meta-baseline-generator

Generates a meta-analysis baseline characteristics section (text + table) from raw data. Supports Chinese and English. Use when the user provides baseline data and wants a formatted results section.

Quality

80%

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-baseline-generator/SKILL.md

Quality

Content

85%

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

The skill body is highly actionable with a clear sequenced workflow and well-organized, verified references, but it carries substantial templated boilerplate that competes with the genuinely useful content. Trimming the generic 'When to Use', 'Key Features', and 'Implementation Details' sections would markedly improve token efficiency.

Suggestions

Delete the templated 'When to Use' bullet list, 'Key Features', and 'Implementation Details' sections that restate the description, keeping only the Workflow, Rules, Testing Guidelines, and Error Handling.

Remove filler such as the hardcoded example path '20260316/scientific-skills/Academic Writing/meta-baseline-generator' and 'See `## Workflow` above for related details.' which add no actionable value.

Dimension	Reasoning	Score
Conciseness	The core Workflow, Rules, and Testing Guidelines are lean and useful, but templated sections — the six-bullet 'When to Use' list, 'Key Features', 'Dependencies', and 'Implementation Details' (e.g. 'Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.') — restate the description and add padding Claude does not need.	2 / 3
Actionability	It provides a copy-paste-ready Python snippet importing process_content, names the executable script path, and points to concrete prompts in references/prompts.md, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The five-step workflow is clearly sequenced with per-step inputs and outputs, and is reinforced by a Testing Guidelines checklist and an Error Handling section with report-and-fallback feedback; this generation task is non-destructive so the missing inline validate-retry loop is not penalized.	3 / 3
Progressive Disclosure	The body is an overview that signals one-level-deep, real bundle files — [references/prompts.md](references/prompts.md) and scripts/text_processor.py, both present on disk — with no nested reference chains, matching the well-signaled one-level anchor.	3 / 3
	Total	11 / 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 complete with an explicit Use-when trigger and occupies a clear, low-conflict niche, but it is only moderately specific and offers a thin set of trigger-term variations. Strengthening the action list and broadening natural keywords would lift the weaker dimensions.

Suggestions

Expand the action list to multiple concrete verbs, e.g. 'Summarizes study characteristics, formats a baseline Markdown table, and inserts the (Table 1) citation' to raise specificity.

Broaden trigger terms with natural phrasings users would actually say, such as 'baseline characteristics table', 'study characteristics summary', or 'meta-analysis results section'.

Dimension	Reasoning	Score
Specificity	Quotes 'Generates a meta-analysis baseline characteristics section (text + table) from raw data' — it names the domain and the text+table deliverable, but describes essentially one composite action rather than listing multiple distinct concrete actions like the score-3 anchor.	2 / 3
Completeness	It states what the skill does ('Generates a meta-analysis baseline characteristics section...') and gives an explicit trigger ('Use when the user provides baseline data and wants a formatted results section'), clearly answering both what and when.	3 / 3
Trigger Term Quality	Phrases 'meta-analysis baseline characteristics', 'baseline data', and 'formatted results section' are relevant, but coverage of natural user phrasings is narrow and missing common variations such as 'baseline characteristics table' or 'study characteristics summary'.	2 / 3
Distinctiveness Conflict Risk	The 'meta-analysis baseline characteristics' niche with its baseline-data trigger is clearly distinct and unlikely to fire for unrelated skills, matching the clear-niche 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.