autocompact-circuit-breaker
Break the autocompact retry loop after several consecutive failures to avoid hammering shared APIs.
legacy-modernization
Modernize legacy applications and codebases. Use for COBOL conversion, framework upgrades, and technical debt reduction.
component-version-upgrade
Upgrade Kokoro model, bot dependencies, or TTS components. TRIGGERS - upgrade kokoro, update model, upgrade bot, update dependencies, version bump, component update.
rdkit-conf
A standardized CLI wrapper for RDKit 3D/2D conformer generation that samples multiple conformers per molecule (ETKDGv3, default 10), optimizes each with a force field (MMFF94s/UFF), keeps the lowest-energy conformer, automatically falls back to 2D layout on total embedding failure with a printed warning, and writes results to SDF or XYZ format. USE WHEN you need to generate 3D (or 2D fallback) molecular geometries from SMILES datasets (.csv/.smi) for downstream tasks such as docking, visualization, or 3D-descriptor computation.
otel-ottl
OpenTelemetry Transformation Language (OTTL) expert. Use when writing or debugging OTTL expressions for any OpenTelemetry Collector component that supports OTTL (processors, connectors, receivers, exporters). Triggers on tasks involving telemetry transformation, filtering, attribute manipulation, data redaction, sampling policies, routing, or Collector configuration. Covers syntax, contexts, functions, error handling, and performance.
deepmd-finetune-dpa3
Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 model to a new downstream dataset. Supports fine-tuning from a self-trained DPA3 model (.pt checkpoint), from a multi-task pre-trained model, or from a built-in pretrained model downloaded via `dp pretrained download` (e.g., DPA-3.1-3M, DPA-3.2-5M). Covers single-task and multi-task fine-tuning workflows.
swap-router-aggregator
"Aggregate quotes from Uniswap V3/V4, ParaSwap, 0x, 1inch, and OKX for best execution."
dft-qe
Generate Quantum ESPRESSO DFT input tasks from a user-provided structure plus user-specified DFT settings. Use when the user wants to prepare QE calculations such as SCF, NSCF, relax, vc-relax, MD, bands, DOS, or phonons starting from a structure file or coordinates together with pseudopotentials, functional choice, cutoffs, k-point settings, smearing, spin/charge, and convergence parameters. This skill prepares the QE task only; use a separate submission skill such as dpdisp-submit to submit the generated task.
compact-bensz-skills
当用户明确要求“压缩/瘦身/精简某个 Agent Skill 的 Markdown 文档”“在不改变功能前提下降低 skill 上下文开销”时使用。先理解目标 skill 的真实能力与安全边界，再在忽略 `tests/`、`plans/` 以及目标 skill 的 `README.md`、`CHANGELOG.md` 的前提下，压缩 `SKILL.md`、`references/*.md` 等工作型 Markdown，并把中间产物隔离到 `.compact-bensz-skills/`。⚠️ 不适用：用户主要想新增功能、修复脚本逻辑、批量改代码、或只想压缩非 skill 文档。
esp32-arch-review
Review ESP32 firmware architecture for RTOS safety, memory management, error handling, and embedded best practices.
caffe-cifar-10
Guidance for building Caffe from source and training CIFAR-10 models. This skill applies when tasks involve compiling Caffe deep learning framework, configuring Makefile.config, preparing CIFAR-10 dataset, or training CNN models with Caffe solvers. Use for legacy ML framework installation, LMDB dataset preparation, and CPU-only deep learning training tasks.
gpt2-codegolf
Guidance for implementing neural network inference (like GPT-2) under extreme code size constraints. This skill should be used when tasks require implementing ML model inference in minimal code (code golf), parsing model checkpoints in constrained environments, or building transformer architectures in low-level languages like C with strict size limits.
llm-inference-batching-scheduler
Guidance for implementing batching schedulers for LLM inference systems with compilation-based accelerators. This skill applies when optimizing request batching to minimize cost while meeting latency thresholds, particularly when dealing with shape compilation costs, padding overhead, and multi-bucket request distributions. Use this skill for tasks involving batch planning, shape selection, generation-length bucketing, and cost-model-driven optimization for neural network inference.
pytorch-model-cli
Guidance for implementing CLI tools that perform inference using PyTorch models in native languages (C/C++/Rust). This skill should be used when tasks involve extracting weights from PyTorch .pth files, implementing neural network forward passes in C/C++, or creating standalone inference tools without Python dependencies.
torch-pipeline-parallelism
Guidance for implementing PyTorch pipeline parallelism for distributed model training. This skill should be used when tasks involve implementing pipeline parallelism, distributed training with model partitioning across GPUs/ranks, AFAB (All-Forward-All-Backward) scheduling, or inter-rank tensor communication using torch.distributed.
schemelike-metacircular-eval
Guide for building metacircular evaluators in Scheme-like languages. This skill applies when implementing interpreters that can interpret themselves, handling tasks involving eval/apply loops, environment management, closure implementation, and multi-level interpretation. Use for any metacircular evaluator, Scheme interpreter, or self-interpreting language implementation task.
largest-eigenval
Guidance for optimizing numerical linear algebra computations, particularly finding eigenvalues of small dense matrices faster than standard library implementations. This skill applies when the task involves performance optimization of matrix operations, beating numpy/scipy performance baselines, or writing high-performance numerical code with Cython/LAPACK.
build-cython-ext
Guidance for building and fixing Cython extensions, particularly for numpy compatibility issues. This skill should be used when tasks involve compiling Cython code, fixing deprecated numpy type errors, or resolving compatibility issues between Cython extensions and modern numpy versions (2.0+).
make-doom-for-mips
Guide for cross-compiling complex C programs (like DOOM) for embedded MIPS environments with custom VM runtimes. This skill applies when building software that targets MIPS architecture with limited stdlib support, custom syscall interfaces, or JavaScript-based VM execution environments. Use when cross-compiling games, applications, or any C code for constrained MIPS targets.