scientist-high

Advanced research - complex analysis and ML (Opus-tier)

Quality

39%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/scientist-high/SKILL.md

Quality

Discovery

14%

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 description is severely underdeveloped, functioning more as a label than a useful skill description. It lacks concrete actions, explicit trigger guidance, and sufficient specificity to help Claude distinguish it from other research or analysis skills. The '(Opus-tier)' notation suggests internal categorization but provides no value for skill selection.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Conducts multi-source literature reviews, performs statistical modeling, builds and evaluates ML pipelines, synthesizes findings into research reports'

Include an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs deep research synthesis, statistical analysis, machine learning model development, or complex multi-step analytical workflows'

Differentiate from simpler research/analysis skills by specifying the complexity threshold or unique capabilities, e.g., 'For research requiring multiple analytical methods, large dataset processing, or synthesis across 5+ sources'

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'complex analysis' and 'ML' without listing any concrete actions. It doesn't specify what the skill actually does - no verbs describing capabilities.	1 / 3
Completeness	Missing both clear 'what' (no specific actions listed) and 'when' (no 'Use when...' clause or trigger guidance). The parenthetical '(Opus-tier)' describes capability level, not usage context.	1 / 3
Trigger Term Quality	Contains some relevant keywords ('research', 'analysis', 'ML') but uses technical shorthand and lacks natural variations users might say like 'machine learning', 'data science', 'statistical analysis', or specific research tasks.	2 / 3
Distinctiveness Conflict Risk	Extremely generic terms like 'research', 'analysis', and 'ML' would conflict with many other skills. Nothing distinguishes this from basic research skills, data analysis skills, or other ML-related skills.	1 / 3
	Total	5 / 12 Passed

Implementation

64%

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

The skill provides solid, executable code examples for ML and causal analysis tasks, which is its main strength. However, it lists capabilities (ML modeling, causal inference, etc.) without providing guidance for all of them, lacks validation checkpoints in workflows, and includes some unnecessary content like the closing quote and capability list that Claude already understands.

Suggestions

Remove the 'Advanced Capabilities' bullet list - these are concepts Claude already knows; instead, show when to use each technique

Add validation checkpoints to the ML pipeline (e.g., check for class imbalance, validate train/test split, verify no data leakage)

Either provide code examples for all listed capabilities (time series, feature engineering) or remove them from the list and link to separate reference files

Remove the closing quote - it adds no actionable value

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code examples, but the capability bullet list adds little value (Claude knows what ML modeling and causal inference are), and the closing quote is unnecessary padding.	2 / 3
Actionability	Provides fully executable, copy-paste ready Python code for both ML pipeline and A/B test analysis with specific libraries, parameters, and output formatting patterns.	3 / 3
Workflow Clarity	The ML pipeline shows a clear sequence but lacks validation checkpoints - no guidance on checking for data quality issues, handling failed grid searches, or validating model assumptions before deployment.	2 / 3
Progressive Disclosure	Content is reasonably organized with clear sections, but for a 'high' tier research skill, there are no references to more detailed documentation for advanced topics like time series analysis or feature engineering mentioned in capabilities.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 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: TurnaboutHero/oh-my-antigravity
Commit: fab464f

Reviewed: 24 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.