literature-filtering

Filter literature by publication year, journal, and predefined screening rules to produce inclusion/exclusion lists; use when conducting preliminary screening or systematic review screening to narrow the literature scope.

Quality

70%

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/Evidence Insight/literature-filtering/SKILL.md

Quality

Content

65%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 content is highly actionable with a complete executable example, but it is held back by an inlined long script, redundant prose re-explaining that script, and the absence of an explicit validation feedback loop for a batch operation.

Suggestions

Move the full Python script into a scripts/ file and keep only a short excerpt inline, reducing token cost and removing redundancy with the 'Implementation Details' section.

Add an explicit validation/verification checkpoint (e.g., re-run borderline exclusions, reconcile counts against the screening log) with a fix-and-retry loop for the batch screening workflow.

Trim the 'Implementation Details' section to only what the code does not already show, or fold its key parameters into the script comments, to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body inlines a ~170-line script and the 'Implementation Details' section re-explains journal normalization, execution order, and outputs already shown in the code, so it is mostly efficient but includes redundant explanation that could be tightened.	3 / 5
Actionability	It provides a complete, copy-paste-ready Python script with a sample input CSV, covering the common screening case fully and executably.	5 / 5
Workflow Clarity	A clear filter sequence (year, journal, criteria) and a review section exist, but as a batch operation it lacks an explicit validate→fix→retry feedback loop, capping it at 3.	3 / 5
Progressive Disclosure	References to references/guide.md and assets/screening_log_template.csv are signaled one level deep, but the large runnable script is inlined in SKILL.md rather than placed in a scripts/ file, leaving organization only partly appropriate.	3 / 5
	Total	14 / 20 Passed

Description

75%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 clear, third-person description that concretely states what the skill does and when to use it with reasonable trigger terms. It is strong but stops just short of the top anchor on specificity, trigger coverage, and explicitness of the 'when' clause.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Filter literature by publication year, journal, and predefined screening rules', 'produce inclusion/exclusion lists') with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Both 'what' (filter by year/journal/rules to produce inclusion/exclusion lists) and 'when' ('use when conducting preliminary screening or systematic review screening') are explicit in third person, but the 'when' could be slightly more specific, so it sits at 4 rather than 5.	4 / 5
Trigger Term Quality	Natural terms like 'literature', 'publication year', 'journal', 'preliminary screening', and 'systematic review screening' give good coverage a user would say, though synonyms like 'bibliography' or 'abstract screening' are missing.	4 / 5
Distinctiveness Conflict Risk	The systematic-review/literature-screening niche is clearly distinct with minimal conflict risk, with only minor overlap against general research skills, matching the 'mostly distinct' anchor.	4 / 5
	Total	16 / 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/Evidence Insight/literature-filtering/SKILL.md
Commit: 63c61d3

Reviewed: 11 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.