meta-analysis-methods-generator

Generates the Methods section for a meta-analysis paper, including search strategy, screening, quality assessment, data extraction, and statistical analysis.

Quality

47%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/meta-analysis-methods-generator/SKILL.md

Quality

Content

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill suffers heavily from template bloat — roughly 60% of the content is generic boilerplate that applies to any skill and wastes tokens. The core value lies in the well-structured prompt templates for the six meta-analysis subsections and the clear IO contract, but this is buried under redundant sections. The skill also has a confusing identity crisis between being a script-execution skill (referencing validate_skill.py) and a prompt-chaining skill (the actual useful content).

Suggestions

Remove all generic boilerplate sections (When to Use, When Not to Use, Required Inputs, Failure Handling, Completion Checklist, Deterministic Output Rules, Validation and Safety Rules, Quick Validation, Output Contract, Recommended Workflow) — these add no skill-specific value and waste tokens.

Remove all references to scripts/validate_skill.py since no bundle exists and the actual skill is prompt-based text generation, not script execution.

Consolidate into a lean structure: IO Contract → Workflow (single version) → Prompt Templates → Quality Rules. This would cut the content by ~60% while preserving all actionable information.

Add a concrete end-to-end example showing sample PICOS input and a snippet of expected output to make the skill more actionable.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and padded with boilerplate sections that add no value. Sections like 'When to Use', 'When Not to Use', 'Required Inputs', 'Failure Handling', 'Completion Checklist', and 'Deterministic Output Rules' are generic filler that Claude already knows. The skill repeats itself across 'Workflow', 'Recommended Workflow', 'Example Usage', and 'Implementation Details'. Much of the content is template boilerplate not specific to meta-analysis methods generation.	1 / 3
Actionability	The prompts/templates section provides concrete prompt content for each subsection (Search Strategy, Literature Screening, etc.) with specific outlines and instructions, which is genuinely useful. However, the references to `scripts/validate_skill.py` are misleading since no bundle files exist, the IO contract is somewhat clear but the execution path is confused between script-based and prompt-based approaches, and there's no executable code for the actual task.	2 / 3
Workflow Clarity	The Workflow section provides a clear 4-step sequence (Input Validation → Context Retrieval → 6 Execution Steps → Compilation) with specific inputs for each step. However, there are no validation checkpoints between steps, no feedback loops for error recovery, and the relationship between the script-based workflow in 'Example Usage' and the prompt-based workflow in 'Workflow' is contradictory and confusing.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with no external file references that actually exist. The 'Implementation Details' section says 'See ## Workflow above' which is a self-referential non-reference. All prompt templates are inlined (which could be appropriate) but the massive amount of boilerplate sections makes navigation difficult. Multiple sections repeat the same information (three different workflow descriptions, two validation sections).	1 / 3
	Total	6 / 12 Passed

Description

67%

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 in specificity and distinctiveness, clearly enumerating the concrete sub-tasks involved in writing a meta-analysis Methods section. Its main weaknesses are the absence of an explicit 'Use when...' clause and missing some natural trigger terms users might employ (e.g., 'systematic review', 'PRISMA'). Adding trigger guidance would significantly improve Claude's ability to select this skill at the right time.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for help writing or drafting the Methods section of a meta-analysis or systematic review paper.'

Include additional natural trigger terms like 'systematic review', 'PRISMA', 'literature review methodology', and 'meta-analysis write-up' to improve matching against common user phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: search strategy, screening, quality assessment, data extraction, and statistical analysis. These are well-defined sub-tasks within the meta-analysis Methods section.	3 / 3
Completeness	Clearly answers 'what does this do' (generates the Methods section with specific components), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes relevant terms like 'meta-analysis', 'Methods section', 'search strategy', 'screening', and 'statistical analysis', but misses common user variations like 'systematic review', 'PRISMA', 'literature review methods', or 'meta-analysis paper writing'.	2 / 3
Distinctiveness Conflict Risk	Highly specific niche: generating the Methods section specifically for a meta-analysis paper. This is unlikely to conflict with general writing skills, other academic writing skills, or statistical analysis skills due to its precise scope.	3 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: aipoch/medical-research-skills
Commit: d915031

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.