meta-results-sensitivity-analysis

Generates the "Results" section for meta-analysis sensitivity analysis based on statistical tables and titles. Use when the user wants to describe sensitivity analysis results or format sensitivity tables for a meta-analysis paper.

Quality

65%

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/Academic Writing/meta-results-sensitivity-analysis/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 body is over-padded with generic meta-process boilerplate and its core worked example is non-executable pseudocode referencing a missing script, while validation guidance contradicts itself. Section structure exists but cross-references are broken and one referenced bundle file is absent.

Suggestions

Replace the commented-out pseudocode example with executable code, or implement and ship the referenced scripts/format_result.py so the import actually resolves.

Remove the generic boilerplate sections ('Execution model', 'Output discipline', 'Deterministic Output Rules', 'Completion Checklist') that restate what Claude already knows, keeping only task-specific guidance.

Fix the contradictory validation guidance and the broken 'See ## Usage above' / 'See ## Workflow above' pointers, which currently reference sections that appear later in the file.

Dimension	Reasoning	Score
Conciseness	The body is padded with many generic process sections Claude already knows ('Execution model: validate the request...', 'Output discipline: keep results reproducible...', 'Deterministic Output Rules', 'Completion Checklist'), making it noticeably verbose beyond a few unnecessary explanations (3).	2 / 5
Actionability	The core example is entirely commented-out pseudocode ('# description = llm.generate(...)', '# final_output = format_sensitivity_result(...)') that imports a non-existent scripts/format_result.py, so guidance is concrete but incomplete rather than executable (4) or entirely vague (2).	3 / 5
Workflow Clarity	A clear 2-step sequence exists ('1. Generate Description... 2. Format Output...') but validation checkpoints are implicit and contradictory (one section says run validate_skill.py --help, another says 'No local script validation step is required'), missing explicit checkpoints for a 4.	3 / 5
Progressive Disclosure	Section headers give some structure, but navigation is unreliable: 'See ## Usage above' and 'See ## Workflow above' point to sections that appear below, and the example references scripts/format_result.py which is not in the bundle, leaving references present but not clearly signaled.	3 / 5
	Total	11 / 20 Passed

Description

87%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 well-crafted: it concisely states a concrete purpose and provides an explicit 'Use when' trigger clause with natural keywords. It carves out a clear, low-conflict niche. Minor gains would come from adding synonyms like 'Leave-One-Out' to the trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Generates the Results section', 'describe sensitivity analysis results', 'format sensitivity tables'), with only minor coverage gaps, matching the 'several specific actions' anchor above the 1-2 action midpoint.	4 / 5
Completeness	It clearly states what it does ('Generates the Results section for meta-analysis sensitivity analysis based on statistical tables and titles') and explicitly when to use it ('Use when the user wants to describe sensitivity analysis results or format sensitivity tables for a meta-analysis paper'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	'sensitivity analysis results', 'sensitivity tables', 'meta-analysis paper' are natural terms a user would say, giving good keyword coverage, but synonyms like 'Leave-One-Out' are missing so it is not comprehensive (5).	4 / 5
Distinctiveness Conflict Risk	The sensitivity-analysis-within-meta-analysis niche is specific with distinct triggers, giving minimal conflict risk with other skills; it is not merely broad like the lower anchors.	5 / 5
	Total	18 / 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/Academic Writing/meta-results-sensitivity-analysis/SKILL.md
Commit: 63c61d3

Reviewed: 13 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.