How Dotpack Works
Dotpack makes you faster by providing a prebuilt “pack” of workflows and expertise for your codebase:
- Commands: the workflows you run (
/build,@fix) - Agents: the specialists that execute the workflow (planner, engineer, QA, reviewer)
- Skills: stack-aware conventions that shape output automatically
Core concepts: Commands vs Agents vs Skills
| Concept | What it is | How you use it | Where it lives |
|---|---|---|---|
| Commands | Named workflows (the “thing you run”) | You invoke explicitly (/build, @fix) | .dotpack/commands/ |
| Agents | Specialized roles (the “who does the work”) | Selected by the workflow (or referenced by name) | .dotpack/agents/ |
| Skills | Stack knowledge + conventions (the “how it should be done”) | Activates from context (files/frameworks) | .dotpack/skills/ |
How commands produce outcomes
A typical “build” workflow looks like:
- Plan the work
- Implement changes
- Add/adjust tests when relevant
- Review and verify
The point is to ship working changes with less back-and-forth.
What ships by default (keep this factual)
- Start here:
/build,/fix,/plan - Common agent roles: Planner, Engineer, QA, Reviewer
- Common skills: conventions for frameworks/tools you’re using (e.g. Next.js/React/TypeScript/Tailwind)
The mechanism (supporting detail)
Dotpack keeps these workflows consistent across tools by generating tool-specific outputs from a single source:
- Source (
.dotpack/): where commands/agents/skills live - Build (
dotpack build): generates tool configs - Execution: you run commands in your AI tool
Source vs generated files
Edit these:
.dotpack/
├── commands/
├── agents/
└── skills/Don’t hand-edit these (regenerate instead):
.gemini/
.cursor/
.claude/Regenerating output
dotpack buildWhat to commit
- Solo: commit everything or just
.dotpack/(either works) - Team: commit
.dotpack/always; commit generated outputs if not everyone installs the CLI
Last updated on