Skip to content

Quickstart

Start in minutes

Install the skill, onboard your repository, then plan and execute with any agent — the steps that make your repository spec-driven and agent-pilotable.

The adoption path

  1. 01

    Install the Deep Work Plan skill

    Add the skill to your repository — a router plus eight sub-skills (create, execute, refine, resume, status, verify, onboard, author). Use the Skills CLI for the fastest path, or clone the repo and run setup where git and a shell are available.

    Terminal 
    npx skills add DailybotHQ/deepworkplan-skill

    or

    Terminal 
    git clone https://github.com/DailybotHQ/deepworkplan-skill.git && cd deepworkplan-skill && ./setup.sh
  2. 02

    Onboard the repository

    Run the onboard sub-skill and let the agent reason about your actual repo. It generates AGENTS.md, a docs/ knowledge base, per-module docs, and a cross-agent .agents/ home (with the .claude → .agents symlink), wires the thin dwp-* commands, and scaffolds a gitignored .dwp/.

    Terminal 
    /deepworkplan-onboard
  3. 03

    Evolve the kit and accept addons

    Use /skill-create and /agent-create (the author sub-skill) to grow stack-appropriate skills, agents, and commands. Onboarding also offers three opt-in addons — devcontainer, Dailybot, and dependency-upgrade — that you accept only when they fit.

  4. 04

    Plan and execute

    Generate a Deep Work Plan and run it task by task, validating each gate and resuming across sessions — piloting the repository against its own spec.

    Terminal 
    /dwp-create <goal>

    or

    Terminal 
    /dwp-execute

The outcome

Your repository becomes spec-driven and agent-pilotable: the plan is the durable source of truth, and the repository itself becomes the harness any agent runs against.

Next steps

Read the methodology Browse the kit See examples