https://github.com/redhuntlabs/wizard
Build AI spells for what you do - a meta-builder that turns recurring tasks into reusable workflows that any AI assistant can run.
https://github.com/redhuntlabs/wizard
ai-agents ai-skills ai-tools ai-workflow automation claude-code claude-code-plugin copilot-cli cursor cursor-plugin developer-tools gemini-cli meta-framework productivity prompt-engineering
Last synced: about 18 hours ago
JSON representation
Build AI spells for what you do - a meta-builder that turns recurring tasks into reusable workflows that any AI assistant can run.
- Host: GitHub
- URL: https://github.com/redhuntlabs/wizard
- Owner: redhuntlabs
- License: mit
- Created: 2026-04-19T13:32:40.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2026-04-24T07:19:46.000Z (about 2 months ago)
- Last Synced: 2026-05-26T23:05:13.711Z (26 days ago)
- Topics: ai-agents, ai-skills, ai-tools, ai-workflow, automation, claude-code, claude-code-plugin, copilot-cli, cursor, cursor-plugin, developer-tools, gemini-cli, meta-framework, productivity, prompt-engineering
- Language: JavaScript
- Homepage: https://github.com/redhuntlabs/wizard#readme
- Size: 1.99 MB
- Stars: 4
- Watchers: 0
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-claude-code-toolkit - Superpower Builder - builder` then `/plugin install superpower-builder@superpower-builder` | Interview-driven meta-builder that turns recurring tasks into reusable `SKILL.md` files. Routes by workflow/discipline/content/subagent kind, then pressure-tests baseline-without-skill vs. with-skill before saving. MIT, no telemetry. | (Skills / Community Skills)
- awesome-cursor-skills - Superpower Builder - Interview-driven meta-builder that turns recurring tasks into reusable `SKILL.md` files, routed by kind (workflow, discipline, content, subagent) with baseline-vs-with-skill pressure-testing on each generated skill. Ships 25 bundled superpowers covering dev (TDD, plan/execute) and non-dev (research, writing, decisions) work. Installs via Cursor plugin descriptor (`.cursor-plugin/plugin.json`). (Plugins / Utilities)
README
Build AI spells for what you do.
Your AI wizard — every task you do twice becomes a spell you can cast in any tool.
Runs in Claude Code, Cursor, Codex, Gemini, OpenCode, and Copilot CLI.
25 spells ·
12 framework skills ·
12 workflow shapes ·
6 AI tools ·
0 telemetry
Maintained by RedHunt Labs
Install ·
Quick start ·
Library ·
Commands ·
Docs
---
## What it is
Your AI assistant is good at one-off tasks. It is **much better** when you give it a recipe to follow.
At its core, Wizard is **a meta-builder** — it turns the way *you* already work into reusable spells your AI assistant can cast on demand. Around that core it ships three more things:
> **A meta-builder** that interviews you and turns your recurring tasks into your own spells, saved to a personal library. *(The main act.)*
>
> **Capture a chat that worked** — `/capture-this-chat` reads the current AI session and turns it into a draft spell in one command. Or use `/build-spell --from-transcript ` for a saved transcript from any source.
>
> **A spellbook** of 25+ ready-to-use spells — for emails, research, decisions, planning, status updates, dev workflows, and more.
>
> **A multi-tool plugin** that runs the same skills in every major AI coding tool — install once, use anywhere.
## Why it exists
| Problem | What this fixes |
|---|---|
| You re-explain the same task to the AI every time | Spells are reusable recipes the AI loads automatically |
| Prompts work in one tool, break in another | One skill format runs in 6 different AI tools |
| The AI is great at code but useless at *your* work | Spells cover research, writing, decisions, daily tasks |
| You want the AI to follow a discipline (no shipping without tests, no citing without verifying) | Discipline-kind spells enforce non-negotiable rules with hard gates |
| You hand-write the same workflow as a system prompt over and over | The meta-builder interviews you once and ships a tested spell |
