{
  "markdown": "<p align=\"center\">\n  <img src=\"assets/hero-banner.svg\" alt=\"Wizard\" width=\"100%\">\n</p>\n\n<h3 align=\"center\">Build AI spells for what you do.</h3>\n\n<p align=\"center\">\n  Your AI wizard — every task you do twice becomes a spell you can cast in any tool. <br/>\n  Runs in <strong>Claude Code</strong>, <strong>Cursor</strong>, <strong>Codex</strong>, <strong>Gemini</strong>, <strong>OpenCode</strong>, and <strong>Copilot CLI</strong>.\n</p>\n\n<p align=\"center\">\n  <a href=\"LICENSE\"><img alt=\"License: MIT\" src=\"https://img.shields.io/badge/license-MIT-9d7bff.svg?style=flat-square\"></a>\n  <img alt=\"Node 18+\" src=\"https://img.shields.io/badge/node-%3E=18-7afcff.svg?style=flat-square\">\n  <img alt=\"Spells bundled\" src=\"https://img.shields.io/badge/spells-37%20bundled-ff7ad9.svg?style=flat-square\"\n       title=\"25 spells + 12 framework skills\">\n  <img alt=\"Status: V1\" src=\"https://img.shields.io/badge/status-v1.0.0-28c840.svg?style=flat-square\">\n  <img alt=\"No telemetry\" src=\"https://img.shields.io/badge/telemetry-none-1a1b26.svg?style=flat-square\">\n</p>\n\n<p align=\"center\">\n  <sub>\n    <b>25</b> spells &nbsp;·&nbsp;\n    <b>12</b> framework skills &nbsp;·&nbsp;\n    <b>12</b> workflow shapes &nbsp;·&nbsp;\n    <b>6</b> AI tools &nbsp;·&nbsp;\n    <b>0</b> telemetry\n  </sub>\n</p>\n\n<p align=\"center\">\n  <sub>\n    Maintained by <a href=\"https://redhuntlabs.com/\"><b>RedHunt Labs</b></a>\n  </sub>\n</p>\n\n<p align=\"center\">\n  <img src=\"assets/demo.svg\" alt=\"Demo: building a spell in under a minute\" width=\"100%\">\n</p>\n\n<p align=\"center\">\n  <a href=\"#install\">Install</a> &nbsp;·&nbsp;\n  <a href=\"#your-first-5-minutes\">Quick start</a> &nbsp;·&nbsp;\n  <a href=\"#whats-in-the-box\">Library</a> &nbsp;·&nbsp;\n  <a href=\"#slash-commands\">Commands</a> &nbsp;·&nbsp;\n  <a href=\"#documentation\">Docs</a>\n</p>\n\n---\n\n## What it is\n\nYour AI assistant is good at one-off tasks. It is **much better** when you give it a recipe to follow.\n\nAt 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:\n\n> **A meta-builder** that interviews you and turns your recurring tasks into your own spells, saved to a personal library. *(The main act.)*\n>\n> **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 <path>` for a saved transcript from any source.\n>\n> **A spellbook** of 25+ ready-to-use spells — for emails, research, decisions, planning, status updates, dev workflows, and more.\n>\n> **A multi-tool plugin** that runs the same skills in every major AI coding tool — install once, use anywhere.\n\n## Why it exists\n\n| Problem | What this fixes |\n|---|---|\n| You re-explain the same task to the AI every time | Spells are reusable recipes the AI loads automatically |\n| Prompts work in one tool, break in another | One skill format runs in 6 different AI tools |\n| The AI is great at code but useless at *your* work | Spells cover research, writing, decisions, daily tasks |\n| 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 |\n| You hand-write the same workflow as a system prompt over and over | The meta-builder interviews you once and ships a tested spell |\n\n## Is this for you?\n\n| If you are... | You probably want... |\n|---|---|\n| **A researcher / writer / analyst** | The `research/` track — `literature-scan`, `interview-synthesis`, `verifying-before-citing`, and the `general-research-loop` chain |\n| **A knowledge worker** | The `work/` track — `preparing-for-a-meeting`, `writing-a-status-update`, `responding-to-feedback` |\n| **An everyday user** | The `everyday/` track — `writing-an-email`, `summarizing-a-document`, `planning-a-trip`, `troubleshooting-whats-not-working` |\n| **A developer** | The `dev/` track — `brainstorming-a-feature`, `writing-an-implementation-plan`, `executing-a-plan-step-by-step`, plus the `dev-tdd-loop` chain |\n| **Building a custom workflow** | The meta-builder. Type `/build-spell` and answer 5-15 minutes of questions. |\n\nTailored 5-minute intros: [for-non-devs.md](docs/for-non-devs.md) · [for-devs.md](docs/for-devs.md)\n\n---\n\n## Install\n\nPick the AI tool you already use. Each install is one or two commands.