agentleFS
ykeezyykeezy/skills/setup/SKILL.md

setup

Skill1 starsChanged 3 months agoMITView on GitHub

Onboard this workflow into the project — index the flow's output locations (runtime config, house style, glossary, ADRs, plans) in the project's memory file so every agent session starts oriented. Run once per project.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 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.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask in plain text, one line answerable.

    line 15
  2. Distinctive:

    Ask: "Add this index block to {memory file}?

    line 44
  3. Distinctive:

    If the user has hand-written pointers to the same paths elsewhere in the file, point them out and let the user remove the duplicates — do …

    line 50

“Common” is measured: kept by at least 6 in 10 of the 171 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

Register the workflow's output locations in the project's memory file. This is the only skill that ever writes to the memory file, and the only thing it writes there is one marker-wrapped index block — pointers, never content.

Rules

  • Write one thing only: the <!-- setup:index --> block. Touch nothing else in the memory file — not even to fix typos.
  • The index holds addresses, not content. Point at the canonical paths even when the files do not exist yet — their skills create them lazily.
  • Ask in plain text, one line answerable. No checkbox tools.
  • First write requires the user's explicit confirmation. If declined, do not write and do not re-ask within this run.

Steps

1. Find the memory file

  • CLAUDE.md exists → that is the memory file.
  • Else AGENTS.md exists → that is the memory file.
  • Neither exists → the project has no injection channel. Ask: "No memory file found — create one so agent sessions start oriented? CLAUDE.md (Claude Code) or AGENTS.md (Codex and others), or skip." If skipped, stop and report.

2. Present the draft

The block is fixed — five entries, one line each:

<!-- setup:index -->
## Workflow Outputs

- Runtime configuration (verified by /setup-runtime): docs/agents/runtime.md
- House style (recorded by /setup-style): docs/house-style.md
- Domain glossary: CONTEXT.md
- Architecture decisions: docs/adr/
- Implementation blueprints: docs/plans/
<!-- /setup:index -->

In a multi-context repo, point the glossary entry at CONTEXT-MAP.md instead.

Ask: "Add this index block to {memory file}? It gives every agent session a map of the workflow's outputs."

3. Write

  • Markers already present → replace the block between them (keep the markers). If the content is already identical, report "index up to date" and write nothing.
  • No markers → on confirmation, append the block at the end of the file.
  • If the user has hand-written pointers to the same paths elsewhere in the file, point them out and let the user remove the duplicates — do not edit those lines.

4. Handoff

Report what was written, then:

"Onboarding has two more steps: /setup-runtime verifies the dev loop and records the runtime configuration; /setup-style captures the team's coding conventions. Their outputs will already be indexed — run them when ready."

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.

Reviews can't be read right now.

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.