## Is this for you?
| If you are... | You probably want... |
|---|---|
| **A researcher / writer / analyst** | The `research/` track — `literature-scan`, `interview-synthesis`, `verifying-before-citing`, and the `general-research-loop` chain |
| **A knowledge worker** | The `work/` track — `preparing-for-a-meeting`, `writing-a-status-update`, `responding-to-feedback` |
| **An everyday user** | The `everyday/` track — `writing-an-email`, `summarizing-a-document`, `planning-a-trip`, `troubleshooting-whats-not-working` |
| **A developer** | The `dev/` track — `brainstorming-a-feature`, `writing-an-implementation-plan`, `executing-a-plan-step-by-step`, plus the `dev-tdd-loop` chain |
| **Building a custom workflow** | The meta-builder. Type `/build-spell` and answer 5-15 minutes of questions. |
Tailored 5-minute intros: [for-non-devs.md](docs/for-non-devs.md) · [for-devs.md](docs/for-devs.md)
---
## Install
Pick the AI tool you already use. Each install is one or two commands.
> **Quickest path (Claude Code or Copilot CLI):**
> ```
> /plugin marketplace add redhuntlabs/wizard
> /plugin install wizard@wizard
> ```
> Other tools below.
Claude Code
**Recommended (one command, no clone needed):**
```
/plugin marketplace add redhuntlabs/wizard
/plugin install wizard@wizard
```
**Or install from a local clone:**
```bash
git clone https://github.com/redhuntlabs/wizard.git
```
```
/plugin install
```
The boot skill loads automatically via [hooks/hooks.json](hooks/hooks.json) on every session start.
Cursor
```bash
git clone https://github.com/redhuntlabs/wizard.git
```
In Cursor: `Settings → Plugins → Install from path` → select the cloned folder.
The descriptor lives at [.cursor-plugin/plugin.json](.cursor-plugin/plugin.json).
Codex CLI
```bash
git clone https://github.com/redhuntlabs/wizard.git ~/wizard
cd ~/wizard && npm install
```
Add to `~/.codex/AGENTS.md`:
```markdown
@~/wizard/AGENTS.md
```
Full instructions: [.codex/INSTALL.md](.codex/INSTALL.md)
Gemini CLI
```bash
gemini extensions install
```
Tool-name mapping: [GEMINI.md](GEMINI.md). Descriptor: [gemini-extension.json](gemini-extension.json).
OpenCode
In `opencode.json`:
```json
{
"plugins": ["/.opencode/plugins/wizard.js"]
}
```
Full instructions: [.opencode/INSTALL.md](.opencode/INSTALL.md)
GitHub Copilot CLI
**Recommended (one command, no clone needed):**
```bash
copilot plugin marketplace add redhuntlabs/wizard
copilot plugin install wizard@wizard
```
**Fallback (older Copilot CLI without plugin support):** clone the repo and add to your project's or home directory's `AGENTS.md`:
```markdown
@/AGENTS.md
```
Then ensure scripts are runnable: `cd && npm install`. If slash commands aren't supported in your version, ask in plain English: "build a spell for me."
---
## Your first 5 minutes
**1. Cast a bundled spell.**
```
Cast the writing-an-email spell to draft a reply to my landlord
saying I'll be 3 days late on rent because of a paycheck delay.
```
**2. Build your own.**
```
/build-spell
```
The meta-builder interviews you (5-15 minutes), drafts a SKILL.md, runs a try-it test, and saves it to `~/.wizard/`.
**3. Browse what shipped.**
```
/list-spells
```
Filter by `--kind discipline`, `--audience researcher`, or `--updates`.
---
## What's in the box
### 🌱 Everyday
For anyone, any day.
- writing-an-email
- summarizing-a-document
- planning-a-trip
- troubleshooting-whats-not-working
- asking-for-feedback
### 💼 Work
Knowledge-worker essentials.
- researching-a-company
- preparing-for-a-meeting
- writing-a-status-update
- responding-to-feedback
- wrapping-up-a-piece
- verifying-before-shipping (discipline)
### 🧠 Thinking
For making harder calls.
- making-a-decision
- breaking-down-a-problem
- learning-something-new
- decisions-need-an-alternative (discipline)
### 🔬 Research
Citation-rigorous workflows.
- literature-scan
- interview-synthesis
- structured-literature-review
- verifying-before-citing (discipline)
- researching-five-things-in-parallel (subagent)
### ⚙️ Dev
For shipping software.
