<div align="center">

<picture> <source media="(prefers-color-scheme: dark)" srcset="./assets/dwp-mark-dark.png" /> <img alt="Deep Work Plan" src="./assets/dwp-mark-light.png" width="200" /> </picture>

# DeepWorkPlan Skill Pack

**Models matter. Context matters more.**

[](LICENSE) [](https://agentskills.io) [](https://skills.sh)

[🌐 deepworkplan.com](https://deepworkplan.com) · [🔒 Security](SECURITY.md) · [📝 Changelog](CHANGELOG.md) · [🤝 Contributing](CONTRIBUTING.md)

</div>

---

> The official DeepWorkPlan agent skill pack, maintained by [Dailybot](https://www.dailybot.com).

DeepWorkPlan turns any repository into a **structured environment** — context, guardrails, and a durable plan — where any coding agent executes with precision and finishes long-horizon work. It makes the repo AI-first (an adapted `AGENTS.md`, `docs/`, per-module docs, and `.agents/` config), then drives structured, multi-task **Deep Work Plans**: plan, execute, refine, resume, and report on long-running work, with all plan output living in a gitignored `.dwp/` directory.

> DeepWorkPlan is spec-driven development where the repository itself becomes the harness.

- **License:** [MIT](LICENSE) - **Security policy:** [SECURITY.md](SECURITY.md) - **Changes:** [CHANGELOG.md](CHANGELOG.md) - **Format:** [Open Agent Skills](https://agentskills.io) standard - **Docs:** <https://deepworkplan.com>

## Skills

| Skill | What it does | |-------|-------------| | **deepworkplan-onboard** | Make any repo AI-first. Reasons about the repo's stack and archetype (orchestrator hub vs individual repo), then generates an adapted `AGENTS.md`, `docs/`, per-module docs, `.agents/`, and the `.claude → .agents` / `.cursor → .agents` symlinks. Offers opt-in addons. | | **deepworkplan-create** | Cr