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

43%

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-sensitivity-analysis/SKILL.md

Quality

Content

12%

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

The body is dominated by generic template boilerplate and offers no executable guidance: its only code is commented pseudocode, it references a formatter script that is missing from the bundle, and its validation guidance is self-contradictory. The actual workflow is buried under padding rather than presented concisely.

Suggestions

Replace the commented pseudocode example with real, executable code (e.g., a working format_sensitivity_result implementation) or ship scripts/format_result.py so the documented import path actually exists.

Cut the generic boilerplate sections (Execution model, Output discipline, Validation and Safety Rules, Deterministic Output Rules, Completion Checklist) down to skill-specific guidance only, since they restate knowledge Claude already has.

Reconcile the validation guidance: pick one consistent validation step instead of pointing to 'validate_skill.py --help' and then stating no local script validation is required.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate ("Execution model", "Output discipline", "Validation and Safety Rules", "Deterministic Output Rules", "Completion Checklist") that restates concepts Claude already knows, fitting the 'verbose; explains concepts Claude knows; padded with unnecessary context' anchor rather than the tighter level 2.	1 / 3
Actionability	The only code example is commented-out pseudocode ("# description = llm.generate(...)", "# final_output = format_sensitivity_result(...)"), the referenced scripts/format_result.py does not exist in the bundle, and scripts/validate_skill.py is a stub with no real logic, matching the 'vague or abstract; no concrete code/commands; describes rather than instructs' anchor.	1 / 3
Workflow Clarity	The Workflow section lists steps (Generate Description, Format Output) but lacks concrete commands or validation checkpoints, and the 'Quick Validation' section contradicts itself (first pointing to validate_skill.py --help, then stating no local script validation is required), fitting the 'steps listed but validation gaps; checkpoints missing or implicit' anchor rather than the lower level because a sequence is present.	2 / 3
Progressive Disclosure	The skill is a monolithic single file bloated with inline boilerplate that belongs in separate references, and it cites scripts/format_result.py which is absent from the bundle, matching the 'monolithic wall of text ... poor organization' anchor rather than the structured level 2.	1 / 3
	Total	5 / 12 Passed

Description

75%

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-formed: it states a concrete purpose and includes an explicit 'Use when' trigger clause in correct third-person voice. It is slightly held back by moderate action specificity and somewhat academic trigger vocabulary rather than natural user phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("Generates the 'Results' section ... based on statistical tables and titles") but does not list multiple specific actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It states what the skill does ("Generates the 'Results' section ...") and gives an explicit when clause ("Use when the user wants to describe sensitivity analysis results or format sensitivity tables ..."), satisfying the level-3 anchor that requires both what and when with explicit triggers.	3 / 3
Trigger Term Quality	Includes relevant natural terms like 'sensitivity analysis', 'meta-analysis', and 'sensitivity tables', but the vocabulary is fairly academic and misses common user variations, fitting the 'some relevant keywords but missing common variations' anchor; voice is correctly third person.	2 / 3
Distinctiveness Conflict Risk	The niche is narrowly scoped to meta-analysis sensitivity analysis with distinct triggers unlikely to overlap with general skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.	3 / 3
	Total	10 / 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.