review-idea

Interview the user relentlessly about a plan or implementation idea until reaching shared understanding, resolving each branch of the decision tree. For existing plans, refines them. For raw ideas, builds a plan from scratch. Then stress-tests the plan through a tribunal of AI personas (Skeptic, Critic, Advocate) and produces a verdict with strengths, weaknesses, risks, and action items. Use when asked to "review my plan", "review my idea", "challenge my design", "stress test this approach", "get feedback on my plan", "flesh out this idea", or /review-idea.

Quality

96%

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

Quality

Content

92%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 a well-structured orchestration protocol with a clear phase sequence, concrete agent configuration, explicit validation gates, and an unresolved-question feedback loop. Bundle content is appropriately externalized to real one-level-deep reference files, with only minor conciseness slack from repeated restatements.

Suggestions

Consolidate the repeated 'Read references/interview-guide.md' and 'the plan text produced in Phase 2' restatements to shave tokens without losing clarity.

Consider a single short header noting which references are loaded in which phase, instead of re-issuing the read instruction at the start of Phases 2, 3, and 4.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and action-oriented with no over-explanation of concepts Claude already knows, but contains minor redundancies such as repeatedly restating 'Read references/interview-guide.md' and 'the plan text produced in Phase 2 (and only that — no interview transcript)' that could be trimmed.	4 / 5
Actionability	Despite being an instruction-only orchestration skill, the guidance is copy-paste concrete: named agents ('skeptic', 'critic', 'advocate', 'jury') with subagent_type 'general-purpose', parallel spawn instructions, a SendMessage protocol, and an exact output template with table columns (Risk \| Likelihood \| Impact \| Mitigation), severity tags, and verdict classifications.	5 / 5
Workflow Clarity	Five phases are executed in strict order with explicit gating checkpoints ('Do not proceed until all 3 are complete', 'ask the user to proceed') and a clear feedback loop in Phase 4 that iterates unresolved questions until the jury has none left.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview that splits detailed protocols into three verified, one-level-deep reference files (interview-guide.md, personas.md, jury-rules.md), each clearly signaled by 'Read references/...'; navigation is easy and no nesting exceeds one level.	5 / 5
	Total	19 / 20 Passed

Description

100%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 strong across the board: it states concrete capabilities in third person, supplies a rich set of natural trigger phrases including the slash command, and explicitly pairs 'what' with 'when'. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Interview the user relentlessly', 'resolving each branch of the decision tree', 'builds a plan from scratch', 'stress-tests the plan through a tribunal of AI personas (Skeptic, Critic, Advocate)', 'produces a verdict with strengths, weaknesses, risks, and action items' — giving comprehensive coverage rather than just a couple of actions.	5 / 5
Completeness	Explicitly answers 'what' (interview, refine/build, stress-test, verdict) and 'when' via a concrete 'Use when...' clause with trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Includes many natural phrases users would actually say — 'review my plan', 'review my idea', 'challenge my design', 'stress test this approach', 'get feedback on my plan', 'flesh out this idea' — plus the /review-idea command, covering synonyms and variations comprehensively.	5 / 5
Distinctiveness Conflict Risk	The plan/idea-review niche with distinct triggers ('stress test this approach', 'challenge my design', 'flesh out this idea') is clearly delimited and unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MrToxy/claude-skills
Path: deprecated/review-idea/SKILL.md
Commit: 66c7102

Reviewed: 2 hours 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.