metis

Plan consultant - validates and improves execution plans

Quality

37%

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/metis/SKILL.md

Quality

Discovery

17%

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 too brief and vague to effectively guide skill selection. It lacks explicit trigger conditions, uses jargon users wouldn't naturally say, and doesn't clarify what types of 'execution plans' it handles or what validation/improvement actually involves.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'review my plan', 'check my approach', 'improve my strategy', or 'validate my steps'

Specify what types of execution plans this handles (e.g., project plans, task sequences, implementation strategies) and what validation/improvement actions are performed

Include concrete examples of when this skill should trigger versus other planning-related skills to reduce conflict risk

Dimension	Reasoning	Score
Specificity	Names the domain ('execution plans') and two actions ('validates' and 'improves'), but lacks comprehensive detail about what validation or improvement entails or what types of plans are covered.	2 / 3
Completeness	Provides a weak 'what' (validates and improves plans) but completely lacks any 'when' clause or explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Uses technical jargon ('execution plans', 'consultant') that users are unlikely to naturally say. Missing common variations like 'review my plan', 'check my approach', 'planning help', or 'strategy review'.	1 / 3
Distinctiveness Conflict Risk	'Execution plans' is somewhat specific but could overlap with project planning, code execution plans, database query plans, or general strategy skills. The term 'consultant' adds little distinctiveness.	2 / 3
	Total	6 / 12 Passed

Implementation

57%

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

This skill provides a reasonable framework for plan validation with good structural organization and a useful review template. However, it leans toward describing a role rather than providing actionable validation procedures, and lacks concrete validation steps or executable guidance for actually checking plan quality.

Suggestions

Replace the persona framing with direct instructions - remove 'You are Metis' and the closing quote to save tokens

Add concrete validation procedures: specific checks to perform (e.g., 'verify each task has an owner', 'check total estimates against deadline') rather than abstract checklist items

Include a feedback loop: what happens after review? How does Claude verify the revised plan addresses concerns before proceeding to execution?

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient but includes some unnecessary elements like the persona framing ('You are Metis'), the closing quote, and explanatory context about when it's called that Claude could infer from the system design.	2 / 3
Actionability	Provides a concrete review format template and checklist, but lacks executable code or specific commands. The guidance is more of a framework than copy-paste ready instructions - the example shows structure but not how to actually perform validation steps.	2 / 3
Workflow Clarity	The review checklist provides clear categories but lacks explicit sequencing or validation checkpoints. There's no feedback loop for what happens after concerns are raised or how to verify the revised plan addresses issues.	2 / 3
Progressive Disclosure	For a skill of this size (~70 lines), the content is well-organized with clear sections (Responsibilities, Review Checklist, Review Format, When Called). No external references needed and structure is easy to navigate.	3 / 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.