meta-analysis

Statistical methods for combining results across multiple studies. Use when aggregating cross-study or cross-experiment results.

Quality

61%

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 ./researchclaw/skills/builtin/experiment/meta-analysis/SKILL.md

Quality

Content

56%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 is admirably lean and well-structured for a simple advisory skill, but it functions as a best-practices checklist rather than executable or workflow guidance: no concrete methods, code, formulas, or sequenced validation steps are provided.

Suggestions

Add concrete, executable guidance (formulas or a code snippet for computing pooled effect sizes / confidence intervals, and a forest-plot command) to lift actionability.

Restructure the parallel bullets into a sequenced workflow with explicit validation checkpoints (e.g., check heterogeneity, then choose fixed vs. random effects, then validate with a sensitivity analysis) to improve workflow_clarity.

Dimension	Reasoning	Score
Conciseness	Seven terse bullets with no padding and no over-explanation of concepts Claude already knows; every line earns its place.	5 / 5
Actionability	Gives high-level advisory directives ("Use forest plots", "Report effect sizes") but no executable code, commands, formulas, or concrete steps, fitting the 'minimal concrete guidance' anchor.	2 / 5
Workflow Clarity	The numbered items are parallel best-practice advisories rather than a sequenced procedure, with no validation checkpoints, matching the 'rough sequence, many gaps, validation absent' anchor.	2 / 5
Progressive Disclosure	A short (~9 line), single-file skill with a clear section header and no need for external references, satisfying the under-50-lines simple-skill exception for well-organized content.	5 / 5
	Total	14 / 20 Passed

Description

67%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 concise, third-person, and clearly answers both what the skill does and when to use it, with decent trigger terms and low conflict risk. Its main weakness is specificity: it stays high-level without naming concrete statistical methods or richer trigger synonyms.

Suggestions

Add 1-2 concrete methods to the description (e.g., 'computes pooled effect sizes and confidence intervals') to lift specificity from 3 to 4-5.

Broaden trigger terms with natural synonyms a user might say ('meta-analysis', 'pool the results', 'pooled effect size') to push trigger_term_quality to 5.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("combining results across multiple studies") but does not enumerate specific statistical methods, so it lands at the 1-2 concrete actions anchor rather than a comprehensive list.	3 / 5
Completeness	Explicitly states both what ("Statistical methods for combining results across multiple studies") and when ("Use when aggregating cross-study or cross-experiment results"), but the 'when' could be more specific with concrete user trigger phrases.	4 / 5
Trigger Term Quality	Includes natural phrases a researcher would say ("combining results", "aggregating", "cross-study", "cross-experiment") with good coverage, though common synonyms like "pooled" or "effect size" are absent.	4 / 5
Distinctiveness Conflict Risk	The cross-study aggregation framing is a clear niche with distinct triggers, with only minor overlap risk against general results-aggregation skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: aiming-lab/AutoResearchClaw
Path: researchclaw/skills/builtin/experiment/meta-analysis/SKILL.md
Commit: be4ba47

Reviewed: 5 days 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.