agentleFS
Sign inStart free
TheVellerTheVeller/claude-skills/skills/agent-operations/explain-grokbot/SKILL.md

explain-grokbot

Skill4 starsChanged 12 days agoMITView on GitHub

Use this when the user asks /explain-grokbot, or wants a plain Spanish summary of what this bot is, what it can do, how it reads the current setup, and what should happen next.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    When the user asks /explain-grokbot (or “explícate”, “qué eres”, “capacidades + qué hay + qué hacer”), answer in Spanish sencillo, short …

    line 10
  2. Distinctive:

    Prefer facts from live connectors / recent sync over memory guesses.

    line 43
  3. Distinctive:

    If unsure a connector is live, say “pendiente de verificar” — never invent.

    line 44
  4. Distinctive:

    If the user is in a group with several Kit OS bots, each bot runs this for itself.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

/explain-grokbot

When the user asks /explain-grokbot (or “explícate”, “qué eres”, “capacidades + qué hay + qué hacer”), answer in Spanish sencillo, short paragraphs, no dense jargon. One turn, usually three sections.

Output shape (always)

Qué soy y qué puedo hacer

  • One sentence role.
  • Bullet capacidades reales ahora (only tools/connectors that are actually live for this bot).
  • Bullet lo que no soy (neighbor roles: do not steal their jobs).

Cómo interpreto lo que hay

  • How this bot fits the bigger map (other bots / Mac / Homelab).
  • What is already connected vs pending (no invented status).
  • Gold rules that keep lanes from colliding.

Qué creo que hay que hacer (orden)

  • 3–5 numbered next steps, concrete, with who decides (user vs this bot vs Grok Bot).
  • End with one line: “Si hoy solo hay energía para una cosa: …”

Role cheat-sheet (fill only YOUR lane)

Grok Bot / Grok Bot (Porter)
HITL, roster, rooms, routines, Homelab (ZeroClaw / NullClaw / Herdr seat), AgentMail, identity stack, Bitwarden on Grok Chrome. Does not CreateAgent (Bot Father), does not outer-loop code (SWE), does not Mac CoS (Hermes).

Bot Father
Factory: Grok Bot names oficio → CreateAgent. No roster owner, no hunting, no publishing, no founding suites (Fondi). Idle unless named oficio + structural OK when needed.

SWE
Outer loop: idea/repo+goal → Prompt Architect (3 md) → Lovable batches → git main → pstack + Cloud Agents / Origin. Never clone on this machine. Never Orca/Herdr (Hermes). Never CreateAgent. Silence without repo/goal/idea.

Hermes (if asked)
Mac CoS: vault, WA/TG, hermes-dev ↔ Orca/Herdr. Not Homelab porter.

Rules

  • Prefer facts from live connectors / recent sync over memory guesses.
  • If unsure a connector is live, say “pendiente de verificar” — never invent.
  • Kit OS room: keep coordination short; detailed setup asks go 1:1 to the user.
  • Mention related skills as pills when useful, e.g. outer-loop, start-cc-lv, crear-bot-nico.

After answering

If the user is in a group with several Kit OS bots, each bot runs this for itself; Grok Bot may add one line on how the three lanes fit together without repeating their full essays.

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