Raspberrypi Local logo

Raspberrypi Local

Community
Firstp1ck
raspberrypi-local

Use automatically for Raspberry Pi computers, Raspberry Pi OS, Raspberry Pi Imager, raspi-config, config.txt/cmdline.txt, GPIO, HATs/accessories, camera/rpicam/libcamera/Picamera2, SSH/VNC/Connect, bootloader/EEPROM/NVMe/USB boot, Compute Module, Pico/RP2040/RP2350/Pico SDK/MicroPython, and Raspberry Pi documentation questions. Prefer local Raspberry Pi Documentation evidence via raspberrypi_wiki tools before web sources.

Overview

PublisherFirstp1ck
Repositorypi-coding-agent-forge
Skill nameraspberrypi-local
Stars
93
Forks
22
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 Firstp1ck on GitHub. Read the source before you install it.

Installation

Install the Raspberrypi Local 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/Firstp1ck/pi-coding-agent-forge/tree/main/pi-extension-raspberrypi-wiki-local/skills/raspberrypi-local
  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/Firstp1ck/pi-coding-agent-forge.git /tmp/pi-coding-agent-forge
mkdir -p .claude/skills
cp -r /tmp/pi-coding-agent-forge/pi-extension-raspberrypi-wiki-local/skills/raspberrypi-local .claude/skills/raspberrypi-local
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Raspberrypi Local 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 Raspberrypi Local 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 Raspberrypi Local 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.

Raspberry Pi Documentation Local Wiki

Use the local official Raspberry Pi Documentation corpus before web sources. Optimize for source-backed answers with bounded output and local path citations.

Corpus profile

  • Local checkout path: ~/.raspberrypiwiki
  • Indexed source: official raspberrypi/documentation repository, primarily documentation/asciidoc/
  • Parser/format: AsciiDoc
  • Indexed extensions: .adoc, .asciidoc, .asc
  • Setup command: /raspberrypi-wiki-local-setup
  • Smoke test: /raspberrypi_wiki-smoke-test or raspberrypi_wiki_smoke_test({ maxSearchResults: 5 })

The repository contains source files used to build the public Raspberry Pi Documentation site. It also has build/tooling Markdown files; the local wiki intentionally indexes only AsciiDoc documentation files to avoid build-doc noise in support searches.

Confidence target

Aim for 90-95/100 confidence by combining local documentation evidence, exact section citations, read-only local evidence when relevant, and explicit caveats when docs/output are incomplete.

If confidence is below 90/100, improve it by searching a second wording, listing sections, extracting exact sections, checking related pages, checking official online docs for freshness, or asking for missing hardware/OS details.

Required workflow

  1. Start with raspberrypi_wiki_search({ query, limit: 5, includeSnippets: false }).
  2. If the page is large or aggregate-like, run raspberrypi_wiki_sections({ page, maxSections: 40-80 }).
  3. Prefer exact section extraction for final evidence:
    • raspberrypi_wiki_extract({ page, section, maxChars: 4000-8000, maxSections: 2-5 })
  4. Use query extraction only for exploration, then switch to exact headings when available.
  5. Use raspberrypi_wiki_read({ page, maxChars }) only for broad context or when no relevant heading is identifiable.
  6. Use raspberrypi_wiki_related({ page, limit: 5-10 }) when the issue spans linked topics.
  7. Run read-only local diagnostics when system/project evidence is relevant.
  8. Compare documentation guidance with observed local state.
  9. Cite local paths and section names in final answers.
  10. Ask before destructive, persistent, hardware-risk, or user-facing changes.

Search hints

Use specific Raspberry Pi terms and current tool names:

  • SSH/headless: ssh headless setup, raspi-config ssh, imager remote access.
  • Camera: rpicam libcamera picamera2, rpicam options, camera_auto_detect, camera module.
  • Boot/config: config.txt dtoverlay dtparam, cmdline.txt, device tree overlay.
  • GPIO: gpio pinout pinctrl, 40-pin header, raspi-gpio.
  • Storage/boot: nvme boot pi 5, usb boot, bootloader eeprom BOOT_ORDER.
  • Network/remote desktop: wifi networkmanager nmcli, vnc, raspberry pi connect.
  • Pico/microcontrollers: pico sdk blink, rp2040, rp2350, micropython.
  • Accessories/HATs: include the product name, e.g. sense hat, ai camera, m.2 hat+.

Source priority

  1. Local Raspberry Pi Documentation corpus via raspberrypi_wiki_* tools.
  2. Local project/system evidence relevant to the user's current Raspberry Pi or host environment.
  3. Official online Raspberry Pi Documentation/GitHub only when local docs are missing, stale, or insufficient.
  4. Other sources only when necessary and clearly labeled.

