Steward Goal

Organization

vibevm

steward-goal

Render or refresh deterministic user-local GOAL.md from a selected campaign node in plan.toml for any owner-facing central continuation; diagnose only for workers or while a valid explicit formal handoff offering fences writes.

Overview

Publisher	vibevm
Repository	`vibevm`
Skill name	`steward-goal`
Stars	285
Forks	83
Bundled files	2
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by vibevm on GitHub. Read the source before you install it.

Installation

Install the Steward Goal AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.world/multi-user-planning/v1.0.0/vibevm/vibespecs/skills/steward-goal
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.world/multi-user-planning/v1.0.0/vibevm/vibespecs/skills/steward-goal

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/vibevm/vibevm.git /tmp/vibevm
mkdir -p .claude/skills
cp -r /tmp/vibevm/vibevm/vibepacks/org.vibevm.world/multi-user-planning/v1.0.0/vibevm/vibespecs/skills/steward-goal .claude/skills/steward-goal

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Steward Goal in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Steward Goal on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Steward Goal is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Steward goal {#root}

@fact:GOAL-SKILL-PURPOSE Produce the canonical local campaign goal specified by spec://org.vibevm.world/multi-user-planning/flows/multi-user-planning/goal-projection#root. The plan remains authority; do not paraphrase with an LLM. @status:impl/done

@fact:GOAL-SKILL-REFERENCE-RENDERER When Python 3.11+ is available, prefer the bundled deterministic scripts/render_goal.py and pass the exact context. No holder or session claim is required for ordinary owner-facing continuation. Its output is the protocol's reference implementation; inspect the protocol before modifying or replacing it. Without Python, follow the same byte rules directly and perform the double-render check. @status:impl/done

Procedure {#procedure}

@fact:GOAL-SKILL-RESOLVE Resolve the exact stewardship context and read its settings, advisory custody and raw plan bytes once. Validate the plan graph before deriving anything. A timeout, crash, compaction, new chat, model or account change needs no session, receipt or takeover record. A refresh preserves raw plan bytes, node states, evidence and supported extension fields; it does not replan or authorize implementation. @status:impl/done
@fact:GOAL-SKILL-SELECT Use valid goal_node; infer only a single unambiguous top-level non-terminal campaign. On ambiguity or invalid id, report the typed refusal and do not write. @status:impl/done
@fact:GOAL-SKILL-AUTH A worker may diagnose but never write. For an owner-facing central agent, vacant, held, stale heartbeat and mismatched holder/session are advisory and do not block refresh. A valid offering created by an explicit owner-requested formal handoff may report staleness but must not create or replace GOAL.md. @status:impl/done
@fact:GOAL-SKILL-RENDER Follow the protocol's exact subtree, ordering, frontier, candidate, route, closure, profile and fixed-text rules. Render canonical GOAL.md plus the bounded one-line GOAL-CLAUDE.txt /goal adapter. Emit UTF-8 without BOM, LF endings, no timestamp and one trailing newline per file. @status:impl/done
@fact:GOAL-SKILL-PUBLISH Write a same-directory temporary file, recheck raw plan hash, selected goal, effective canonical profile and that no valid explicit offering began, then publish the Claude command first and GOAL.md marker last. Holder/session/heartbeat changes do not move a goal input. Retry one moved semantic snapshot at most; refuse the second. @status:impl/done
@fact:GOAL-SKILL-VERIFY Re-read the marker and both outputs, recompute raw plan and Claude-condition SHA, count condition UTF-16 units, and render a second time in memory. Accept only exact hashes, a condition at most 4000 units, and byte-identical second rendering. Compare complete output bytes with the current renderer: an unchanged plan hash alone does not make older generated instructions current after a compatible package update. @status:impl/done

Output {#output}

@fact:GOAL-SKILL-REPORT Report the selected node, plan revision/hash, profile, current/stale result, both output paths, condition length and whether bytes changed. Keep an ordinary refresh report harness-neutral. Show the manual Claude recipe only when the owner requests it or asks to continue through the Claude Code adapter: copy trimmed GOAL-CLAUDE.txt, run claude -c in the bound worktree, paste, Enter. The explicit formal-handoff workflow retains its required full goal and exact command output. Do not start the campaign merely because the goal was refreshed; follow the current owner's scope. @status:impl/done

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

scripts/render_goal.py30 KB
scripts/test_render_goal.py21 KB

Frequently asked questions

What does the Steward Goal AI skill do?

Why use Steward Goal on TypingMind?

Because you install it once and use it with any model. Steward Goal is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Steward Goal in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.world/multi-user-planning/v1.0.0/vibevm/vibespecs/skills/steward-goal. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Steward Goal?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Steward Goal?

As many as you like. As long as a model supports skills, you can use Steward Goal with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Steward Goal AI skill free?

It is published on GitHub by vibevm. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Test Audit

openclaw

OrganizationPopular

Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only…

Feishu Perm

Feishu collaborator and permission workflows. Activate when the user explicitly asks to inspect or change sharing, permissions, or collaborators.

Block Kit

Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Steward goal {#root}

Procedure {#procedure}

Output {#output}

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now