- brainstorming-a-feature
- writing-an-implementation-plan
- executing-a-plan-step-by-step
### 🔗 Chains
Multi-stage, end-to-end.
- general-research-loop
- dev-tdd-loop
**25 hand-crafted spells + 12 framework skills + 12 workflow shapes** — all in [`spells/`](spells/) and [`skills/`](skills/).
---
## Slash commands
| Command | What it does |
|---|---|
| `/build-spell` | Interview-driven meta-builder. Routes to the right specialist by `kind`. Now supports `--from-transcript `. |
| `/capture-this-chat` | Turn the current chat session into a reusable spell. See [`docs/capturing-chats.md`](docs/capturing-chats.md). |
| `/cast-spell ` | Cast a specific spell on the current task |
| `/list-spells` | Browse the spellbook. Filters: `--kind`, `--audience`, `--updates` |
| `/refine-spell ` | Update an existing spell (mandatory re-test) |
| `/share-spell ` | Export. Modes: `--strict` (vanilla SKILL.md), `--bundle` (zip) |
---
## Documentation
> **Start here:** [for-non-devs.md](docs/for-non-devs.md) or [for-devs.md](docs/for-devs.md)
| Topic | Doc |
|---|---|
| Why behavioral engineering, the 1% rule, the Iron Law | [philosophy.md](docs/philosophy.md) |
| `kind`, `complexity`, `audience` — picking the right shape | [taxonomy.md](docs/taxonomy.md) |
| The SKILL.md format spec | [spell-format-spec.md](docs/spell-format-spec.md) |
| Building blocks: excuses tables, hard gates, warning signs | [skills-primitives.md](docs/skills-primitives.md) |
| `$WIZARD_HOME` — your personal library | [personal-library.md](docs/personal-library.md) |
| Semver, update discovery, customization preservation | [versioning-and-updates.md](docs/versioning-and-updates.md) |
| Three export modes | [sharing-spells.md](docs/sharing-spells.md) |
| End-to-end walkthroughs (research + dev) | [general-parity-tutorial.md](docs/general-parity-tutorial.md) |
| V1 release criteria + the self-tests | [definition-of-done.md](docs/definition-of-done.md) |
---
Project structure
```
wizard/
README.md this file
AGENTS.md core agent instructions (Codex / OpenCode / Copilot)
CLAUDE.md, GEMINI.md tool-specific entry points
CONTRIBUTING.md, LICENSE
CHANGELOG.md release notes
package.json Node project + CLI scripts
gemini-extension.json
.claude-plugin/ Claude Code plugin descriptor
.cursor-plugin/ Cursor plugin descriptor
.codex/INSTALL.md
.opencode/ OpenCode plugin (wizard.js)
hooks/ session-start bootstrap
scripts/ validate-spell / new-spell / build-loader / adversarial tests
templates/ SKILL.md templates per kind
agents/ subagent definitions (e.g. spell-tester)
commands/ slash command definitions
skills/ framework skills (meta-builder, validator, inference engine)
spells/ bundled spellbook — everyday / work / thinking / research / dev / chains
docs/ all documentation
assets/ banner + demo SVGs
```
---
## Contributing
PRs welcome — see [CONTRIBUTING.md](CONTRIBUTING.md). The bar for the bundled spellbook is high; for narrower or specialist spells, prefer publishing a community pack ([sharing-spells.md](docs/sharing-spells.md)).
Every PR runs the validator and the adversarial tests. New spells must include a worked example and a `PASS` tester verdict.
## Privacy
No telemetry. Ever. Everything runs locally inside your AI tool. Your spells live in `~/.wizard/` on your machine.
## Acknowledgements
Inspired by [obra/superpowers](https://github.com/obra/superpowers) by Jesse Vincent — the `SKILL.md` format and the Iron Law come from there.
## Attribution
Built and maintained by [RedHunt Labs](https://redhuntlabs.com/) — a CTEM and attack-surface-management team that ships open-source tooling for the security community.
## License
MIT — see [LICENSE](LICENSE).
Made for everyone who'd rather build a tool once than re-prompt forever.