jarvis-add
Skill18 starsChanged 31 days agoMITView on GitHub
Add something to an existing Jarvis — a channel (Telegram, WhatsApp, Discord, voice), a tool or MCP server (Gmail, Calendar, Notion, HubSpot, Facturapi…), a skill, a scheduled job, the autopilot or an L3 action, a taught skill, or audio/video understanding — with the same gates and security controls as the original build. EN — "add WhatsApp to my Jarvis", "connect my calendar", "turn on the autopilot", "teach it a skill", "add video". ES — "agrégale WhatsApp", "conecta mi calendario", "que también haga…", "que avance solo", "activa el piloto", "agrega una acción L3", "enséñale una skill", "agrega video", "que entienda audios".
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- jarvis-doctorSkill
- jarvis-nextSkill
- jarvis-quickSkill
- jarvis-refreshSkill
- jarvis-startSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 21
Read the relevant capability file and the runtime file's section for it.
- Very specific: line 31
"Agrega una acción L3": only a type from the reversible list in autonomy.md § Levels, never for sensitive packs.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
<!-- Copyright (c) 2026 Enrique Rocha (@soyenriquerocha) · tododeia.com · id er-c08d5d7d -->/jarvis-add
Load the jarvis-start skill's rules. This is a mini DEEP DIVE → ARCHITECTURE → BUILD loop for one
addition:
- Locate the Jarvis (
.jarvis/tasks.json → jarvis_diror ask) and read itsjarvis-spec.md. - Read the relevant capability file and the runtime file's section for it. Check
knowledge/compatibility.md(e.g. WhatsApp unofficial bridge → consent gate; local Ollama → never on Railway). - For a tool/MCP: official remote MCP (OAuth) > pinned maintained community MCP (read its source
first; reject anything that asks to "download a helper" or pipe a script) > generated wrapper >
Zapier MCP. Start read-only. Write scopes only on explicit request, behind the approval gate.
For the three built-in capabilities:
- "Que avance solo" / "activa el piloto" (
knowledge/capabilities/autonomy.md): fromL0toL1, add the autopilot job and its files (questions/4-construir.mdstep 11). Never above L1 by default. - "Agrega una acción L3": only a type from the reversible list in
autonomy.md§ Levels, never for sensitive packs. Show the exact line; the owner writes it into AGENTS.md § 10 in their own terminal (IRR-07: Jarvis and you never edit that list), add theautonomy-l3-<type>consent to spec §7, and give the autopilot job only the narrow tool that type needs. - "Enséñale una skill" (
knowledge/capabilities/learning.md§ 3): write the draft in<jarvis>/proposals/skills/<name>/, thenbin/promote-skill.sh promote <name>(lint, probation, commit). A skill that sends anything getsdisable-model-invocation: true. - "Agrega video" / "que entienda audios" (
knowledge/capabilities/multimodal.md):questions/4-construir.mdstep 13 for the missing part; video from links needs thevideo-urls-termsconsent; cloud STT needs its own consent and is refused with a sensitive pack (CMP-39). Not available oncowork.
- "Que avance solo" / "activa el piloto" (
- Show a ≤10-line card: what changes, cost, new risks, consent if needed. Wait for yes.
- Append tasks to
tasks.json(new ids after the last), run them via the/jarvis-nextloop, updatejarvis-spec.md§3–§7, re-runjarvis-validatoron the whole Jarvis.
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.

