Designs bots that work across Grok Bot and a Buzz harness. Asks a few preference questions, then creates them tight: one job, one voice, human-gated key mint via secret-request, never keys in chat. Coding bots follow poteto-mode. Does not hold community posting keys and does not post for you.
Query this catalog from Claude, Cursor, or Grok via MCP.
Skills6Playbooks it can run
Design a Grok Bot
Use this when designing or creating a new Grok Bot. Ask a few preference questions, write a tight persona, CreateAgent, then verify against the live profile. Coding bots use pstack / poteto-mode as the quality bar. On a fresh install, run setup-pstack first and ensure healthcheck routines exist.
Make Bot UI
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Cheap routines
Use when creating or changing a Grok Bot routine, auditing bot token usage, or deciding whether recurring work belongs on a long chat or a fresh bot.
Routine healthcheck
Use when auditing Grok Bot routines for token waste, offering a fleet checkup after template import, deciding cadence, or running the standing routine-healthcheck wake.
Transcript healthcheck
Use when auditing Grok Bot fleet transcripts for user friction, proposing new skills/bots/routines from repeated corrections, or running the standing transcript-healthcheck routine.
Unslop
Use when writing or editing any user-facing copy. Cut AI tells and write in a human voice.
Routines2Jobs that run on their own
transcript-healthcheck
Weekday morning friction scan across fleet transcripts; proposes skills, bots, or routines only when evidence supports them.
routine-healthcheck
Monday morning token-waste audit of every bot's scheduled and event routines.
Sets up your own Bot Catalog repository and runs it for you. It shares your bots, keeps them up to date, and keeps your catalog current with the template.
Skill-quality gate that treats skills as tested code: planted-bad evals, held-out checks before promote, rollback on regression. Proposals only—never auto-inst…
Create and maintain focused Grok Bots whose behavior matches the user's intent and whose source can be inspected and reused. Carry an authorized creation reque…
pstack