\n\n> **Quickest path (Claude Code or Copilot CLI):**\n> ```\n> /plugin marketplace add redhuntlabs/wizard\n> /plugin install wizard@wizard\n> ```\n> Other tools below.\n\n<details>\n<summary><b>Claude Code</b></summary>\n\n**Recommended (one command, no clone needed):**\n\n```\n/plugin marketplace add redhuntlabs/wizard\n/plugin install wizard@wizard\n```\n\n**Or install from a local clone:**\n\n```bash\ngit clone https://github.com/redhuntlabs/wizard.git\n```\n\n```\n/plugin install <path-to-cloned-repo>\n```\n\nThe boot skill loads automatically via [hooks/hooks.json](hooks/hooks.json) on every session start.\n</details>\n\n<details>\n<summary><b>Cursor</b></summary>\n\n```bash\ngit clone https://github.com/redhuntlabs/wizard.git\n```\n\nIn Cursor: `Settings → Plugins → Install from path` → select the cloned folder.\n\nThe descriptor lives at [.cursor-plugin/plugin.json](.cursor-plugin/plugin.json).\n</details>\n\n<details>\n<summary><b>Codex CLI</b></summary>\n\n```bash\ngit clone https://github.com/redhuntlabs/wizard.git ~/wizard\ncd ~/wizard && npm install\n```\n\nAdd to `~/.codex/AGENTS.md`:\n\n```markdown\n@~/wizard/AGENTS.md\n```\n\nFull instructions: [.codex/INSTALL.md](.codex/INSTALL.md)\n</details>\n\n<details>\n<summary><b>Gemini CLI</b></summary>\n\n```bash\ngemini extensions install <path-to-cloned-repo>\n```\n\nTool-name mapping: [GEMINI.md](GEMINI.md). Descriptor: [gemini-extension.json](gemini-extension.json).\n</details>\n\n<details>\n<summary><b>OpenCode</b></summary>\n\nIn `opencode.json`:\n\n```json\n{\n  \"plugins\": [\"<path-to-cloned-repo>/.opencode/plugins/wizard.js\"]\n}\n```\n\nFull instructions: [.opencode/INSTALL.md](.opencode/INSTALL.md)\n</details>\n\n<details>\n<summary><b>GitHub Copilot CLI</b></summary>\n\n**Recommended (one command, no clone needed):**\n\n```bash\ncopilot plugin marketplace add redhuntlabs/wizard\ncopilot plugin install wizard@wizard\n```\n\n**Fallback (older Copilot CLI without plugin support):** clone the repo and add to your project's or home directory's `AGENTS.md`:\n\n```markdown\n@<path-to-cloned-repo>/AGENTS.md\n```\n\nThen ensure scripts are runnable: `cd <path-to-cloned-repo> && npm install`. If slash commands aren't supported in your version, ask in plain English: \"build a spell for me.\"\n</details>\n\n---\n\n## Your first 5 minutes\n\n**1. Cast a bundled spell.**\n\n```\nCast the writing-an-email spell to draft a reply to my landlord\nsaying I'll be 3 days late on rent because of a paycheck delay.\n```\n\n**2. Build your own.**\n\n```\n/build-spell\n```\n\nThe meta-builder interviews you (5-15 minutes), drafts a SKILL.md, runs a try-it test, and saves it to `~/.wizard/`.\n\n**3. Browse what shipped.**\n\n```\n/list-spells\n```\n\nFilter by `--kind discipline`, `--audience researcher`, or `--updates`.\n\n---\n\n## What's in the box\n\n<table>\n<tr>\n<td valign=\"top\" width=\"33%\">\n\n### 🌱 Everyday\n\n<sub>For anyone, any day.</sub>\n\n- writing-an-email\n- summarizing-a-document\n- planning-a-trip\n- troubleshooting-whats-not-working\n- asking-for-feedback\n\n</td>\n<td valign=\"top\" width=\"33%\">\n\n### 💼 Work\n\n<sub>Knowledge-worker essentials.</sub>\n\n- researching-a-company\n- preparing-for-a-meeting\n- writing-a-status-update\n- responding-to-feedback\n- wrapping-up-a-piece\n- verifying-before-shipping <em>(discipline)</em>\n\n</td>\n<td valign=\"top\" width=\"33%\">\n\n### 🧠 Thinking\n\n<sub>For making harder calls.</sub>\n\n- making-a-decision\n- breaking-down-a-problem\n- learning-something-new\n- decisions-need-an-alternative <em>(discipline)</em>\n\n</td>\n</tr>\n<tr>\n<td valign=\"top\">\n\n### 🔬 Research\n\n<sub>Citation-rigorous workflows.</sub>\n\n- literature-scan\n- interview-synthesis\n- structured-literature-review\n- verifying-before-citing <em>(discipline)</em>\n- researching-five-things-in-parallel <em>(subagent)</em>\n\n</td>\n<td valign=\"top\">\n\n### ⚙️ Dev\n\n<sub>For shipping software.</sub>\n\n- brainstorming-a-feature\n- writing-an-implementation-plan\n- executing-a-plan-step-by-step\n\n</td>\n<td valign=\"top\">\n\n### 🔗 Chains\n\n<sub>Multi-stage, end-to-end.