Turn rough dictated requests into structured prompts, critique plans with a panel of AI reviewers before committing, close sessions with handoff notes, and optionally pull second opinions from Codex or Gemini.
Advisor to a busy principal. Optimizes for the user's time, attention, and decision quality. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.
Surfaces what's missing that a domain expert would expect. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.
Works backward from failure to surface the top 3 causes a plan could fail. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.
Finds wishful thinking in plans, drafts, and decisions. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.
Dispatch a small panel of critic agents in parallel on a plan, draft, or decision, then synthesize their raw critiques in a separate fresh-context pass. Use when the user asks for a council, a panel of critics, or a multi-angle review.
Close out a work session: write a short HANDOFF.md snapshot so the next session picks up where this one left off. Run at the end of any substantive session.
Smoke-test skill for the starter kit. Confirms the plugin installed and skills load. Use when the user runs /kit-hello or asks to verify the starter kit installation.
One-time starter-kit setup: detects optional AI engines (Codex, Gemini), confirms each with you, writes the engines config, and optionally personalizes how Claude writes for you. Safe to re-run anytime.
Turn a rough request into a clear, structured prompt, show it, then run it. Use when your request is rough, dictated, or messy, when one real ask is buried in a long brain dump, or when you want to refine or improve an existing prompt (refine mode returns the improved prompt without running it).
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A professor's guide to building AI workflows — from chatbots to self-improving systems.
Website: claudeblattman.com
A free, open-source resource for non-developers who want to build real AI workflows. Three paths:
No coding background required. Everything is built with markdown and AI tools.
New to the desktop agent apps? Start with the Desktop Agent Starter Kit:
Install Claude Code, then sign in.
In Claude Code, add and install the starter plugin:
/plugin marketplace add chrisblattman/claudeblattman
/plugin install starter-kit@claudeblattman
After your first Claude Code handoff, optionally install the Codex starter pack:
git clone https://github.com/chrisblattman/claudeblattman.git
cd claudeblattman/codex-starter
python3 install-codex-starter.py install
Then follow Start Here: Desktop Agent Starter Kit.
The older skills/ library remains available as advanced/reference material,
but it is not the recommended first-run path.
claudeblattman/
├── docs/ # Website source (MkDocs Material)
├── plugins/starter-kit/ # Claude plugin for the desktop-agent starter kit
├── codex-starter/ # Codex starter pack installer + skills
├── skills/ # Downloadable skill files
├── agents/ # Downloadable agent files
├── templates/ # Starter templates (CLAUDE.md, goals.yaml)
├── mkdocs.yml # Site configuration
├── CONTRIBUTING.md # Maintenance guide
└── LICENSE # MIT
See CONTRIBUTING.md for how to edit content, add skills, and maintain the site.
The starter kit is versioned separately from the broader docs. Each public
starter-kit release should have a matching tag such as starter-kit-v0.1.0 and
a current public-manifest.json. If a plugin release needs rollback, install
from the last known-good tag and avoid changing the marketplace/plugin names.
MIT — use anything here however you want.
Built by Chris Blattman. The name is a joke. The tools are real.
npx claudepluginhub chrisblattman/claudeblattman --plugin starter-kitAgentic engineering done right — 57 structured workflows, 17 specialist agent personas, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.
Agentic workflow mechanics: CLAUDE.md instruction quality and structured context handoff
Opinionated workflow guides and best practices - the preacher's proven patterns for Claude Code projects
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows