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

riley1802
riley1802/lumen-ai

kitchen-adventure

Act as a dungeon master for a text-based adventure set in a world where everyone is a sentient kitchen appliance. Trigger when user says "start kitchen adventure".

★ 0
riley1802
riley1802/lumen-ai

interactive-map

Show an interactive map view for the given location.

★ 0
riley1802
riley1802/lumen-ai

calculate-hash

Calculate the hash of a given text.

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

nemo-guardrails

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

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

nemo-evaluator-sdk

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

后端与接口运维与部署
★ 0
uchilaka
uchilaka/orchx-maker-toolkit

good-skill

A well-formed fixture skill.

Skill与智能体开发
★ 0
Tashima-Tarsh
Tashima-Tarsh/Disha6.6

nemo-curator

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

数据分析师图像与多媒体
★ 0
uchilaka
uchilaka/orchx-maker-toolkit

some-other-name

Name does not match its directory.

★ 0
uchilaka
uchilaka/orchx-maker-toolkit

no-desc

暂无简介

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

nanogpt

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

★ 0
uchilaka
uchilaka/orchx-maker-toolkit

summon-profile

Synchronizes the local Gemini profile (~/.gemini) with a remote machine via scp.

★ 0
uchilaka
uchilaka/orchx-maker-toolkit

start-worktree

Creates a new isolated git worktree for a JIRA ticket, generates a draft PR checkpoint doc, and sets up the branch following user conventions. Use when starting a new task or feature.

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

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

★ 0
uchilaka
uchilaka/orchx-maker-toolkit

specialist

Orchestrates expert reviews by delegating analysis to specialized sub-agents. Use this when the user asks for a "/specialist" review, a deep technical audit, or specific feedback on code, architecture, security, design, documentation, testing, or devops.

测试与质量
★ 0
uchilaka
uchilaka/orchx-maker-toolkit

release

Automates the version bump, changelog, build, and git release process for the repository. Use this when the user is ready to cut a new release of the toolkit.

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

model-pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

★ 0
uchilaka
uchilaka/orchx-maker-toolkit

path-to-ga

Analyzes project skills, global skills, and GEMINI.md to optimize the toolkit for general availability (GA) and public distribution.

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

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

★ 0