129 skills · sorted by relevance
Examine Windows shortcuts and Jump Lists, records of recently used files, to reconstruct user activity. Extract paths, timestamps, and device details with LECmd and JLECmd, including traces that remain after target files are deleted.
Connect to and acquire images from cameras in MATLAB using Image Acquisition Toolbox. Use this skill when the user wants to: use a webcam, acquire images, capture video, stream from a camera, connect to a GigE Vision camera, preview live video, list available cameras, configure camera properties, use a CoaXPress frame grabber, or use a Camera Link frame grabber. Covers USB webcams, GigE Vision, USB3 Vision, CoaXPress, Camera Link, and GenICam-compliant cameras. Always prefer videoinput from Image Acquisition Toolbox over webcam support package or gigecam.
The English summary is being prepared. Showing the original description.
Firmware development for the Guition JC-ESP32P4-M3-DEV board (JC-ESP32P4-M3 module — ESP32-P4NRW32 with 32 MB in-package PSRAM, 16 MB flash, and an ESP32-C6 radio co-processor on SDIO) — its MIPI-DSI panel and MIPI-CSI camera connectors, IP101 Ethernet, ES8311 codec with speaker amplifier and microphone, microSD on SDMMC, RS485, three USB-C sockets, the 26-pin JP1 header, and the PlatformIO + ESP-IDF (pioarduino) setup around them. Use when working on this board or any ESP32-P4 devkit: project setup, platformio.ini and sdkconfig.defaults, the silicon revision split between rev v1.3 and rev v3.x, why the bootloader dies with "Illegal instruction", the pin map and which header pins are traps, Wi-Fi through esp_hosted and esp_wifi_remote, mounting the TF card and its on-chip LDO, bringing up a DSI panel, the shared I2C bus, audio direction and the amplifier enable, Ethernet RMII pins, choosing a free GPIO, flashing over any of the three USB-C ports, or debugging why something on the board does not work.
The English summary is being prepared. Showing the original description.
Firmware development for the Raspberry Pi Pico (original, RP2040 — dual Cortex-M0+ @ 133 MHz, 264 KB SRAM, 2 MB QSPI flash) — its 26 exposed GPIO, 4-channel 12-bit ADC, 16-channel PWM, 2× UART/I2C/SPI, PIO state machines, USB 1.1 CDC, VSYS/VBUS/SMPS power wiring, and the PlatformIO + arduino-pico (earlephilhower) setup around them. Use when working on this board, any Pico H or Pico clone, or a bare RP2040: project setup, platformio.ini, the earlephilhower-vs-Mbed core choice, pin mapping, USB CDC serial, analogRead/analogWrite behaviour, Wire/SPI defaults, battery power, EEPROM emulation, BOOTSEL/UF2 flashing, or debugging why something on the board does not work.
The English summary is being prepared. Showing the original description.
Firmware development for the Arduino Nano (A000005, ATmega328P @ 16 MHz, 5 V) — its 30 KB usable flash, 2 KB SRAM, 1 KB EEPROM, 8-channel 10-bit ADC, six 8-bit PWM pins across three timers, UART shared with the USB-serial chip, I2C on A4/A5, SPI on D10–D13, sleep modes, and the Arduino AVR core + PlatformIO setup around them. Use when working on this board or any ATmega328P Nano clone (FTDI or CH340 USB): project setup, platformio.ini, old-vs-new bootloader uploads, pin mapping, A6/A7 restrictions, timer/Servo/tone conflicts, the 2 KB SRAM budget, analog references, powering from VIN, ICSP recovery, or debugging why something on the board does not work.
The English summary is being prepared. Showing the original description.
Firmware development for the ESP32-C3 0.42" OLED board (ESP32-C3FH4, QFN32) — the ABRobot / 01Space "ESP32-C3-0.42LCD" mini board and its clones, sold as "ESP32-C3 SuperMini with OLED" and "ESP32 C3 OLED development board". Covers its 72x40 SSD1306 OLED on I2C, the single I2C bus, blue LED on GPIO8, BOOT button on GPIO9, USB Serial/JTAG console, ADC1, Wi-Fi/BLE, and the ESP-IDF + PlatformIO setup around them. Use when working on this board or a bare ESP32-C3: project setup, platformio.ini and sdkconfig, pin mapping and strapping pins, getting the 0.42-inch display to show something other than snow, U8g2 offsets, adding a second I2C device, flashing over USB-C, or debugging why something on the board does not work.
The English summary is being prepared. Showing the original description.
PXE/netboot 経由で Debian + HW RAID10 を自動インストール (OpenWrt ローカル TFTP + embed ipxe.efi + IPv4 リテラル mirror)。BMC USB redirector が累積劣化した機種 (TX1320 M3 等) や、 cross-site 拠点の install に使う。phase 19 で training-tx1320 で完遂、 物理操作なしで自力 SSH まで到達。
The English summary is being prepared. Showing the original description.
スタックチャン・アタマ（M5Stack単体版）をUSBシリアルまたはWiFi HTTP API経由で制御するスキル。テキスト読み上げ・表情変更・音量調整・カメラ撮影・WAV再生をPCからコマンド実行。パイプライン再生で高速応答。borotの返答をスタックチャンに喋らせる連携にも対応。「スタックチャンに喋らせて」「stackchan-atama」で使用。
The English summary is being prepared. Showing the original description.
Erstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.
The English summary is being prepared. Showing the original description.
VISONSDK ドローン (54X / KF615 系) を PC から操縦・映像確認・顔追従するクライアント群。 iPhone 上の iOS アプリ (test.app) が制御サーバー (TCP 8080) と MJPEG 映像サーバー (HTTP 8081/stream) を提供し、USB 越しに iproxy で PC に転送する。「ドローンを飛ばす」「ドローン映像を見る」 「ドローンに顔を追わせる」「離陸/着陸/スティック操作」などで使う。
The English summary is being prepared. Showing the original description.
Test SwiftUI apps on a real iPhone or iPad by repeatedly capturing screens, analyzing them, taking actions, and verifying results. An embedded HTTP server enables interaction, with optional remote access through Tailscale.
Investigate unclear failures, intermittent behavior, and performance regressions before changing code. Separate symptoms from assumptions, trace how failures arise, and rank possible causes by evidence and ease of testing, then report the cause and supporting proof.
Locate relevant code in an unfamiliar repository or after a direct search fails. This read-only explorer returns a short list of file paths, verified line ranges, and relevance notes for another agent to use.
Compress agent replies into short phrases while preserving technical details, negations, numbers, and exact commands. Use it to reduce repeated explanations and keep chat responses brief until you explicitly turn the mode off.
Turn a Caveman token-usage report into specific edits to instruction files, repeated context, and memory. Review each proposed change before approval, then measure the result and distinguish confirmed file reductions from less certain session-level effects.
Evaluate Caveman optimization observations by selecting a specific code change with operator approval. Compare the original and changed versions on identical inputs, checking both task quality and resource usage before deciding whether to keep the change.
Create short commit messages using Conventional Commits, a format that labels the type of change. Emphasize intent, keep the subject concise, and include explanatory text when breaking changes, security fixes, data migrations, or reversions require context.
Make agent replies shorter and easier to scan by putting answers first and removing filler. Preserves technical details, exact commands, numbers, and essential conditions while keeping the user's chosen language.
Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.
Verify that existing work meets its acceptance conditions using the smallest sufficient set of checks. Reuse results that still match the repository state, report outcomes precisely, and stop once the evidence is complete without adding unrelated work.
Build a narrowly scoped feature or integration using existing repository structures. Define observable acceptance criteria and non-goals, complete the working path across relevant layers, and stop when focused checks confirm the requested outcome.
Delegate code lookup, small edits, and diff reviews to three specialized subagents. Their compact, structured results help conserve the main agent's context, with guidance on when to delegate and when to keep work in the main conversation.
Fix bugs and small behavior changes by tracing the cause and editing the smallest responsible part of the code. Preserve surrounding behavior and existing user changes, then run focused checks to confirm the fix and guard against recurrence.
Look up commands for concise response modes, commit messages, review comments, and Markdown compression. The reference also explains how to check the current mode, return to normal responses, and configure startup defaults.