agentleFS
jmporchetjmporchet/pstack-hermes/skills/setup-pstack/SKILL.md

setup-pstack

Skill2 starsChanged 2 months agoMITView on GitHub

Configure the Hermes port of pstack and understand its delegation limits. Use when enabling pstack, configuring its workflows, or asking about per-role model selection.

  • Reads credentials

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use poteto-help, principle-explain-the-number and 8 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

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 16 projects that use this

  • jaydubya818Skill

    principle-attack-the-premise

    Apply when repeated fixes fail and a shared assumption may be wrong.

    Also in 19 projects that use this

  • jaydubya818Skill

    principle-test-behavior-not-implementation

    Apply when tests mirror internals instead of asserting observable outcomes.

    Also in 19 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

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    If distinct models are required, run separate Hermes processes or profiles with their own model configuration and give each process a …

    line 20
  2. Very specific:

    Start rigorous work with pstack:poteto-mode.

    line 28
  3. Very specific:

    Use delegate_task for parallel analysis.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 25 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

Set up pstack for Hermes

This is the Hermes migration of pstack's setup flow. The plugin is already namespaced: load skills as pstack:<skill> (for example, pstack:poteto-mode).

Important platform difference

Cursor's pstack can assign different model choices to different Task roles. Hermes' delegate_task interface does not expose a per-child model selector; delegated work uses the active session's delegation configuration. Do not create or read a Cursor pstack-models.mdc rule, and do not invent model slugs.

If distinct models are required, run separate Hermes processes or profiles with their own model configuration and give each process a clearly scoped brief. Keep model and provider settings in Hermes configuration, never in .env unless they are credentials.

Normal use

  1. Enable the plugin with hermes plugins enable pstack when it is disabled.
  2. Start rigorous work with pstack:poteto-mode.
  3. For a focused workflow, explicitly load the qualified skill, such as pstack:how, pstack:why, or pstack:interrogate.
  4. Use delegate_task for parallel analysis. Give every child a complete, self-contained goal, scope, and verification predicate.
  5. Give each writer an isolated worktree or output path. Keep the coordinator responsible for synthesis and external writes.

Offer project verification once

During setup, search the current repository for a project-local .hermes/skills/verify-*/SKILL.md. If none exists, offer once to load pstack:create-verification-skill. Do not create it without the user's approval. If one exists, report its path and skip the offer.

There is no additional pstack model file to maintain in Hermes. Verify the active model with hermes model or the current session status before a run.

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.