loop-corp
Skill4 starsChanged 11 days agoMITView on GitHub
Use when running the Grok corp: HITL 1:1 with Ignacio, team work in rooms, ritual clock, vault-first, two-layer reports. During a timed sprint, run Sprint Parallel first. Not raw scout noise — see hallazgo / reporte-gm.
In this repository131 other files it gives its agents.
- agent-contractSkill
- brand-chrome-loginSkill
- contexto-aristasSkill
- crear-bot-nicoSkill
- daily-standupSkill
- design-a-grok-botSkill
- drift-hunt-rosterSkill
- explain-grokbotSkill
- exportar-botSkill
- govern-agentic-osSkill
- grok-bot-project-opsSkill
- hallazgoSkill
- handoff-local-hermesSkill
- identity-pipelineSkill
- no-devSkill
- orca-handoffSkill
- panorama-de-flujoSkill
- reporte-gmSkill
- routine-healthcheckSkill
- sprint-parallelSkill
- transcript-healthcheckSkill
- getting-started-brandySkill
- getting-started-calendario-contenidoSkill
- getting-started-cazador-de-canalesSkill
- getting-started-cazador-de-vuelosSkill
- getting-started-cazador-gangasSkill
- getting-started-cazador-inmobiliarioSkill
- getting-started-cazador-programasSkill
- getting-started-cazador-sponsorsSkill
- getting-started-cazador-viviendaSkill
- getting-started-content-drafterSkill
- getting-started-data-scienceSkill
- getting-started-demand-hunterSkill
- getting-started-digital-storesSkill
- getting-started-directory-builderSkill
- getting-started-enrichment-deskSkill
- getting-started-event-hunterSkill
- getting-started-expense-managerSkill
- getting-started-gm-operacionesSkill
- getting-started-inbox-managerSkill
- getting-started-intake-intelSkill
- getting-started-intelligence-gmSkill
- getting-started-join-a-startupSkill
- getting-started-last30daysSkill
- getting-started-life-opsSkill
- getting-started-luma-taggingSkill
- getting-started-market-watcherSkill
- getting-started-meta-vaultSkill
- getting-started-musa-designerSkill
- getting-started-plantillas-notionSkill
- getting-started-product-hunterSkill
- getting-started-publisherSkill
- getting-started-pulso-brandSkill
- getting-started-pulso-diaSkill
- getting-started-renewals-hunterSkill
- getting-started-saves-archivistSkill
- getting-started-scraping-deskSkill
- getting-started-seo-deskSkill
- getting-started-sliderSkill
- getting-started-swe-outer-loopSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Use this when running Ignacio’s Grok corp: 9h sprints, GM cycles, new bots, or any “how does the company talk?” question.
- Distinctive: line 29
No spam a canales existentes.
- Distinctive: line 84
All Tasks / Finance OS / Comms stay their own schemas.
≈ “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.
Files
Loop Corp (Grok Bot)
Use this when running Ignacio’s Grok corp: 9h sprints, GM cycles, new bots, or any “how does the company talk?” question.
If the sprint has a defined reset/cut time, run Sprint Parallel first. That skill turns on dual-channel (1:1 GMs + rooms) and max parallelization until the cut. This file is the standing corp OS.
Comm
Ignacio 1:1 (HITL) → Grok Bot results, A3, decisions
Grok Bot → sala GMs+Orquestador orders
GMs → their staff rooms
Bot ↔ bot 1:1 OK
Scout → GM hallazgo
GM → sala GMs → Grok Bot
Grok Bot → Ignacio 1:1 weekday 09:00:
1) 5 reporte-gm (Forja, Levy, Brandy, Inti, Oppy) — lo importante
2) corte Grok Bot — lo más más (máx 3 TOPs)No spam a canales existentes. Rooms GM = one-to-many.
Ignacio’s personal chats are HITL: he looks at results. Do not dump wiring there. GMs never write Ignacio. Scouts never.
Outside a timed sprint, command GMs from the GM room and do not 1:1 them for ops. During a timed sprint, also 1:1 each GM in the same beat (see Sprint Parallel). Never DM scouts. Forja is split Core / ROI (cap 6).
Factory
GM proposes. Grok Bot creates. Ignacio if structural or A3. Frozen: Closer, Ventas, Partnerships, caja-bot, Skool/WhatsApp, publishers, identity farm. No crear bots desde este skill.
Loop
intent → GMs en paralelo → staff hallazgo → GM audita + 1 mejora → reporte-gm → Grok Bot resume a Ignacio.
Ritual clock (America/Lima)
Scouts 05:15–06:20. Hermes 06:30/06:45/07:00. Pulso Día 07:10. GMs 07:25–07:50. Grok Bot HITL pack 09:00 (5 GM + corte). Close 21:00. Sunday ritual. Monthly caja, no A4.
Sprint: aggregators, not executors. NotebookLM = Hermes.
Formato
Exact hallazgo and reporte-gm. Do not invent a third.
Hallazgo:
SCOUT
OFERTA / SEÑAL (1 frase)
LINKS
SCORE ROI o urgencia (1–5)
FIT (1–5) — vs Memory Setup / perfil (obligatorio si scout = Programas & Perks)
TAG (opcional): embajador | beca | hackathon
NEXT STEP sugerido (no ejecutar A3)Reporte GM:
GM
PERÍODO
TOP 1–3 (una línea + link + score)
DESCARTADOS (conteo, no lista)
PEDIDO A SCOUTS (próximo barrido)
PROPUESTA BOT (opcional, 1 máx, a Grok Bot — no crear)
A3 (sí/no — solo si hay que gastar/publicar/cerrar)- Newest-on-top into existing
Ledger-{Forja,Levy,Brandy,Inti,Oppy}.md. - Headings + fenced field block. No prose soup.
- One line per TOP: offer + link + score.
- DESCARTADOS = count, not a list. No invented fields or numbers.
- YAML: single frontmatter, no duplicated
---. - Gold paste: Ledger-Inti.
- Mid-session = vault. Session close = same Notion page if a URL exists. Else stay vault and say
ledger missing. Do not create DBs or pages. - All Tasks / Finance OS / Comms stay their own schemas. GM reports do not become those rows.
- Flojo (sin link/score, DESCARTADOS-lista, cifra inventada) = Grok Bot lo devuelve al GM. Ignacio ve
n/den ese hueco.
Procesos (sprint)
Idle / solo-ack is a bug. Each GM owns ONE end-to-end flow mapped to vault skills, not a random hallazgo. Run them in parallel (Sprint Parallel).
| GM | Flujo | Skills |
| Forja | corte ventas | Pulso Revenue → hallazgo → reporte-gm |
| Levy | ritual AM | Renovaciones + Pulso Día (assemble-day) → reporte-gm; caja = Hermes |
| Brandy | lote editorial | Eventos/Calendario/Comunidad/Inspiración → Borrador A1 (sim) → reporte-gm |
| Inti | learning | research-pipeline → Inbox/Ingesta → Síntesis → NotebookLM (Hermes) |
| Oppy | mapa OS | verifica que los 4 flujos existen en vault; 1 gap |
Workspace rooms (Núcleo, GPT-Chain, Veller, Crafter) map their own 4 boxes when those brands are the ROI north star.
Sala GMs = loop. Each cycle: trigger → skill → output → owner. No invented numbers.
Vault
Vault-first. Drafts off-vault ok. Docs en vault = pensados, no dumps. Migrar a Notion al cerrar sesión (Hermes). No tocar Notion durante el loop.
Skills: hallazgo (scout → GM) · reporte-gm (GM → sala GMs → Grok Bot).
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
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.