Tool usage

  • raspberrypi_wiki_search({ query, limit, includeSnippets }): find candidate pages. Keep limit at 5 unless exploring broadly; snippets default off.
  • raspberrypi_wiki_sections({ page, maxSections }): inspect headings before extracting from large pages.
  • raspberrypi_wiki_extract({ page, section, maxChars, maxSections }): retrieve focused exact sections; best for final answers.
  • raspberrypi_wiki_extract({ page, query, maxChars, maxSections }): retrieve query-relevant sections; best for exploration.
  • raspberrypi_wiki_read({ page, maxChars }): retrieve broad page text; use sparingly.
  • raspberrypi_wiki_related({ page, limit }): discover linked local pages.
  • raspberrypi_wiki_smoke_test({ maxSearchResults }): verify parser/search/extract/read/related behavior after package or corpus updates.

Diagnostics policy

Prefer read-only commands first and only run commands relevant to the user's issue/environment. Useful Raspberry Pi diagnostics include:

bash
uname -a
tr -d '\0' </proc/device-tree/model 2>/dev/null || cat /proc/device-tree/model 2>/dev/null || true
cat /etc/os-release
vcgencmd version 2>/dev/null || true
vcgencmd get_throttled 2>/dev/null || true
command -v raspi-config >/dev/null && raspi-config nonint get_config_var arm_64bit /boot/firmware/config.txt 2>/dev/null || true
grep -RsnE '^(dtoverlay|dtparam|camera_auto_detect|display_auto_detect|arm_64bit|boot_order|program_usb_boot_mode)' /boot/config.txt /boot/firmware/config.txt 2>/dev/null || true
ip -brief addr 2>/dev/null || true
systemctl status ssh --no-pager 2>/dev/null || true
lsblk -f 2>/dev/null || true

For Pico/Pico SDK work, prefer read-only project checks first:

bash
cmake --version 2>/dev/null || true
python3 --version 2>/dev/null || true
printenv PICO_SDK_PATH PICO_TOOLCHAIN_PATH 2>/dev/null || true
find . -maxdepth 3 -name CMakeLists.txt -o -name pico_sdk_import.cmake 2>/dev/null

Safety policy

Ask before mutation, especially:

  • Editing /boot/firmware/config.txt, /boot/config.txt, /boot/firmware/cmdline.txt, EEPROM/bootloader configuration, NetworkManager profiles, or system services.
  • Running rpi-eeprom-update, rpi-update, firmware flashing, SD-card/USB/NVMe imaging, partitioning, formatting, or boot-order changes.
  • Installing/removing packages, enabling remote access, changing passwords/SSH keys, or exposing services to a network.
  • GPIO, HAT, camera, display, or power-supply wiring changes. Tell the user to power down before physical wiring changes when appropriate.

Do not assume non-Raspberry-Pi Linux hosts behave like Raspberry Pi OS. Verify model, OS release, boot path, and relevant commands first.

Token/output discipline

  • Keep search limits small (limit: 5-10) and leave snippets off unless they are needed.
  • Prefer search -> sections -> exact section extract for final answers.
  • Use query extraction only to discover likely sections on large pages.
  • Use maxChars around 4000-8000 and maxSections around 2-5 for focused answers.
  • Use read only when the relevant section cannot be identified.
  • If a tool reports omittedSectionCount or truncated: true, mention it when it affects confidence.

Citation format

Use local source citations like:

txt
Sources:
- ~/.raspberrypiwiki/documentation/asciidoc/computers/remote-access/ssh.adoc — Enable the SSH server
- ~/.raspberrypiwiki/documentation/asciidoc/computers/raspberry-pi/boot-nvme.adoc — NVMe SSD boot

Frequently asked questions

What does the Raspberrypi Local AI skill do?

Use automatically for Raspberry Pi computers, Raspberry Pi OS, Raspberry Pi Imager, raspi-config, config.txt/cmdline.txt, GPIO, HATs/accessories, camera/rpicam/libcamera/Picamera2, SSH/VNC/Connect, bootloader/EEPROM/NVMe/USB boot, Compute Module, Pico/RP2040/RP2350/Pico SDK/MicroPython, and Raspberry Pi documentation questions. Prefer local Raspberry Pi Documentation evidence via raspberrypi_wiki tools before web sources.

Why use Raspberrypi Local on TypingMind?

Because you install it once and use it with any model. Raspberrypi Local 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 Raspberrypi Local in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Firstp1ck/pi-coding-agent-forge/tree/main/pi-extension-raspberrypi-wiki-local/skills/raspberrypi-local. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Raspberrypi Local?

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 Raspberrypi Local?

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

Is the Raspberrypi Local AI skill free?

Yes. It is published on GitHub by Firstp1ck 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 👇