agentleFS
0xrsydn0xrsydn/pstack-pi/skills/setup-pstack/SKILL.md

setup-pstack

Skill7 starsChanged 34 days agoMITView on GitHub

Explain or troubleshoot pstack model routing. Use for pstack setup questions, configuration errors, or requests to change pstack models. The native /setup-pstack command performs interactive configuration.

30 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use poteto-help, make-bot-ui and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 13 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 15 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 6 projects that use this

  • TheOnlyFusionCubeSkill

    statechart

    Draw what an app's user sees as a Mermaid statechart from a TLA+ model. States are gray if they work, red if still wrong, and green if fixed. Each bug TLC finds is a numbered path. Use for /statechart, \"show the PM the bug\", or to turn an agreed chart into a TLA+ skeleton.

    Also in 8 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the native /setup-pstack command for configuration.

    line 8
  2. Very specific:

    If pstack_task reports an invalid or unavailable model, run /setup-pstack again.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 29 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Setup pstack

Use the native /setup-pstack command for configuration. Do not create model slugs from memory and do not edit the file unless the command cannot run.

The command uses Pi's authenticated model registry. It asks for a reasoning budget, starts from the upstream Grok 4.7 and Claude Opus 5.5 pair, shows every upstream role, validates all selections, and writes ~/.pi/agent/pstack-models.json atomically.

Pi stores model identity and thinking level separately. A role assignment has this shape:

{
  "model": "provider/model-id",
  "thinking": "xhigh"
}

"model": "inherit-parent" inherits both the active parent model and its thinking level. Panel roles contain arrays of assignments. Their array length sets the fan-out count.

The exact role IDs are:

  • feature-refactoring
  • bug-fix
  • perf-issue
  • hillclimb
  • judgment-prose
  • hardest-tasks
  • how-explorer
  • how-explainer
  • why-investigators
  • why-synthesizer
  • reflect-tooling
  • reflect-judgment-divergent-synthesizer
  • arena-runners
  • arena-cross-judge-pool
  • swarm-workers
  • architect-runners
  • interrogate-reviewers

If pstack_task reports an invalid or unavailable model, run /setup-pstack again. The command also migrates the old four-role file when it can parse it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.