SKILLEMALL.ai
RU Sign in

AC micropython-skills

Program and interact with embedded development boards (ESP32, ESP32-S3, ESP32-C3, ESP8266, NodeMCU, Raspberry Pi Pico, RP2040, STM32) through real-time REPL. This skill turns microcontroller hardware into an AI-programmable co-processor — read sensors, control actuators, flash firmware, diagnose devices, and deploy algorithms. Trigger when the user mentions any dev board or hardware interaction: ESP32, ESP8266, NodeMCU, Pico, 开发板, 板子, 单片机, 嵌入式, microcontroller, development board, sensor reading, GPIO, LED, motor, relay, I2C, SPI, UART, ADC, PWM, servo, DHT, BME280, temperature sensor, 传感器, 读传感器, 控制电机, 继电器, flash firmware, 烧录, 刷固件, 刷机, mpremote, MicroPython, IoT, MQTT, WiFi on board, 设备没反应, device not responding, or any task involving programming or controlling a physical microcontroller board.

ClawHub Agent Skills author: 0x1abin v1.0.0 MIT-0 15 files body ≈ 3 215 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
95
Quality 40%
88
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 5

    ✓ No critical or high findings

    Medium and low: 5
    • low Dangerous commands cmd-privilege scripts/device_probe.py:244
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      return None, f"Permission denied on {port}. Run: sudo chmod 666 {port}"
      code literal
    • low Dangerous commands cmd-privilege scripts/device_probe.py:344
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      else f"Run: sudo chmod 666 {port}"
      code literal
    • low Dangerous commands cmd-privilege scripts/firmware_flash.py:94
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      return None, f"Permission denied on {port}. Run: sudo chmod 666 {port}"
      code literal
    • low Dangerous commands cmd-privilege SKILL.md:64
      Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
      - `status: "permission_denied"` → Serial port not accessible. On Linux: `sudo chmod 666 /dev/ttyACM0`. On Windows: check Device Manager for driver issues.
      quoted
    • low Dangerous commands cmd-eval-dynamic SKILL.md:212
      Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
      mpremote exec "exec(open('my_program.py').read())"
      quoted

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 59/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 7 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 52 steps, 1 vague phrases
    • 100Failures and branches. 5 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3215 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 13 top-level sections: this looks like several domains in one skill
    • medium 5 test cases, all positive: not one "should refuse" or "should ask first"
    • low No test case covers injection arriving through data

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 804: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 52 items
    • +4Has examples (11 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 4 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: suspicious
    This is a legitimate MicroPython hardware-control skill, but it needs review because it can persistently modify devices, enable remote access, expose credentials, and recommends unsafe serial-port permissions.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026