review-plan

Name: review-plan
Author: chrisblattman

Review a proposed plan with a single-pass structured critique and a clear verdict. Use when the user asks to review a plan, stress-test a plan, critique a workflow, identify risks, or improve an execu

by chrisblattman(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from chrisblattman/claudeblattman (codex-starter/skills/review-plan/SKILL.md). Install upstream with npx skills add chrisblattman/claudeblattman --skill review-plan. Copyright stays with the author.

Review Plan

Review Priorities

Focus on whether the plan will work in practice:

Objective clarity and success criteria.
Missing dependencies, permissions, sources, or stakeholders.
Sequencing risks and irreversible actions.
Scope creep, maintenance cost, and simpler alternatives.
Verification, rollback, and handoff.

Workflow

Restate the plan and its intended outcome.
Identify the highest-risk assumptions.
Separate blocking issues from improvements.
Recommend a revised sequence.
Call out what not to do.
End with a verdict: proceed, revise first, or rethink.

Output Shape

Plan under review:
Blocking issues:
Important improvements:
Revised sequence:
What not to do:
Verdict:

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

chrisblattman-claudeblattman-review-plan.ocm.jsonjson

{
  "ocm": "1",
  "id": "chrisblattman-claudeblattman-review-plan",
  "kind": "skill",
  "name": "review-plan",
  "description": "Review a proposed plan with a single-pass structured critique and a clear verdict. Use when the user asks to review a plan, stress-test a plan, critique a workflow, identify risks, or improve an execution sequence.",
  "publisher": "chrisblattman",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Review a proposed plan with a single-pass structured critique and a clear verdict. Use when the user asks to review a plan, stress-test a plan, critique a workflow, identify risks, or improve an execution sequence."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/chrisblattman/claudeblattman",
      "path": "codex-starter/skills/review-plan/SKILL.md",
      "ref": "12e14d42d5c8af6383019ac27ef91e898e812fc2",
      "url": "https://github.com/chrisblattman/claudeblattman/blob/12e14d42d5c8af6383019ac27ef91e898e812fc2/codex-starter/skills/review-plan/SKILL.md",
      "key": "chrisblattman/claudeblattman/codex-starter/skills/review-plan/SKILL.md"
    }
  },
  "instructions": "# Review Plan\n\n## Review Priorities\n\nFocus on whether the plan will work in practice:\n\n1. Objective clarity and success criteria.\n2. Missing dependencies, permissions, sources, or stakeholders.\n3. Sequencing risks and irreversible actions.\n4. Scope creep, maintenance cost, and simpler alternatives.\n5. Verification, rollback, and handoff.\n\n## Workflow\n\n1. Restate the plan and its intended outcome.\n2. Identify the highest-risk assumptions.\n3. Separate blocking issues from improvements.\n4. Recommend a revised sequence.\n5. Call out what not to do.\n6. End with a verdict: proceed, revise first, or r",
  "cost": {
    "context_tokens": 185
  }
}

Fetch it by URL: GET /api/v1/registry/chrisblattman-claudeblattman-review-plan/manifest?version=1.0.0