Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

espressif

@espressif source repo

12 published skills

  1. ▌
    Lcd Touch I2c Migration · espressif
    Use when migrating ESP Board Manager board definitions or application code from legacy dev_lcd_touch_i2c / type lcd_touch_i2c to generic dev_lcd_touch with type lcd_touch and sub_type i2c, including YAML field mapping, setup_device.c touch factory updates, and compatibility checks.
    0
    installs
  2. ▌
    Migrate To Esp Pylib · espressif bundle
    Migrates Espressif Python tools to the shared esp-pylib library. Use when the user explicitly asks to migrate to esp-pylib, replace duplicated code (FatalError, logging, console output options via set_console_options, set_info_stream, progress bars, collapsible log stages, byte progress or unbounded counters, IDE WebSocket, INI config, ROM ELF resolution, serial port discovery, DTR/RTS reset primitives, named reset sequences, Click ParamTypes and Click option classes), convert argparse CLIs to rich-click, remove dependencies superseded by an esp_pylib.* module, or troubleshoot common migration pitfalls (pinned stdout file vs TTY progress, soft_wrap defaults, terminal width in tests, logger prefix assertions in tests, leftover argparse imports after rich-click, breaking vs cosmetic API changes).
    0
    installs
  3. ▌
    Espdl Operator · espressif bundle
    End-to-end guide for implementing, testing, and optimizing neural network operators in the ESP-DL framework. Covers C++ module implementation, C reference kernels, SIMD assembly optimization, esp-ppq quantization strategy integration, Docker-based build/test, and inference result alignment between esp-dl and esp-ppq. Use this skill whenever the user wants to add a new operator, implement an operator, optimize an existing operator with SIMD, add quantization support for an operator, or test/validate operator correctness. Also triggers for "算子实现", "添加算子", "SIMD优化", "量化支持", "算子对齐" and similar phrases.
    0
    installs
  4. ▌
    Espdl Quantize · espressif bundle
    Iteratively tune esp-ppq QuantizationSetting to recover post-quantization accuracy on ESP-DL targets. Drives a closed loop of "baseline -> calibration × TQT(default) cartesian product -> distribution-aware residual fixes -> agent-driven open exploration -> re-evaluate" in the current Python environment, using a minimal user contract (calib dataloader + evaluate function). Generic across architectures (ResNet / EfficientNet / ViT / DETR / YOLO / LSTM and any esp-ppq-supported graph) — the search procedure is distribution-driven and does not depend on a specific network family. Method ordering is accuracy-first with a soft penalty for passes that slow down on-device inference; once the prescribed Phase-1/2/3 sequence exhausts, the skill hands control to the agent (Phase 5) with a structured history of improving levers + the per-iteration error artifacts to read, so the agent can compose multi-knob iterations (lever stacking, calibration cross-pollination, ablation, cost-trim) without a rigid template. LSQ on PO
    0
    installs
  5. ▌
    Esp32p4 Simd · espressif bundle
    ESP32-P4 PIE (Processor Instruction Extensions) SIMD instruction set reference and optimization guide. Use when working with ESP32-P4 custom AI/DSP SIMD instructions in assembly orintrinsic form, converting scalar code to vectorized SIMD code, or implementing neural network operators for esp-dl. Covers read/write, data exchange, arithmetic, comparison, bitwise logical, shift, and FFT-dedicated instructions with 128-bit QR vector registers.
    0
    installs
  6. ▌
    Esp32 S3 Pie Simd Optimization · espressif bundle
    ESP32-S3 Processor Instruction Extensions (PIE) SIMD reference for accelerating C code. Use when converting scalar C loops into PIE SIMD assembly (EE.* instructions). Covers 128-bit QR registers, vector arithmetic, MAC, non-aligned data, FFT, and common patterns. Target chip: ESP32-S3 (Xtensa LX7 with TIE extensions).
    0
    installs
  7. ▌
    Deploy · espressif
    Run make deploy targeting the region/profile from AWS_REGION/AWS_PROFILE if set, else the default AWS profile and its configured region. Supports per-stack-group deploys.
    0
    installs
  8. ▌
    Run Tests · espressif
    Run make test to green first, then make itest; report all failures and re-run failing tests one by one to form an RCA and fix where the cause is clear.
    0
    installs
  9. ▌
    Sync Docs · espressif
    Sync API definitions (swagger YAMLs) and specs (docs/en/specs/) with the code on the current branch, documenting any new/changed features the branch introduces.
    0
    installs
  10. ▌
    Mr Template · espressif
    Generate a review-optimized MR/PR description from the diff between the current branch and main, following the repo's git-flow conventions. Use when opening a merge request, drafting a PR description, or summarizing a branch for review.
    0
    installs
  11. ▌
    Commit Message · espressif
    Generate a commit message for the currently **staged** changes.
    0
    installs
  12. ▌
    Implementation Plan · espressif
    Analyse design/brainstorming docs, compare with implementation, create/update comprehensive implementation plan with progress tracking
    0
    installs