subaud

Skills

Instructions our agents read when a task matches: how we plan, build, test and review. The working-method skills below aren't published yet. Several are adapted from obra/superpowers (MIT). The tools' own skills (diazo, galley, cull, sift, muda, imprint) come with each tool.

From idea to merged codeThree skills, one after the other: brainstorming → writing-plans → executing-plans

what
The path from an idea to merged code. brainstorming turns an idea into an approved design, one question at a time, on diazo's page when the design is big. writing-plans turns the approved spec into a plan with exact tasks, files and checks. executing-plans has a worker subagent build it, test first, then a reviewer from the other model provider reviews the whole change.
why
Each step needs your approval before the next, and the change is kept to the correct size for the ask: as small as correctness allows, with what it leaves out stated.
ask
Say to your agent
Let's brainstorm this before writing any code.
obra/superpowers

test-driven-developmentSkills

what
Write the test first, watch it fail, write the smallest code that passes, watch it pass. One test per behavior the plan asks for, or one that reproduces the bug actually seen.
why
If you didn't watch the test fail, you don't know whether it tests the right thing.
ask
Say to your agent
Write a test that shows this bug, then fix it.
obra/superpowers

systematic-debuggingSkills

what
Find the root cause before fixing a bug, in four phases: read the real logs and state, compare with code that works, test one idea at a time, then fix at the cause with a test that reproduces it.
why
A fix aimed at the symptom usually moves the failure somewhere else, and each guess that half-works makes the next one harder to read.
ask
Say to your agent
The build is failing. Find the root cause before changing anything.
obra/superpowers

receiving-code-reviewSkills

what
How the agent handles a review's findings: check each against the code first, fix the ones that show the approved behavior failing, push back on wrong ones with evidence, and note the rest as follow-ups.
why
A review is evidence to check, not a list of orders. It is finished when the approved behavior works and nothing regressed, not when a reviewer finds nothing.
ask
Say to your agent
Go through the reviewer's findings and tell me which ones you'll fix.
obra/superpowers

reviewing-a-documentSkills

what
How the agent runs a galley review: opening the document, taking each round you send, and finishing when you approve.
why
It is what makes "open this in galley" enough: the agent knows how a review works.
ask
Say to your agent
Open the README in galley so we can review it.
galley.tools

running-long-jobsSkills

what
A command that only needs to finish (a deploy, a build, a test suite) runs in its own named tmux window. You can watch it live; the agent checks its log when it's done and closes the window.
why
You see the job in the status bar, and the agent spends no turns watching it.
ask
Say to your agent
Run the test suite in a tmux window I can watch.
(not published yet)

rememberingSkills

what
There is no memory store. When you say "remember this", the agent finds the file the rule belongs in (your global instructions, a repository's CLAUDE.md, an issue) and proposes the edit for you to approve.
why
Things worth keeping live in a file that is read in full, versioned and reviewable, where you can see and change them.
ask
Say to your agent
Remember this: ‹rule›.
(not published yet)

cleaning-up-branchesSkills

what
How to decide which git branches and worktrees are safe to delete, including branches whose pull request was squash-merged.
why
A squash-merged branch looks unmerged to git's usual checks, so finished work can look unfinished.
ask
Say to your agent
Clean up the merged branches in this repository.
(not published yet)

pi-subagent-dispatchSkills

what
How a pi session on our machines picks the model and provider for each subagent, and what to do when a dispatch fails.
why
It carries out the model rules (who builds, who reviews whom) without the session having to work them out each time.
ask
(works by itself once installed)
(not published yet)

driving-chromeSkills

what
How a session clicks, fills and reads pages in your own Chrome, with your logins, through the Playwright MCP server.
why
Signed-in sites need your real browser; you are never asked to log in to a separate one.
ask
Say to your agent
Open the sign-up page in my Chrome and fill in the form.
(not published yet)

using-the-toolsSkills

what
Picks the subaud tool a request calls for, or none, and hands off between them. It is installed with every subaud tool.
why
A one-line fix needs no tool; a change with a choice in it needs diazo. The agent reaches for a tool only when the request calls for it.
ask
(works by itself once installed)
subaud.tools

getting-started-with-subaudSkills

what
Runs the three short walks setup starts: proj, then diazo, then galley, on the real pages, with a ring on what to press.
why
You learn each tool by clicking it, without typing anything.
ask
Say to your agent
Get me started with subaud.
How setup goes

Habits and tricks

Things we do that aren't a package. Each is a line in our agents' standing instructions.

A reviewer from the other providerHabits and tricks

what
Work built by a Claude model is reviewed by an OpenAI model, and the other way round.
why
A reviewer from a different model family brings a second, independent look at the change.
ask
Say to your agent
Review this with the other provider.
executing-plans · pi-subagents

A git worktree per branchHabits and tricks

what
A worktree is a second checkout of the same repository in its own folder, on its own branch. Every branch an agent works on gets one, under the workspace's .worktrees folder; the main clone stays on its base branch.
why
Several sessions can work on one repository at once without switching branches under each other.
ask
Say to your agent
Do this on a new branch in its own worktree.
cleaning-up-branches

Long jobs in a tmux windowHabits and tricks

what
A deploy, build or test run goes in a named tmux window you can watch, never hidden in the background.
why
You can see it running, and the agent spends nothing watching it.
ask
Say to your agent
Run the deploy in a tmux window I can watch.
running-long-jobs

Never wait inside a commandHabits and tricks

what
When an agent has to wait on CI, a merge or a deploy, it checks once and then schedules a wakeup, rather than sleeping inside a command.
why
Waiting inside a command locks the session; with a wakeup it stays free to answer you.
ask
Say to your agent
Check the CI run once, then wake yourself when it should be done.
pi-wakeup · pi-schedule

One question at a timeHabits and tricks

what
The agent asks one clear question, with the options, their pros and cons and its recommendation, then waits. It decides the ordinary calls itself and lists them so you can reverse any.
why
Each question gets a real answer, and you only decide what is genuinely yours to decide.
ask
Say to your agent
Ask me one question at a time, with your recommendation.
brainstorming · diazo

Keys through creel, never in chatHabits and tricks

what
Any key, token or password goes through creel's masked box. Before asking for one, the agent says what it is, what access it grants and what it will be used for.
why
A secret typed into the chat is in the conversation; one typed into creel never reaches the agent.
ask
Say to your agent
I need to give you ‹KEY_NAME›. Ask me for it with creel.
creel · pi-creel

A pull request with auto-mergeHabits and tricks

what
When a branch is finished, the agent pushes it, opens a pull request and turns on auto-merge, so it merges by itself once its checks pass.
why
The agent doesn't stop to ask you for each merge, and the repository's checks still decide whether it lands.
ask
Say to your agent
Open the pull request with auto-merge on.
(a habit; no package)

Switching Claude accountsHabits and tricks

what
When one Claude subscription runs out, the session switches to another with /claude-account, the accounts panel in our pi-claude-bridge fork, and its subagents follow.
why
Work carries on without signing out and back in.
ask
(a panel you open in pi)
pi-claude-bridge