MCPInstall

raspberry-pi-pico2

by sammcjAI & Agents

Use when developing with Raspberry Pi Pico 2 or the Pi Debug Probe.

Installs
82
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/sammcj/agentic-coding --skill raspberry-pi-pico2
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads raspberry-pi-pico2 automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Raspberry Pi Pico 2 and Debug Probe

This skill covers development with Raspberry Pi Pico 2 (RP2350) boards and the Raspberry Pi Debug Probe. It includes hardware specs, SDK setup, build configuration, debugging workflows, and common pitfalls.

Reference Files

Consult these for detailed technical content. Read only the file relevant to the current task:

  • references/pico2-hardware.md - RP2350 specs, RP2040 vs RP2350 comparison, pin layout, wireless variant, security features, chip variants
  • references/debug-probe.md - Debug Probe hardware, wiring diagrams, OpenOCD setup, GDB workflow, UART serial, RTT, VS Code integration, rescue mode, troubleshooting
  • references/sdk-toolchain.md - pico-sdk setup, CMake configuration, ARM vs RISC-V builds, picotool commands, MicroPython/CircuitPython, project structure

Quick Reference

Board Selection (CMake)

BoardCMake FlagPlatform
Pico 1-DPICO_BOARD=pico (default)rp2040
Pico 1 W-DPICO_BOARD=pico_wrp2040
Pico 2-DPICO_BOARD=pico2rp2350-arm-s
Pico 2 W-DPICO_BOARD=pico2_wrp2350-arm-s
Pico 2 RISC-V-DPICO_BOARD=pico2 -DPICO_PLATFORM=rp2350-riscvrp2350-riscv

Debug Probe Wiring (SWD)

Debug Probe "D" PinWire ColourPico 2 SWD Pad
SCOrangeSWCLK
GNDBlackGND
SDYellowSWDIO

Debug Probe Wiring (UART)

Debug Probe "U" PinWire ColourPico 2 PinGPIO
TXOrangePin 2GP1 (RX)
RXYellowPin 1GP0 (TX)
GNDBlackPin 3GND

Note the crossover: probe TX to Pico RX, probe RX to Pico TX.

OpenOCD Target Configs

TargetConfig File
Pico 1 (RP2040)target/rp2040.cfg
Pico 2 (RP2350)target/rp2350.cfg
Pico 2 RISC-Vtarget/rp2350.cfg with -c "set USE_CORE { rv0 rv1 }"
Rescue (RP2350)target/rp2350.cfg with -c "set RESCUE 1"

Typical Debug Session

# Terminal 1: OpenOCD
openocd -f interface/cmsis-dap.cfg -f target/rp2350.cfg -c "adapter speed 5000"

# Terminal 2: GDB
arm-none-eabi-gdb my_app.elf
(gdb) target remote localhost:3333
(gdb) monitor reset init
(gdb) load
(gdb) break main
(gdb) continue

Flash via SWD

openocd -f interface/cmsis-dap.cfg -f target/rp2350.cfg \
  -c "adapter speed 5000" \
  -c "program my_app.elf verify reset exit"

Use the .elf file for SWD flashing, not .uf2.

Gotchas

These are the most common mistakes and non-obvious behaviours. Pay close attention.

  1. SDK defaults to Pico 1. You must explicitly pass -DPICO_BOARD=pico2 to target RP2350. Forgetting this builds for RP2040 and the binary will not run on a Pico 2.

  2. Use the Raspberry Pi fork of OpenOCD. Upstream OpenOCD (0.12.0) lacks full RP2350 support. Clone from https://github.com/raspberrypi/openocd.git branch rpi-common.

  3. Wrong target config = failed connection. Using rp2040.cfg with a Pico 2 silently fails. Always match the target config to the chip.

  4. SWD uses .elf, BOOTSEL uses .uf2. These are different formats for different flashing methods. Do not try to flash a .uf2 via OpenOCD/SWD.