</sub>\n\n- general-research-loop\n- dev-tdd-loop\n\n</td>\n</tr>\n</table>\n\n**25 hand-crafted spells + 12 framework skills + 12 workflow shapes** — all in [`spells/`](spells/) and [`skills/`](skills/).\n\n---\n\n## Slash commands\n\n| Command | What it does |\n|---|---|\n| `/build-spell` | Interview-driven meta-builder. Routes to the right specialist by `kind`. Now supports `--from-transcript <path>`. |\n| `/capture-this-chat` | Turn the current chat session into a reusable spell. See [`docs/capturing-chats.md`](docs/capturing-chats.md). |\n| `/cast-spell <name>` | Cast a specific spell on the current task |\n| `/list-spells` | Browse the spellbook. Filters: `--kind`, `--audience`, `--updates` |\n| `/refine-spell <name>` | Update an existing spell (mandatory re-test) |\n| `/share-spell <name>` | Export. Modes: `--strict` (vanilla SKILL.md), `--bundle` (zip) |\n\n---\n\n## Documentation\n\n> **Start here:** [for-non-devs.md](docs/for-non-devs.md) or [for-devs.md](docs/for-devs.md)\n\n| Topic | Doc |\n|---|---|\n| Why behavioral engineering, the 1% rule, the Iron Law | [philosophy.md](docs/philosophy.md) |\n| `kind`, `complexity`, `audience` — picking the right shape | [taxonomy.md](docs/taxonomy.md) |\n| The SKILL.md format spec | [spell-format-spec.md](docs/spell-format-spec.md) |\n| Building blocks: excuses tables, hard gates, warning signs | [skills-primitives.md](docs/skills-primitives.md) |\n| `$WIZARD_HOME` — your personal library | [personal-library.md](docs/personal-library.md) |\n| Semver, update discovery, customization preservation | [versioning-and-updates.md](docs/versioning-and-updates.md) |\n| Three export modes | [sharing-spells.md](docs/sharing-spells.md) |\n| End-to-end walkthroughs (research + dev) | [general-parity-tutorial.md](docs/general-parity-tutorial.md) |\n| V1 release criteria + the self-tests | [definition-of-done.md](docs/definition-of-done.md) |\n\n---\n\n<details>\n<summary><b>Project structure</b></summary>\n\n```\nwizard/\n  README.md                  this file\n  AGENTS.md                  core agent instructions (Codex / OpenCode / Copilot)\n  CLAUDE.md, GEMINI.md       tool-specific entry points\n  CONTRIBUTING.md, LICENSE\n  CHANGELOG.md               release notes\n  package.json               Node project + CLI scripts\n  gemini-extension.json\n  .claude-plugin/            Claude Code plugin descriptor\n  .cursor-plugin/            Cursor plugin descriptor\n  .codex/INSTALL.md\n  .opencode/                 OpenCode plugin (wizard.js)\n  hooks/                     session-start bootstrap\n  scripts/                   validate-spell / new-spell / build-loader / adversarial tests\n  templates/                 SKILL.md templates per kind\n  agents/                    subagent definitions (e.g. spell-tester)\n  commands/                  slash command definitions\n  skills/                    framework skills (meta-builder, validator, inference engine)\n  spells/                    bundled spellbook — everyday / work / thinking / research / dev / chains\n  docs/                      all documentation\n  assets/                    banner + demo SVGs\n```\n\n</details>\n\n---\n\n## Contributing\n\nPRs 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)).\n\nEvery PR runs the validator and the adversarial tests. New spells must include a worked example and a `PASS` tester verdict.\n\n## Privacy\n\nNo telemetry. Ever. Everything runs locally inside your AI tool. Your spells live in `~/.wizard/` on your machine.\n\n## Acknowledgements\n\nInspired by [obra/superpowers](https://github.com/obra/superpowers) by Jesse Vincent — the `SKILL.md` format and the Iron Law come from there.\n\n## Attribution\n\nBuilt and maintained by [RedHunt Labs](https://redhuntlabs.com/) — a CTEM and attack-surface-management team that ships open-source tooling for the security community.\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\n<p align=\"center\">\n  <sub>Made for everyone who'd rather build a tool once than re-prompt forever.</sub>\n</p>\n",
  "bytes": 12386,
  "sha": "f9ee3884677334cfcf6f10fa943234687a96fbc79861dc86e5a5d15d26680b96",
  "repo_slug": "redhuntlabs/wizard",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_redhuntlabs_wizard_49fd53a4/readme"
}