GITHUB AGENT SKILLS / 技能收录

给你的 AI 助手
装上专业技能

我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

LOrdEnRYQuE
LOrdEnRYQuE/LRDEnE-Ai-Specialist

architecture

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

★ 0
LOrdEnRYQuE
LOrdEnRYQuE/LRDEnE-Ai-Specialist

templates

Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.

★ 0
LOrdEnRYQuE
LOrdEnRYQuE/LRDEnE-Ai-Specialist

app-builder

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

★ 0
LOrdEnRYQuE
LOrdEnRYQuE/LRDEnE-Ai-Specialist

api-patterns

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.

开发工程师后端与接口
★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

reflect

Mid-conversation reflection skill that pauses execution and zooms out from detail-mode to honestly reassess direction, assumptions, and bias. Use when the user says 'reflect', 'take a step back', 'step back', 'zoom out', 'are we missing something', 'bigger picture', 'sanity check this', 'are we on track', 'are we overthinking this', 'forest for the trees', or any variation signaling intent to break out of detail-mode and reassess. Also trigger when the conversation has gone deep on implementation details without strategic check-in, or when the user shows signs of being stuck — that's often a signal the framing needs a reset, not more detail work. Intentionally low-intake: runs the 5-dimension analysis immediately when prior context is rich enough; asks one forcing clarifier only when invocation context is too thin to reassess from.

★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

referral-program

When the user wants to design, launch, or optimize a referral or affiliate program. Use when they mention 'referral program,' 'affiliate program,' 'word of mouth,' 'refer a friend,' 'incentive program,' 'customer referrals,' 'brand ambassador,' 'partner program,' 'referral link,' or 'growth through referrals.' Covers program mechanics, incentive design, and optimization — not just the idea of referrals but the actual system.

设计师视觉设计
★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

recursive-decision-ledger

Run repeated rollouts ("Prime Gauss" style recursive prompting) while keeping an append-only decision ledger of trials, marks, coherence checks, and promotion gates, so recursive confidence never auto-approves live trading, deploy, or destructive actions. Use when the user asks for repeated rollouts, marked decision processes, high-dimensional search, stochastic optimization, local-optima exploration, ensemble comparison, or recursive reasoning with a visible evidence trail.

★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

ra-qm-skills

Router/index for the 15 regulatory & quality-management skills bundled in this plugin (ISO 13485 QMS, EU MDR 2017/745, FDA submissions under QMSR, ISO 14971 risk, CAPA, document control, ISO 27001/ISMS, ISO 42001 AIMS, EU AI Act, GDPR/DSGVO, SOC 2, auditing). Use when a compliance request doesn't obviously match one skill and you need to pick the right one (e.g., 'prepare us for an ISO 13485 audit', 'is my AI system high-risk under the AI Act').

★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

quality-nonconformance

Quality control and non-conformance management for regulated manufacturing (FDA 21 CFR 820, IATF 16949, AS9100): NCR lifecycle and disposition, 5-Why/Ishikawa/fault-tree/8D root cause analysis, CAPA systems, SPC interpretation, AQL sampling, and supplier quality audits. Use when investigating non-conformances, performing root cause analysis, managing CAPAs, interpreting SPC data, or handling supplier quality issues.

★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

图像与多媒体
★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

weights-and-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

分析与可视化
★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

后端与接口
★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

unsloth

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

资料检索与研究
★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

distributed-llm-pretraining-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

torchforge-rl-training

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

★ 0