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 specific figure legends.
56
63%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/meta-results-forest-plot-analyzer/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines a narrow, specialized domain (forest plot analysis for meta-analysis) with concrete actions and explicit trigger guidance. It includes domain-specific terminology that users would naturally use, and the bilingual aspect (Chinese/English) adds further distinctiveness. The 'Use when...' clause effectively communicates when Claude should select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: analyzes forest plots, generates detailed descriptions, formats figure legends, interprets statistical significance (heterogeneity, p-value), and supports Chinese or English output. | 3 / 3 |
Completeness | Clearly answers both 'what' (analyzes forest plots, generates descriptions, formats figure legends in Chinese/English) and 'when' (explicit 'Use when...' clause specifying interpret forest plot image, describe statistical significance, format figure legends). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'forest plot', 'meta-analysis', 'heterogeneity', 'p-value', 'figure legends', 'statistical significance'. These are domain-specific terms that users in this field would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining forest plots, meta-analysis, bilingual figure legends, and specific statistical metrics. Very unlikely to conflict with other skills due to the narrow domain focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 from excessive generic boilerplate that obscures the actual useful content. The core two-step workflow (Vision LLM analysis + script formatting) and the formatting rules are the only genuinely valuable parts, but they are buried among ~15 sections of template filler that add no skill-specific value. The skill would be dramatically improved by removing all generic sections and focusing on the concrete workflow, formatting rules, and examples.
Suggestions
Remove all generic boilerplate sections (When to Use, When Not to Use, Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling, Deterministic Output Rules, Completion Checklist) — these add no skill-specific value and waste tokens.
Consolidate the workflow into a single clear section with the two steps, concrete script invocation with actual CLI arguments, and an explicit validation checkpoint between the LLM analysis and formatting steps.
Provide a concrete, complete example of the Vision LLM prompt (not just guidelines) and show the exact script command with real flags, e.g., `python scripts/format_result.py --input analysis.txt --language en --figure-num 2`.
Remove circular internal references ('See ## Usage above', 'See ## Workflow above') and merge the duplicated content into a single coherent flow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Multiple sections restate the same information (e.g., 'When to Use' and 'When Not to Use' are generic boilerplate, 'Quick Validation' appears twice, 'Example Usage' references a non-existent '## Usage' section then duplicates workflow info). Generic sections like 'Failure Handling', 'Deterministic Output Rules', 'Completion Checklist', and 'Output Contract' add no skill-specific value and waste tokens on things Claude already knows. | 1 / 3 |
Actionability | The core workflow (Vision LLM analysis + script formatting) is somewhat concrete, and the example showing input/output is helpful. However, the actual script invocation lacks concrete arguments (no real CLI example with actual flags), the prompt guidelines are vague ('describe in detail >300 words'), and much of the content is generic boilerplate rather than executable, copy-paste-ready guidance. | 2 / 3 |
Workflow Clarity | The two-step workflow (Image Analysis → Output Formatting) is clearly sequenced and the example illustrates the flow. However, there are no explicit validation checkpoints between steps (e.g., verifying the LLM output meets the >300 word requirement or contains required statistical elements before passing to the formatting script), and the 'validate_skill.py' reference appears without context on what it actually checks. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with many redundant sections. References like 'See ## Usage above' and 'See ## Workflow above' point to sections within the same file creating circular references. No bundle files are provided, yet the skill references scripts like 'scripts/format_result.py' and 'scripts/validate_skill.py' without any supporting documentation. The structure is poorly organized with important content (the actual workflow in sections 'Usage' and 'Workflow') buried beneath generic boilerplate. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%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
d3c2c0f
- Reviewed
Table of Contents
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.