metis

Plan consultant - validates and improves execution plans

Quality

68%

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 ./skills/metis/SKILL.md

Quality

Content

68%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 lean, well-structured, and gives a concrete review template that an instruction-only skill can act on directly. Its main weakness is workflow clarity: the review process lacks an explicit validation/feedback loop showing what happens after issues are found.

Suggestions

Add an explicit feedback loop, e.g. 'After review, return the revised plan to Prometheus for re-planning; re-validate any changed sections before approval.'

Sequence the review checklist into an ordered workflow (e.g. 1. Completeness → 2. Dependencies → 3. Resources → 4. Risks) with a checkpoint after each.

Add a short 'Definition of done' stating when Metis approves a plan versus sends it back, to make the validation gate explicit.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence with no padding of known concepts; the only trimmable part is the fully worked review-format example, which still earns its place.	4 / 5
Actionability	It provides a concrete review checklist plus a copy-paste-ready review template (Strengths/Concerns with Problem-Impact-Suggestion/Optimizations/Revised Plan), giving mostly executable guidance with minor gaps.	4 / 5
Workflow Clarity	The checklist sections and pipeline diagram give a rough sequence, but there is no explicit review-then-fix-then-revalidate feedback loop and checkpoints are only implicit, matching the score-3 anchor.	3 / 5
Progressive Disclosure	The content is self-contained with well-organized sections (Responsibilities, Review Checklist, Review Format, When Called) and no nested references; it is slightly over the 50-line simple-skill threshold so it does not reach 5.	4 / 5
	Total	15 / 20 Passed

Description

53%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 concise and states a clear purpose, but it omits any explicit 'when to use' trigger guidance and relies on fairly generic action verbs. Adding a 'Use when...' clause with natural trigger phrases would materially improve it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing, validating, or QA-checking an execution plan before it runs.'

Replace generic verbs with more concrete actions, e.g. 'reviews plans for completeness, flags missing dependencies, and re-estimates effort.'

Include natural user phrasings and synonyms ('plan review', 'sanity-check a plan', 'plan QA') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'validates and improves execution plans' names the domain (execution plans) plus two concrete actions, but the actions are generic and not comprehensive, matching the score-3 anchor.	3 / 5
Completeness	It states clearly what the skill does ('validates and improves execution plans') but provides no 'Use when...' trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	'Plan', 'execution plans', and 'consultant' provide some relevant keywords but miss common natural variations users would say (e.g. 'review plan', 'check plan', 'QA a plan'), so it sits at the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	The plan-QA niche is mostly distinct from other skills, with only minor overlap risk against general planning skills, fitting just above the score-3 anchor.	4 / 5
	Total	13 / 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: TurnaboutHero/oh-my-antigravity
Path: skills/metis/SKILL.md
Commit: f73e1ff

Reviewed: 15 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.