agentleFS
Sign inStart free
protokol11protokol11/repo-upgrade/setup-repo/SKILL.md

setup-repo

Skill0 starsChanged 17 days agoMITView on GitHub

Bootstrap a new project folder with a Pi-ready agentic scaffold plus a compliance package. Stamps CLAUDE.md, AGENTS.md, .pi/agents/*.md, .docs/violations/, and .docs/sessions/ from the universal principle catalog.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use implement.

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.
  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 2

    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. Distinctive:

    Before starting a feature when no agentic scaffold exists.

    line 15
  2. Very specific:

    Keep CLAUDE.md < 150 lines.

    line 49
  3. Very specific:

    Use the deep anchors in CONTEXT.md.

    line 50
  4. Distinctive:

    Do not commit sensitive data.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 9 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-repo

Bootstrap a new project with the Pi agentic scaffold and the compliance package.

When to use

  • New project folder.
  • New directory that will use Pi orchestration (explore/plan/coder/tester/fixer).
  • Before starting a feature when no agentic scaffold exists.

Steps

  1. Render — call the renderer before scaffolding.
    • Command: node ~/.agents/skills/principles-render/render.mjs --out <tmp-render-dir>.
    • Completion: temp directory contains role-prompts/*.md, lint-rules.md, spec-template.md.
  2. Scaffold — run scripts/scaffold.ps1 -ProjectPath <path>.
    • Copies templates (incl. .docs/PLAN.md in canonical planmd format — Now/Next/Backlog/Done, 1. [ ], optional [P0]).
    • Replaces project placeholders.
    • Injects role prompts into .pi/agents/*.md.
    • Replaces .docs/SPECS/README.md spec template section with the renderer's template.
    • Writes .docs/violations/lint-rules.md and .docs/violations/audit-log.md.
    • Creates .docs/sessions/STATUS_TEMPLATE.md.
    • Initializes git unless -SkipGit.
  3. Drill — ask the user one question at a time to fill project-specific content.
    • Questions: project purpose, stack, main entry point, sensitive data exclusions, special workflow rules.
    • Completion: CLAUDE.md, CONTEXT.md, README.md, and AGENTS.md contain project-specific content.
  4. Verify — check the scaffold against the acceptance criteria in REFERENCE.md.
    • Required files exist and have non-placeholder content.
    • .docs/PLAN.md follows the canonical planmd format (Now/Next/Backlog/Done).
    • .pi/agents/*.md contain role-specific principles.
    • .docs/violations/ exists with audit-log.md and lint-rules.md.
    • .docs/sessions/ exists instead of sessions/ in the repo root.
  5. Archive spec — move SPEC.md to .archive/ when the user confirms.
    • Completion: SPEC.md is moved to .archive/SPEC-<date>.md or deleted.

Conventions

  • Language: all documents and code terms are English. Chat replies are Russian. Author quotes stay verbatim in > «...».
  • Keep CLAUDE.md < 150 lines; push details to AGENTS.md and REFERENCE.md.
  • Use the deep anchors in CONTEXT.md.
  • Do not commit sensitive data.
  • The compliance package (lint-rules.md, audit-log.md) is generated from the catalog and cannot drift from it.

Output

A bootstrapped project ready for the explore → plan → coder → tester workflow, with compliance artifacts stamped.

Reference

See REFERENCE.md for file-by-file explanations and templates/ for the scaffold.

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.

Check your setup, free