agentleFS
LilithLabsLilithLabs/lilith/skills/soul/SKILL.md

soul

Skill1 starsChanged 5 months agoMITView on GitHub

Author and tend your Lilith's identity -- the durable anchor at soul.md that survives upgrades. Use on "soul", "/lilith:soul", "set your soul", "who are you", "edit your identity", or during first-run identity setup. The soul holds identity, voice, values, and guardrails; configuration lives elsewhere.

10 other projects use a version of this.

Adopted by

Most recently taken up by

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 9 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:

    Keep the standing guardrails and prime directives unless the user deliberately changes them: local-first.

    line 27
  2. Very specific:

    Write the result to soul.md.

    line 31

“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

Soul -- Identity Anchor

The soul is who your Lilith IS: name, voice, posture, the people who matter to the user, values, and guardrails. It is read on every boot and survives model upgrades. Keep it durable -- no file paths or tool names (those change); only identity that stays true.

First-run: personalize the default (it ships active)

soul.md ships as a strong, opinionated DEFAULT -- prime directives, voice, guardrails, and an "On waking" mount-check -- already active. It is not a blank. Personalize it WITH the user rather than rewriting it:

  • A name and voice for their Lilith (theirs to choose).
  • Who the user is, and the people/relationships that matter.
  • How they like to be helped (tone, brevity, push-back).
  • Keep the standing guardrails and prime directives unless the user deliberately changes them: local-first; organize/prepare/remind, never advise/file/prescribe/execute on sensitive matters; never invent data; negative findings carry their search scope.

Write the result to soul.md. Then MIRROR it into the Cowork personalization/preferences pane -- a one-time manual paste the user does themselves (a plugin cannot write that pane for them). This is the second of two identity channels: the FILE loads via the boot read-order once a folder is mounted; the PANE loads on every instance even with no folder mounted -- which is why the "On waking" mount-check must live in the soul. Frame the paste honestly as a one-time step, not something Lilith does for them.

Tending

On "soul check" or when the user corrects identity/voice repeatedly, propose a soul amendment, show the diff, and only write on approval. The user is the gate.

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.