meta-picos-generator

Generates PI(E)COS structure (Population, Intervention, Comparator, Outcomes, Study Design) from Meta-analysis or study titles. Use when the user wants to extract these elements from a title.

Quality

58%

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/meta-picos-generator/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 actual PICOS extraction instructions are clear and actionable, but they are buried under a generic boilerplate scaffold and a contradictory, stub-based validation story that hurts conciseness and clarity. Pruning the scaffold and resolving the validation contradiction would substantially raise the body's quality.

Suggestions

Remove the generic scaffold sections (Key Features, Dependencies, Example Usage, Implementation Details, Validation Shortcut) that restate the description and teach Claude nothing new; keep only the domain-specific PICOS workflow.

Resolve the contradictory validation guidance: either delete the stub `scripts/validate_skill.py` references and keep the "no local validation step" statement, or replace the stub with a real check — do not present both.

Collapse the duplicate "Recommended Workflow" and "Usage" sections into a single sequenced workflow (Clean Title → Extract PICOS → emit JSON) with an explicit final self-check of the JSON fields.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: a large generic scaffold (When to Use, Key Features, Dependencies, Implementation Details, Validation Shortcut) pads the file with statements Claude already knows, and the validation story is contradictory — one section promotes `scripts/validate_skill.py` while "Quick Validation" says no local validation step is required.	2 / 5
Actionability	The core task guidance is concrete (Step 1 clean-title example, Step 2 field definitions with a default-to-RCT rule, and a copy-paste JSON output template), but it is diluted by non-actionable boilerplate and a stub `validate_skill.py` presented as a functional validation tool.	3 / 5
Workflow Clarity	The genuine two-step sequence (Clean Title → Extract PICOS → output JSON) is clear, but duplicate workflow sections and contradictory validation guidance (run validate_skill.py vs. no validation needed) introduce gaps and implicit checkpoints that pull it to 3.	3 / 5
Progressive Disclosure	Sections are headed and navigable and the one referenced path (`scripts/validate_skill.py`) is a real file, but the file is ~115 lines with a large generic scaffold inlined that could be removed or separated, and the only bundle file is a stub, fitting the 3 anchor.	3 / 5
	Total	11 / 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.

The description cleanly states a niche capability and includes an explicit "Use when" trigger, giving it strong completeness and distinctiveness. It is held back from the top by a single-action specificity and trigger-term coverage that omits common synonyms like "systematic review" or "PICO".

Dimension	Reasoning	Score
Specificity	It names the domain and one concrete action — "Generates PI(E)COS structure (Population, Intervention, Comparator, Outcomes, Study Design) from Meta-analysis or study titles" — but offers a single action rather than several specific actions, so it sits at the 3 anchor rather than 4.	3 / 5
Completeness	It explicitly answers both what ("Generates PI(E)COS structure ... from Meta-analysis or study titles") and when ("Use when the user wants to extract these elements from a title") with a concrete trigger phrase, matching the 5 anchor.	5 / 5
Trigger Term Quality	It includes relevant keywords ("Meta-analysis", "study titles", "extract these elements", "PI(E)COS") but misses common synonyms a user might say such as "systematic review", "PICO", or "clinical question", matching the 3 anchor of some relevant keywords missing variations.	3 / 5
Distinctiveness Conflict Risk	The PICOS-from-titles niche is highly specific with distinct triggers and minimal overlap with other skills, matching the 5 anchor for a clear niche.	5 / 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/Data Analysis/meta-picos-generator/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.