meta-results-forest-plot-analyzer

Analyzes forest plots for meta-analysis, generating detailed descriptions and formatting figure legends in Chinese or English. Use when the user wants to interpret a forest plot image, describe its statistical significance (heterogeneity, p-value), and format the output with s...

Quality

58%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/meta-results-forest-plot-analyzer/SKILL.md

Quality

Content

35%

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

The skill has a genuine two-step workflow and real bundled scripts, but the body is buried under generic boilerplate and the documented script usage does not match the actual CLI. It is actionable in places yet verbose and partly misleading.

Suggestions

Strip the generic template sections (When to Use, Key Features, Validation/Safety/Failure/Completion Checklist boilerplate) that restate what Claude already knows, leaving only forest-plot-specific guidance.

Correct the execution instructions: document the script's real positional CLI (python scripts/format_result.py <text> <language>) instead of the non-existent CONFIG block and --help/--check validation claims.

Tighten the vision-LLM step into a concrete, copy-paste-ready prompt template with the required fields (I², P-value, effect sizes, study/sample counts) rather than vague '>300 words' direction.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic template boilerplate ('Use this skill when the request matches its documented task boundary', 'Structured execution path designed to keep outputs consistent and reviewable') and restates obvious process hygiene Claude already knows, matching the verbose score-1 anchor.	1 / 3
Actionability	Concrete elements exist — the format_result.py invocation, citation/header/footer formatting rules, and a worked example — but the vision-LLM step is only vaguely instructed ('Describe the forest plot in detail >300 words') with no executable call, and wiring script inputs is unspecified.	2 / 3
Workflow Clarity	A two-step sequence (Image Analysis then Output Formatting) is present, but the documented validation checkpoints are misleading — the script's real CLI takes positional <text> <language> args yet the body tells users to run --help/--check and edit a non-existent 'CONFIG block', with no real feedback loop.	2 / 3
Progressive Disclosure	The two bundled scripts are real and one-level-deep, and sections are organized, but the ~170-line body is largely a monolithic wall of generic sections (Validation, Safety, Failure, Completion Checklist) that read as inline filler rather than a lean overview pointing to detail files.	2 / 3
	Total	7 / 12 Passed

Description

82%

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 specific, well-triggered description in third person with a clear niche, undermined only by its truncated 'Use when...' clause. It names concrete capabilities and natural trigger terms effectively.

Suggestions

Restore the full, untruncated 'Use when...' clause so the when-trigger is complete rather than cut off at '...format the output with s...'.

Add the common phrasing variations a user might say (e.g. 'forest plot', 'meta-analysis figure', 'pooled effect size') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyzes forest plots for meta-analysis, generating detailed descriptions and formatting figure legends', 'interpret a forest plot image, describe its statistical significance (heterogeneity, p-value)' — matching the score-3 anchor for several specific concrete actions.	3 / 3
Completeness	Both the 'what' and an explicit 'Use when...' trigger are present, but the description is truncated mid-sentence ('...format the output with s...'), leaving the when-clause incomplete, so it cannot reach the clearly-complete level 3.	2 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'forest plot', 'meta-analysis', 'statistical significance', 'heterogeneity', 'p-value', all phrased the way a user would actually request this skill.	3 / 3
Distinctiveness Conflict Risk	The forest-plot-for-meta-analysis niche with its specific statistical triggers is clearly distinct and unlikely to fire for unrelated skills; voice is third person ('Analyzes'), so no specificity penalty applies.	3 / 3
	Total	11 / 12 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
Commit: 7cc5680

Reviewed: 3 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.