agentleFS
Sign inStart free
ARCASSystemsARCASSystems/FounderOS/skills/menu/SKILL.md

menu

Skill7 starsChanged 19 days agoMITView on GitHub

Show what FounderOS can do right now. Say "show me what you can do", "what can FounderOS do", "what should I try next", or "what's relevant right now" (or run /founder-os:menu). Returns 5 to 7 capability suggestions tailored to current state. Reads `brain/.snapshot.md`, open flags, this week's must-do, the last 7 days of `brain/log.md`, and the presence of `core/voice-profile.yml` and `core/brand-profile.yml`. Free-tier accessible - no LLM call inside the algorithm.

4 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

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    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:

    Run python scripts/menu.py --root <root> and capture stdout.

    line 37
  2. Distinctive:

    If the script exits non-zero, surface the error to the user and stop.

    line 39
  3. Distinctive:

    Does not score capabilities itself.

    line 43
  4. Distinctive:

    Does not invent slash commands.

    line 44
  5. Distinctive:

    Does not write to any file.

    line 45
  6. Distinctive:

    Does not call an LLM. The scoring is deterministic, file-based, free-tier accessible.

    line 46
  7. Very specific:

    If scripts/menu.py is missing on this install, surface that to the user and stop.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 3 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

Menu

Runs on: local-exec - runs a local script; on a cloud surface I read the results, I do not run it.

Discovery entry for FounderOS. Returns a small, ranked list of capabilities the founder is most likely to want right now, scored against current state. Natural-language phrasing is primary, slash commands appear parenthetically only for capabilities that have a real command file.

How this skill runs

The menu engine is scripts/menu.py. The skill invokes the script and prints its output verbatim. The model does not score capabilities, does not invent rows, and does not paraphrase the engine's output.

python scripts/menu.py

The script:

  • Reads state files only (brain/.snapshot.md, brain/flags.md, cadence/weekly-commitments.md, brain/log.md, core/voice-profile.yml, core/brand-profile.yml, context/priorities.md, drafts/).
  • Scores capabilities against deterministic rules.
  • Returns the top 5 to 7 by score, with a Day-1 starter set as zero-state fallback.
  • Renders rows natural-language-first, with slash commands only for capabilities that have a real .claude/commands/<name>.md file. Skill-only capabilities (weekly-review, priority-triage, pre-send-check) render natural-language only and never invent a slash form.
  • Closes with the verbatim line specified in scripts/menu.py.
  • Stdlib only. No LLM call. No network call. Free-tier accessible.

What the skill does

  1. Locate the FounderOS install root (the working directory, or the repo root if the user is inside a sub-folder).
  2. Run python scripts/menu.py --root <root> and capture stdout.
  3. Print stdout verbatim. Do not summarize, do not paraphrase, do not add commentary.
  4. If the script exits non-zero, surface the error to the user and stop.

What the skill does not do

  • Does not score capabilities itself. The script is authoritative.
  • Does not invent slash commands. If the script omits a slash form, the model omits it too.
  • Does not write to any file.
  • Does not call an LLM. The scoring is deterministic, file-based, free-tier accessible.

Constraints

  • Output must end with the closing line from scripts/menu.py verbatim.
  • Trigger phrases the operator already uses ("set up my voice profile", "set up my brand profile", "what should I focus on next", "what's on for today?", "audit the OS") appear in the script's rendered rows when the corresponding capability surfaces. The script handles this; the skill does not.
  • If scripts/menu.py is missing on this install, surface that to the user and stop. Do not fall back to a model-side menu (that would re-introduce the v1.20.0 defect this skill was rewritten to fix).

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