Evaluates project proposals against evidence-based criteria to ensure design and plan quality.

Install

mkdir -p .claude/skills/proposal-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13809" && unzip -o skill.zip -d .claude/skills/proposal-review && rm skill.zip

Installs to .claude/skills/proposal-review

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Review proposals, plans, and technical approaches for correctness, missing assumptions, risk, and decision quality. Use for design reviews, plan critiques, and proposal stress tests.
182 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Identify claims made in a proposal
  • Uncover unstated assumptions
  • Find supporting or contradicting code, config, or docs
  • Identify missing risks
  • Suggest alternative considerations
  • Determine required owner decisions

How it works

The skill reviews proposals by checking claims, assumptions, supporting evidence, risks, and alternatives. It outputs a decision memo, preferring blocker, risk, or optimization framing.

Inputs & outputs

You give it
Target proposal or plan
You get back
Decision memo based on `.claude/rules/template-decision-memo.md`

When to use proposal-review

  • Design review
  • Critiquing technical approach
  • Proposal stress testing

About this skill

<!-- GTKB-ANTIGRAVITY-SKILL-ADAPTER Generated: true Generated by: scripts/generate_antigravity_skill_adapters.py Canonical source: .claude/skills/proposal-review/SKILL.md Canonical source sha256: 62231bdfb6aaa649c139d5d26e16f385494e877c4861a56da33eea8b12c8a90e Generated at: 2026-05-19T15:33:26Z Do not edit this adapter directly. Edit the canonical source and regenerate. GTKB-ANTIGRAVITY-SKILL-ADAPTER -->

Proposal Review

Review the target proposal or plan with an evidence-first, decision-support posture.

Default Deliverable

Use .claude/rules/template-decision-memo.md unless the owner asks for a different format.

Required Review Pass

Always check:

  1. what claim the proposal is making
  2. what assumptions are unstated
  3. what code/config/docs support or contradict it
  4. what risks are missing
  5. what alternatives should be considered
  6. what exact owner decision is required

Output Rules

  • Be concrete, not generic.
  • Prefer blocker/risk/optimization framing.
  • If the proposal is sound, say so explicitly and note residual risks or verification gaps.
  • If the proposal is weak, recommend the smallest stronger alternative.

Evidence Sources

Prefer:

  • code/config/docs in the repo
  • Knowledge Database facts where relevant
  • prior CODEX-INSIGHT-DROPBOX/ findings for repeated issues

© 2026 Remaker Digital, a DBA of VanDusen & Palmeter, LLC. All rights reserved.

When not to use it

  • When a different output format is requested by the owner
  • When the task is not a review of a proposal, plan, or technical approach

Limitations

  • The skill requires codebase documentation as an evidence source
  • The skill prefers specific evidence sources like code, config, docs, Knowledge Database facts, and prior findings
  • The skill does not generate new code or designs

How it compares

This skill provides a structured review pass and output rules for concrete, evidence-first decision support, which differs from an unstructured or generic review process.

Compared to similar skills

proposal-review side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
proposal-review (this skill)02moNo flagsIntermediate
confidence-check134moReviewBeginner
specification-architect139moReviewAdvanced
drift-analysis25moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

confidence-check

SuperClaude-Org

Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.

13114

specification-architect

adrianpuiu

A rigorous, traceability-first system that generates five interconnected architectural documents (blueprint.md, requirements.md, design.md, tasks.md, and validation.md) with complete requirements-to-implementation traceability. Use this skill when users need to architect systems, create technical specifications, or develop structured project documentation with guaranteed traceability.

1388

drift-analysis

avifenesh

This skill should be used when the user asks about "plan drift", "reality check", "comparing docs to code", "project state analysis", "roadmap alignment", "implementation gaps", or needs guidance on identifying discrepancies between documented plans and actual implementation state.

213

flow-next-plan-review

gmickel

Carmack-level plan review via RepoPrompt or Codex. Use when reviewing Flow epic specs or design docs. Triggers on /flow-next:plan-review.

11

rfc-check

meta-pytorch

Determine if proposed changes require an RFC. Use when planning significant changes, before starting major work, or when asked whether an RFC is needed.

11

feature-planning

mhattingpete

Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.

10

Search skills

Search the agent skills registry