agentleFS
Sign inStart free
MasRamaMasRama/peka/skills/setup/SKILL.md

setup

Skill1 starsChanged 29 days agoMITView on GitHub

Set up PEKA global memory and background learning. Use when the user runs /peka:setup or asks to turn PEKA on.

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

10 rules. 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" setup --check and read the output.

    line 12
  2. Distinctive:

    Every few turns a reviewer agent saves what is worth remembering (the session pauses briefly while it works and ends with one line on what …

    line 16
  3. Distinctive:

    Ask the user whether to apply.

    line 22
  4. Very specific:

    Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" setup --apply and report the result.

    line 23
  5. Very specific:

    If it fails because settings.json is not valid JSON, show the error and ask the user to fix the file.

    line 24
  6. Very specific:

    Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" legacy.

    line 26
  7. Distinctive:

    Read each listed file.

    line 29
  8. Very specific:

    Write it into the PEKA memory directory shown by setup, using the same frontmatter format (name, description, metadata.type).

    line 30
  9. Very specific:

    Add one line per imported memory to MEMORY.md in that directory.

    line 33
  10. Distinctive:

    Leave the original files where they are.

    line 34

“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

Set up PEKA

  1. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" setup --check and read the output.
  2. Explain to the user, briefly and in their language:
    • PEKA keeps one global memory and a library of learned skills in ~/.peka, shared by every project, with local git history as a safety net.
    • Every few turns a reviewer agent saves what is worth remembering (the session pauses briefly while it works and ends with one line on what it saved), and about once a week a curator agent tidies it. Both run as normal Claude Code subagents and count toward usage like any other subagent.
    • The exact settings changes listed in the check output. A backup of settings.json is written before anything changes.
  3. Ask the user whether to apply. If they decline, stop here.
  4. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" setup --apply and report the result. If it fails because settings.json is not valid JSON, show the error and ask the user to fix the file; do not edit it yourself.
  5. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/peka.mjs" legacy. If it lists old per-project memories, show the list and ask whether to import them into the global memory. Only if the user agrees:
    • Read each listed file.
    • Write it into the PEKA memory directory shown by setup, using the same frontmatter format (name, description, metadata.type). Merge duplicates, and name the project inside project-specific memories, because the memory is now shared.
    • Add one line per imported memory to MEMORY.md in that directory.
    • Leave the original files where they are.
  6. Tell the user to start a new session so the global memory loads.

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