How do I install the Tutti skill?

Run npx skillmds@latest add tomevault-io/tutti in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tutti safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tutti?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tutti free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tutti by tomevault-io — Agent Skill

Name: Tutti
Author: tomevault-io

File contents

Tutti OpenClaw Skill (Starter)

Use this skill to orchestrate a Tutti workspace from another agent loop.

Reference wrapper:

integrations/openclaw/tutti_openclaw.py
integrations/openclaw/action-contract.json

If your tt binary is older than repo main, invoke the wrapper with:

--tt-bin "cargo run --quiet --"

Trigger

Use when asked to launch/monitor/verify/stop a multi-agent workspace managed by Tutti.

Preconditions

Run from workspace root (tutti.toml present).
Run tt doctor before launching long workflows.
Prefer .tutti/state/*.json and tt verify --last --json for verification reads.

Intent Mapping

launch_team: tt up
launch_agent: tt up <agent>
run_workflow: tt run <workflow> [--agent <agent>] [--strict] [--json]
list_workflows: tt run --list --json
plan_workflow: tt run <workflow> --dry-run --json
verify_team: tt verify [--workflow <name>] [--agent <agent>] [--strict] [--json]
generate_handoff: tt handoff generate <agent> --json
list_handoffs: tt handoff list --json [--agent <agent>]
apply_handoff: tt handoff apply <agent> [--packet <path>]
team_status: tt status
agent_output: tt peek <agent> --lines <n>
stop_agent: tt down <agent>
stop_team: tt down
read_verify_status: tt verify --last --json (fallback: .tutti/state/verify-last.json)

Execution Pattern

Preflight:
- python3 integrations/openclaw/tutti_openclaw.py doctor_check
- stop if non-zero and report failures.
Launch:
- ... launch_team or ... launch_agent <agent>.
Work:
- ... list_workflows, then ... run_workflow <workflow>.
Verify:
- ... verify_team --strict for gate-style checks.
Stop:
- ... stop_team or ... stop_agent <agent>.

Failure Policy

Non-zero tt exit: surface command + stderr summary.
tt verify non-strict warnings: report as warning, include tt verify --last --json fields.
Missing state file: treat as transient for up to 3 short retries.

Output Contract (Recommended)

Return:

action performed
command used
exit status
brief evidence (one or two key lines)
next recommended action

For full integration details, see:

docs/AGENT_INTEGRATION_CONTRACT.md
docs/OPENCLAW_SKILL_CONTRACT.md

Source: nutthouse/tutti — distributed by TomeVault.

---name: tuttidescription: Use when asked to launch/monitor/verify/stop a multi-agent workspace managed by Tutti.---# Tutti OpenClaw Skill (Starter)Use this skill to orchestrate a Tutti workspace from another agent loop.Reference wrapper:- `integrations/openclaw/tutti_openclaw.py`- `integrations/openclaw/action-contract.json`If your `tt` binary is older than repo `main`, invoke the wrapper with:- `--tt-bin "cargo run --quiet --"`## TriggerUse when asked to launch/monitor/verify/stop a multi-agent workspace managed by Tutti.## Preconditions1. Run from workspace root (`tutti.toml` present).2. Run `tt doctor` before launching long workflows.3. Prefer `.tutti/state/*.json` and `tt verify --last --json` for verification reads.## Intent Mapping- `launch_team`: `tt up`- `launch_agent`: `tt up <agent>`- `run_workflow`: `tt run <workflow> [--agent <agent>] [--strict] [--json]`- `list_workflows`: `tt run --list --json`- `plan_workflow`: `tt run <workflow> --dry-run --json`- `verify_team`: `tt verify [--workflow <name>] [--agent <agent>] [--strict] [--json]`- `generate_handoff`: `tt handoff generate <agent> --json`- `list_handoffs`: `tt handoff list --json [--agent <agent>]`- `apply_handoff`: `tt handoff apply <agent> [--packet <path>]`- `team_status`: `tt status`- `agent_output`: `tt peek <agent> --lines <n>`- `stop_agent`: `tt down <agent>`- `stop_team`: `tt down`- `read_verify_status`: `tt verify --last --json` (fallback: `.tutti/state/verify-last.json`)## Execution Pattern1. Preflight: - `python3 integrations/openclaw/tutti_openclaw.py doctor_check` - stop if non-zero and report failures.2. Launch: - `... launch_team` or `... launch_agent <agent>`.3. Work: - `... list_workflows`, then `... run_workflow <workflow>`.4. Verify: - `... verify_team --strict` for gate-style checks.5. Stop: - `... stop_team` or `... stop_agent <agent>`.## Failure Policy- Non-zero `tt` exit: surface command + stderr summary.- `tt verify` non-strict warnings: report as warning, include `tt verify --last --json` fields.- Missing state file: treat as transient for up to 3 short retries.## Output Contract (Recommended)Return:- action performed- command used- exit status- brief evidence (one or two key lines)- next recommended actionFor full integration details, see:- `docs/AGENT_INTEGRATION_CONTRACT.md`- `docs/OPENCLAW_SKILL_CONTRACT.md`---> Source: [nutthouse/tutti](https://github.com/nutthouse/tutti) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions

Tutti