Pi Dashboard Control logo

Pi Dashboard Control

Organization
BlackBeltTechnology
pi-dashboard-control

Control the local pi-dashboard over its REST API with curl - list pi sessions, send a prompt, abort a run, spawn a session. Use after pi-dashboard-bootstrap has printed BASE, whenever the user wants to see or steer pi sessions.

Overview

PublisherBlackBeltTechnology
Repositorypi-agent-dashboard
Skill namepi-dashboard-control
Stars
330
Forks
51
Bundled files
2
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.

  • 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 BlackBeltTechnology on GitHub. Read the source before you install it.

Installation

Install the Pi Dashboard Control 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/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/claude-plugin/skills/pi-dashboard-control
  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/BlackBeltTechnology/pi-agent-dashboard.git /tmp/pi-agent-dashboard
mkdir -p .claude/skills
cp -r /tmp/pi-agent-dashboard/packages/claude-plugin/skills/pi-dashboard-control .claude/skills/pi-dashboard-control
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pi Dashboard Control 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 Pi Dashboard Control 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 Pi Dashboard Control 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.

Control pi sessions through the dashboard

Run pi-dashboard-bootstrap first and use its literal BASE (for example http://localhost:8000). REST is the command path. Full endpoint list: references/api-reference.md.

bash
curl -s BASE/api/health
curl -s BASE/api/sessions
curl -s -X POST BASE/api/session/ID/prompt -H 'Content-Type: application/json' -d '{"text":"run the tests"}'
curl -s -X POST BASE/api/session/ID/abort -H 'Content-Type: application/json' -d '{}'
curl -s -X POST BASE/api/session/spawn -H 'Content-Type: application/json' -d '{"cwd":"/path/to/project"}'

Take ID from GET /api/sessions. Replace BASE with the literal URL every time.

View a session in the browser

To show a session to the user, list sessions and open that row's uiUrl (or diffUrl for the changes view) in your browser pane:

bash
curl -s BASE/api/sessions
  1. Use the full id, or the row's uiUrl / diffUrl, exactly as listed. Never shorten the id: build BASE/session/<full id> only when you have no uiUrl. When auth is on, this listing follows the token rules in "When a call is refused" below. The sign-in in the pane is separate and gives you no token.
  2. Add ?embed=1 for a narrow pane: the page then shows the session without the session list.
  3. If the page asks to sign in, ask the user to sign in inside the pane. Never put a token or any credential in a URL.
  4. "Session not found" means a wrong, shortened or archived id: list again and use a full id. A session that is no longer listed is in GET /api/sessions/archived (50 per page: while the response has a nextCursor, request the next page with ?cursor=<nextCursor> until you find it): open BASE/session/<full id>?archived=1.

Other pages (folders, OpenSpec board and archive) are listed in the "UI routes (browser)" section of references/api-reference.md.

When a call is refused

A 401, or a 403 with "reason":"local_proof_required", means the dashboard needs a token. Ask the user to run:

bash
pi-dashboard token create --label claude-code --tier control

control covers prompt, spawn and abort. Ask for a higher tier only if the user explicitly wants one.

Preferred: the user saves the line Authorization: Bearer <token> in a file they create with owner-only permissions and tells you its path. Never create that file yourself. Send every credentialed request in the same command as a verification, so credentials only reach a verified dashboard:

bash
sh "${CLAUDE_SKILL_DIR}/../pi-dashboard-bootstrap/scripts/ensure-dashboard.sh" --check && curl -s -H @/path/to/header-file BASE/api/sessions

Otherwise accept a token the user pastes, send it only as an Authorization: Bearer header, and never write it to a file or repeat it in output. Tell the user it then stays in the conversation history.

Never add curl verbose or trace options to credentialed requests: they print the header.

Bundled files

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

Frequently asked questions

What does the Pi Dashboard Control AI skill do?

Control the local pi-dashboard over its REST API with curl - list pi sessions, send a prompt, abort a run, spawn a session. Use after pi-dashboard-bootstrap has printed BASE, whenever the user wants to see or steer pi sessions.

Why use Pi Dashboard Control on TypingMind?

Because you install it once and use it with any model. Pi Dashboard Control 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 Pi Dashboard Control in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/claude-plugin/skills/pi-dashboard-control. 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 Pi Dashboard Control?

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 Pi Dashboard Control?

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

Is the Pi Dashboard Control AI skill free?

Yes. It is published on GitHub by BlackBeltTechnology 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 👇