  5. Debug builds required for meaningful debugging. Always pass -DCMAKE_BUILD_TYPE=Debug to cmake. Release builds optimise away variable state and reorder code, making breakpoints unreliable.

  6. RISC-V mode has no FPU. The hardware floating-point unit is only available on Cortex-M33. RISC-V mode uses software float, which is significantly slower for float-heavy code.

  7. RISC-V requires a clean build directory. When switching between ARM and RISC-V, delete the build directory and re-run cmake. In-place switching does not work.

  8. RISC-V debugging requires pre-selection. The RP2350 boots into Cortex-M33 by default. To debug RISC-V: picotool reboot -u -c riscv, then use OpenOCD with set USE_CORE { rv0 rv1 }.

  9. Debug Probe does not power the target. The Pico 2 must be powered via its own USB or VSYS. The SWD connector carries no power.

  10. LED pin differs on wireless models. Non-wireless Pico 2 uses GP25 for the onboard LED. Pico 2 W uses WL_GPIO0 through the CYW43439 wireless chip. Code must be conditional.

  11. Git submodules are required. The pico-sdk needs git submodule update --init to pull tinyusb, cyw43-driver, lwip, btstack, and mbedtls. Missing submodules cause cryptic build failures.

  12. OTP is irreversible. Writing OTP bits is permanent. Misconfiguring secure boot (setting SECURE_BOOT_ENABLE without a boot key and with PICOBOOT disabled) permanently bricks the device.

  13. Wireless SPI pin sharing. On Pico 2 W, the VSYS ADC reading and CYW43439 IRQ checking are blocked during SPI transactions to the wireless chip.

  14. Connect GND first. When the Pico 2 is powered from a separate source, connect GND between the target and Debug Probe before any signal lines. Voltage differences can damage the probe.

  15. macOS: OpenOCD needs hidapi and libusb. Install via brew install hidapi libusb. If OpenOCD cannot find the probe, check no other process (VS Code, another OpenOCD instance) holds the USB device.

  16. Multiple debug probes. If multiple CMSIS-DAP devices are connected, specify the serial number: adapter serial <serial_number> in your OpenOCD config.

FAQ

What does the raspberry-pi-pico2 skill do?

Use when developing with Raspberry Pi Pico 2 or the Pi Debug Probe.

How do I install raspberry-pi-pico2?

Run npx skills add https://github.com/sammcj/agentic-coding --skill raspberry-pi-pico2 in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/raspberry-pi-pico2/ (personal) or .claude/skills/raspberry-pi-pico2/ (project).

Which AI agents can use raspberry-pi-pico2?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is raspberry-pi-pico2 safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains raspberry-pi-pico2?

It is published by sammcj in sammcj/agentic-coding. It has 82 recorded installs.

More from sammcj/agentic-coding

View all →

critical-thinking-logical-reasoning

sammcj/agentic-coding

Critically analyse the reasoning in written content (articles, blogs, transcripts, reports), not code. Use only when explicitly asked to critically analyse or critique an argument.

AI & Agents2.4K installs

writing-documentation-with-diataxis

sammcj/agentic-coding

Applies the Diataxis framework to create or improve technical documentation. Use when being asked to write high quality tutorials, how-to guides, reference docs, or explanations, when reviewing documentation quality, or when deciding what type of documentation to create. Helps identify documentation types using the action/cognition and acquisition/application dimensions.

Docs & Writing615 installs

creating-development-plans

sammcj/agentic-coding

Creates structured development plans with phased task breakdowns, requirements, and QA checklists. Use when the user explicitly asks to create a dev plan, development plan, or document development requirements.

Code Quality & Workflow330 installs

ghostty-config

sammcj/agentic-coding

Open the skill to read its SKILL.md instructions.

AI & Agents221 installs

code-simplification

sammcj/agentic-coding

Open the skill to read its SKILL.md instructions.

AI & Agents203 installs

prompt-enhancer

sammcj/agentic-coding

Open the skill to read its SKILL.md instructions.

AI & Agents184 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs