效率提升技能

Orchestrates full project lifecycle by auto-detecting state and routing to the correct phase. Use when starting or resuming a project mid-workflow.

中文简介正在准备中。当前显示原文说明。

Cut or check Runner nightlies — one workflow for macOS and Windows, one public prerelease per channel (nightly from main, remote-nightly from the nightly-remote umbrella), shared stamp, and separate stable feeds

中文简介正在准备中。当前显示原文说明。

Show Honey's benchmark scoreboard — the committed quality and token results per task tier (code, user-facing, agent-to-agent) from bench/. Reports only the reproducible committed figures, never invents per-repo numbers. Use when asked how much Honey saves, how it compares to Caveman / Ponytail / no-skill baseline, or for the headline numbers.

中文简介正在准备中。当前显示原文说明。

Show Honey's benchmark scoreboard: committed quality and token results per task tier vs Caveman, Ponytail, and no-skill. One-shot.

中文简介正在准备中。当前显示原文说明。

Write less code and say less about it: YAGNI, stdlib-first, terse prose. Cuts agent token cost on every coding and writing task.

中文简介正在准备中。当前显示原文说明。

Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the orchestrator's context — come back compressed (Honey Lever 3). Use when a task is search-heavy or review-heavy, spans many files, or you want to keep the orchestrator's context small. Not for trivial one-file work.

中文简介正在准备中。当前显示原文说明。

Router for FunASR speech workflows: local transcription, subtitles, services, vLLM, normalization, and training/export.

中文简介正在准备中。当前显示原文说明。

Operate Flash Linear Attention package workflows: setup, kernels, layers/models, KDA/context parallel, and benchmarking.

中文简介正在准备中。当前显示原文说明。

Use FedML for setup, CLI operations, MLOps launch, distributed and federated training, model serving, and workflow orchestration.

中文简介正在准备中。当前显示原文说明。

Build, inspect, and reuse Featuretools automated feature engineering workflows for EntitySets, DFS, feature matrices, primitive authoring, feature inspection, and selection.

中文简介正在准备中。当前显示原文说明。

Route GenAI Processors tasks to the right workflow guide.

中文简介正在准备中。当前显示原文说明。

Routes face-alignment installation, import checks, landmark-detection workflows, and detector-backend selection.

中文简介正在准备中。当前显示原文说明。

Routes evo trajectory-evaluation workflows for APE/RPE, trajectory I/O, result analysis, configuration, and programmatic usage.

中文简介正在准备中。当前显示原文说明。

Use the einops Python package for readable tensor rearrangement, reductions, repetition, named-axis einsum, packing, framework layers, and repository maintenance workflows.

中文简介正在准备中。当前显示原文说明。

Use Docling to convert, parse, configure, extract, chunk, serve, and maintain document-processing workflows across Python APIs, CLI commands, optional pipelines, and repository edits.

中文简介正在准备中。当前显示原文说明。

Use DeepMind dm_control for MuJoCo simulation, Control Suite environments, PyMJCF models, Composer tasks, rendering, and high-level locomotion/manipulation workflows.

中文简介正在准备中。当前显示原文说明。

Use this skill for Hugging Face Diffusers tasks: pipeline inference, schedulers, adapters/loaders, training recipes, modular pipelines, conversion helpers, CLI checks, and repo maintenance.

中文简介正在准备中。当前显示原文说明。

Routes DI-engine users to the right workflow for CLI/config launches, serial and framework-based RL pipelines, and environment integration.

中文简介正在准备中。当前显示原文说明。

Load, generate, compile, rasterize, evaluate, train, and serve DeTikZify and Ti*k*Zero workflows.

中文简介正在准备中。当前显示原文说明。

Use Dipy for diffusion MRI IO, preprocessing, reconstruction, tractography, registration, visualization-aware workflows, and command-line operations.

中文简介正在准备中。当前显示原文说明。

Use Hugging Face Evaluate to load metrics, comparisons, and measurements; compute and combine results; run evaluator pipelines; create custom modules; troubleshoot optional dependencies, cache, Hub, and CLI workflows.

中文简介正在准备中。当前显示原文说明。

Use for Electricity Maps contrib parser development, capacity updates, zone/exchange configuration maintenance, and focused repo validation workflows.

中文简介正在准备中。当前显示原文说明。

Routes Distil-Whisper inference, PyTorch distillation training, and Flax reproduction workflows.

中文简介正在准备中。当前显示原文说明。

Route Torchreid deep-person-reid workflows for person re-identification training, evaluation, feature extraction, metrics, visualization, and model export.

中文简介正在准备中。当前显示原文说明。