Skill
ask-agents
Send a task or question to Claude Code and/or Gemini as external subagents and report back what they said. Use when the user asks…
@chrisblattmanInstall SkillEducation
Skill
/review-plan
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.
Install
$ npx -y skills add chrisblattman/claudeblattman --skill review-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/review-plan
Context preview
The summary Claude sees to decide when to auto-load this skill.
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.
SKILL.md
review-plan.SKILL.mdname: 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.
Review Plan
Review Priorities
Focus on whether the plan will work in practice:
1. Objective clarity and success criteria. 2. Missing dependencies, permissions, sources, or stakeholders. 3. Sequencing risks and irreversible actions. 4. Scope creep, maintenance cost, and simpler alternatives. 5. Verification, rollback, and handoff.
Workflow
1. Restate the plan and its intended outcome. 2. Identify the highest-risk assumptions. 3. Separate blocking issues from improvements. 4. Recommend a revised sequence. 5. Call out what not to do. 6. 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:
Ships withclaudeblattman
A professor's guide to building AI workflows — from chatbots to self-improving systems. Website: claudeblattman.com
Get the whole plugin
Stats
464
Stars
79
Forks
Active
Maintenance
JavaScript
Language
MIT
License
9d ago
Last commit
7mo ago
Created
3h ago
Added
Other skills on claudeblattman.
@chrisblattmanInstall SkillSkill
done
Wrap up the current session by writing a short HANDOFF.md in the project folder, so the next session can resume quickly. Use when…
@chrisblattmanInstall SkillSkill
prompt
Turn a rough, dictated, or ambiguous request into a clear, structured task, then carry it out. Use when a request is…
@chrisblattmanInstall SkillSkill
council
Dispatch a small panel of critic agents in parallel on a plan, draft, or decision, then synthesize their raw critiques in a…
@chrisblattmanInstall SkillSkill
kit-hello
Smoke-test skill for the starter kit. Confirms the plugin installed and skills load. Use when the user runs /kit-hello or asks to…
@chrisblattmanInstall SkillSkill
kit-setup
One-time starter-kit setup: detects optional AI engines (Codex, Gemini), confirms each with you, writes the engines config, and…
@chrisblattmanInstall Skill