete commands and a defined JSON output schema are present ('python scripts/query_pubmed.py "<input_pmid>"', Result/Reason, standard exclusion categories), but the PDF extraction helper section is left empty after a colon and referenced scripts do not exist, leaving key details incomplete.	3 / 5
Workflow Clarity	The four-step Workflow with Scenario A/B branches is clearly sequenced, but it lacks an explicit validation checkpoint (e.g. confirming the output is parseable JSON) and the per-paper screening of a meta-analysis set is a batch-style operation, which caps clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Sections are organized, but referenced bundle files (references/screening_prompts.md, scripts/extract_pdf.py, scripts/query_pubmed.py) do not exist and are signaled only as inline code paths rather than navigable links, fitting 'references present but not clearly signaled'.	3 / 5
	Total	11 / 20 Passed

Description

78%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 strong: it cleanly states both the capability and a concrete trigger condition in third person, with good domain keywords and a distinct meta-analysis screening niche. Its only weakness is that the capability list stops at two actions rather than enumerating the full screening workflow.

Dimension	Reasoning	Score
Specificity	Names the domain (full-text papers, inclusion/exclusion criteria, PubMed/PMID) with two concrete actions—screening against criteria and an optional PubMed metadata check—but coverage is not comprehensive, matching the '1-2 concrete actions' anchor rather than 'several specific actions'.	3 / 5
Completeness	It explicitly answers both what ('Screen full-text papers against inclusion/exclusion criteria, with optional PubMed metadata check using PMID') and when ('Use when the user needs to evaluate a paper for a meta-analysis') with a concrete 'Use when' trigger phrase, matching the top anchor.	5 / 5
Trigger Term Quality	Good coverage of natural terms a user would say ('meta-analysis', 'evaluate a paper', 'inclusion/exclusion criteria', 'PMID', 'PubMed'), though a few common synonyms (e.g. 'systematic review') are missing, fitting 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	The PMID + inclusion/exclusion + meta-analysis niche is mostly distinct with clear triggers, but it could overlap with adjacent systematic-review or medical-screening skills, fitting 'mostly distinct; minor overlap risk' rather than 'minimal conflict risk'.	4 / 5
	Total	16 / 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: 9 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/meta-screening-fulltext/SKILL.md
Commit: f5ef65b

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.