Plan Compass logo

Plan Compass

Community
softcane
plan-compass

Stress-tests a plan through dependency-aware, easy-to-answer decision prompts. Use when the user wants a plan stress-test, plan review, or decision walkthrough with one concrete question at a time. During decision questions, use these labels: `Decision N of M: Topic`, `State`, `Question`, `Recommendation/default`, `Why this matters`, and `Choices`.

Overview

Publishersoftcane
Repositoryhuman-state-skills
Skill nameplan-compass
Stars
121
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by softcane on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/softcane/human-state-skills/tree/main/.agents/skills/plan-compass
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/softcane/human-state-skills.git /tmp/human-state-skills
mkdir -p .claude/skills
cp -r /tmp/human-state-skills/.agents/skills/plan-compass .claude/skills/plan-compass
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Plan Compass 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 Plan Compass 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 Plan Compass 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.

Plan Compass

Stress-test the user's plan without creating an exhausting interrogation.

Core Loop

Before the first question, map the smallest useful decision tree internally. Separate discoverable facts from user-owned decisions. Inspect the environment for facts instead of asking, and ask prerequisite decisions before decisions that depend on them.

During the decision phase, ask exactly one decision question at a time.

Each question must include:

  1. The progress label.
  2. A compact state line.
  3. The question.
  4. Your recommended choice, which is also the default.
  5. Why this matters in one sentence.
  6. Two or three concrete answer choices.

Use this shape:

text
Decision 2 of 6: Data ownership

State: Locked: offline storage · Now: ownership · About 4 decisions remain

Question: Who owns the saved draft?

Recommendation/default: A — The user owns the draft.

Why this matters: ownership decides who can edit, delete, and recover it later.

Choices:
- A: User owns it.
- B: Team owns it.
- C: Project owns it.

Interaction Rules

  • Do not call the process "grilling" unless the user uses that word first.
  • Keep questions short and specific.
  • Do not ask broad open-ended questions unless unavoidable.
  • Do not ask multiple questions in one response.
  • Do not require the user to hold previous answers in memory.
  • Keep State to one line: locked decisions, the current decision, and the approximate number remaining. Summarize older decisions rather than letting the line grow.
  • Prefer examples over abstract categories.
  • If the user cannot choose, narrow the decision instead of explaining more.
  • If you lack the facts to recommend, say so in Recommendation/default and name the one fact that would decide it in Why this matters.
  • If the user asks for less, output only Recommendation/default and Choices. This is an explicit exception to the normal question format.
  • Keep tangents in a private parking lot. Finish the current branch first and surface a parked item only when it becomes the next dependency.
  • Make progress visible without praise or gamification.

Progress Format

Use this format:

text
Decision 2 of 6: Data ownership

Choose the total decision count conservatively. Prefer 4 to 6 decisions for a normal plan. Use fewer when the user asks for a shorter pass. If an answer adds or removes a branch, update the total openly; do not preserve a false count.

Undecided Sweep

Run this sweep before every ending, whether the walkthrough reaches the confirmation gate or pauses.

Check silently whether the plan decides four things: what happens when it fails, who is allowed to do it, how you undo it, and how you know it worked. List any that are undecided under Open. Do not turn the sweep into extra questions.

Confirmation Gate

When the decisions are sufficient, run the undecided sweep, stop asking decision questions, and show only:

  • Plan ready for confirmation
  • Decisions locked: the agreed decisions in no more than five bullets.
  • Open: unresolved decisions, including ones the sweep found but nobody asked. Use None only when the sweep found nothing.
  • Next action: exactly one small, atomic next action.
  • Confirmation: ask the user to approve the summary or name one change.

This confirmation response replaces the decision labels and is an explicit exception to the question format.

Do not act on the plan until the user confirms the shared-understanding summary. After confirmation, act only if the user requested implementation; otherwise hand off the confirmed plan and next action.

Stop Conditions

Pause the decision walkthrough when:

  • The next decision depends on missing information.
  • The user asks to pause, stop, or end the walkthrough.

When pausing, run the undecided sweep and summarize only:

  • Decisions made.
  • Open decisions, including ones the sweep found but nobody asked. Use None only when the sweep found nothing.
  • One small, atomic next action.

Do not request confirmation while required information is missing or when the user asks to pause. Preserve the state so the next turn can resume from one decision.

Frequently asked questions

What does the Plan Compass AI skill do?

Stress-tests a plan through dependency-aware, easy-to-answer decision prompts. Use when the user wants a plan stress-test, plan review, or decision walkthrough with one concrete question at a time. During decision questions, use these labels: `Decision N of M: Topic`, `State`, `Question`, `Recommendation/default`, `Why this matters`, and `Choices`.

Why use Plan Compass on TypingMind?

Because you install it once and use it with any model. Plan Compass 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 Plan Compass in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/softcane/human-state-skills/tree/main/.agents/skills/plan-compass. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Plan Compass?

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 Plan Compass?

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

Is the Plan Compass AI skill free?

Yes. It is published on GitHub by softcane under the MIT license. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