P3 help

Answer the user's question about p3-stack, hand them a prompt they can send, and link the file the answer came from. For a help question, don't start the work. The user asked how, and a p3-stack run spends real tokens, so let them send the prompt.

A message that asks for work, such as "use p3-stack to fix this bug", is not a help question. Read p3-mode, do the work under it, and mention once that invoking /p3-mode keeps the work in this style.

This file maps questions to the skills and playbooks that hold the answers. Those files own the details. Read the file you route to before you quote it, and trust it when it disagrees with this map. The links here are repo-relative, so give the user the file's public copy: https://github.com/uzairansaruzi/p3-stack/blob/main/ followed by its path.

Find out what they need

Infer the need from the message and the conversation. A named situation, such as "which skill reviews a PR?", goes straight to its section. If the need is still unclear, ask one multiple-choice question with these options, then answer only the section they pick: get set up, start a task with /p3-mode, pick a skill for a situation, fix a run that went wrong, or make p3-stack my own.

Check the state that changes the answer, and mention it only when it does. No p3-models.md means /setup-p3 hasn't run for this user, so every role uses its default model. No verify-* skill or other app harness in the project means agents have no scripted way to drive the app; mention /create-verification-skill when the question is about proving a change works.

Get set up

1. Install by cloning the repo and running ./install.sh. It links every skill into ~/.agents/skills/, where T3 Code reads skills; ./install.sh --project /path/to/repo targets a project's .agents/skills/ instead.
2. Run /setup-p3. It asks for a reasoning budget, maps a model to each role, and writes p3-models.md. The file applies to new sessions.
3. Start a real task with /p3-mode, a goal, and a check that can pass or fail.

Installing changes nothing until the user invokes a skill. Only /p3-help loads from the user's words. The README has the details. Offer to word their first prompt with them.

If cost is the worry, say where the tokens go and how to spend fewer. p3-stack spends extra tokens on subagents and review panels. Rerun /setup-p3 and pick a smaller budget or cheaper models. A role set to auto or inherit-parent runs on the parent thread's model, which saves tokens when that model is cheaper. A shorter panel list runs fewer subagents, one for each entry. Save /p3-mode for work that needs rigor.

Start a task with /p3-mode

/p3-mode matches the task to a playbook, copies the playbook's steps into the todo list, and runs the other skills as the steps need them. A step it skips stays in the list as skip: <reason>. A good prompt states the goal and how to tell it's done. It doesn't list skills, because a hand-written sequence tends to drop or reorder steps the playbook would keep.

Skills are invoked by name (/p3-mode). There are no mode toggles, so start each new task with /p3-mode. Mid-chat, "new task" makes the mode match a fresh playbook. /p3-mode already uses agents/p3-agent.md for the delegates its playbook steps spawn. To get the same style from a delegate of your own, open its brief with agents/p3-agent.md.

Pick a skill

The default answer is /p3-mode, which runs most of the others when its steps need them. Name a skill directly when the user wants more or less of something than the playbook gives. Read the skill before you recommend it, and give one example prompt.

If a skill directory next to this one is missing from the table, read its frontmatter and route by its description. The principle-* directories are covered under principles below.

Close calls:

• /how explains what the code does. /why explains the reasons. /teach runs one or both and explains the result plainly.
• /arena gives every worker the same brief and merges the best parts. /swarm splits work into slices or a race and returns one report.
• /architect implements right after it settles the design. Add "with checkpoint" to review the design before it writes code.
• /interrogate reviews the diff. /blast-radius looks for breakage outside the diff and proves the one fact that makes the change safe.
• /recall rebuilds context across recent threads. Resuming one specific thread, delegated task, or branch is the Session pickup playbook.
• /figure-it-out designs one rigorous run. The Orchestrate playbook runs a program that spans days and many PRs. The Autonomous run playbook drives one task to a finish condition.

Not in p3-stack: p3-stack has no /orchestrate skill. Orchestrate is a /p3-mode playbook.

Playbooks and principles

Playbooks are step lists inside /p3-mode, not skills, so they aren't invoked by name. Inside /p3-mode, describing the task picks one, and these phrases name one directly; the Playbooks section of p3-mode lists every playbook and when it applies:

• "babysit this pr" or "check on pr 123" runs Babysit. It drives the PR to merge-ready and stops there. It doesn't merge unless the user asks to merge, land, or ship.
• "land the stack" runs Shipping. "take over this branch" runs Session pickup. "pause safely" runs Pause safely. "run the eval playbook" runs Eval.
• "full autopilot on this queue" runs Autopilot-full. "stack them, don't ship" runs Autopilot-stack.

p3-stack has no planning skill. For work that spans phases or stacked PRs, asking /p3-mode for a plan runs the Multi-phase plan playbook, which writes the plan and doesn't implement it. For a design question, the Prototype playbook or /architect settles it in code first.

Principles are one-rule skills that /p3-mode reads and cites in its replies. The user rarely invokes one. They steer with the names instead, as in "apply prove it works. show me the real output." Typing /principle-<name> still loads one on demand.

Fix a run that went wrong

Make p3-stack my own

• /automate-me drafts a personal mode skill from the user's own history, to use alongside /p3-mode. /reflect after a session turns its lessons into skill edits the user approves. /p3-mode write a skill for <workflow> runs the authoring playbook, and the eval playbook tests a skill change blind.
• Fix a misbehaving skill in its own PR, not inside the feature work where it went wrong.

Reply

Lead with the answer. Give at most one example prompt in a code block, then the link to that file. Keep it short unless the user asked for the whole map.