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 196669

Nirmit-Angane
Nirmit-Angane/DevFlow

skill_product_positioning

Governs emotional tone, audience, visual metaphor, and 10-second test

产品经理Skill与智能体开发
★ 0
Nirmit-Angane
Nirmit-Angane/DevFlow

skill_performance_optimization

Lighthouse targets, images, fonts, bundle

Skill与智能体开发
★ 0
Nirmit-Angane
Nirmit-Angane/DevFlow

skill_motion_system

Motion personality, tokens, entrance sequence, performance

Skill与智能体开发
★ 0
Nirmit-Angane
Nirmit-Angane/DevFlow

skill_layout_engine

Grid, archetype, section sequencing, hero structure

Skill与智能体开发
★ 0
Nirmit-Angane
Nirmit-Angane/DevFlow

skill_image_generation

Mockup generation, visual anchor, brand continuity

图像与多媒体Skill与智能体开发
★ 0
Nirmit-Angane
Nirmit-Angane/DevFlow

skill_hackathon_optimization

Demo flow, 10-second test, build vs fake, sample data

Skill与智能体开发
★ 0
PGCodeLLM
PGCodeLLM/harbor

upload-parity-experiments

Create or reuse Hugging Face dataset PRs for `harborframework/parity-experiments` and upload Harbor parity/oracle result folders efficiently with sparse checkout, raw git pushes, and Git LFS.

★ 0
Nirmit-Angane
Nirmit-Angane/DevFlow

skill_design_system

Color tokens, typography, spacing, design tokens export

设计师视觉设计Skill与智能体开发
★ 0
PGCodeLLM
PGCodeLLM/harbor

rewardkit

Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.

★ 0
Nirmit-Angane
Nirmit-Angane/DevFlow

skill_component_architecture

Component hierarchy, naming, props, data flow

Skill与智能体开发
★ 0
PGCodeLLM
PGCodeLLM/harbor

publish

Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.

★ 0
PGCodeLLM
PGCodeLLM/harbor

create-task

Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.

★ 0
PGCodeLLM
PGCodeLLM/harbor

create-adapter

Scaffold a new Harbor benchmark adapter by running `harbor adapter init` and then guide implementation using the Adapters Agent Guide as the authoritative spec.

Skill与智能体开发
★ 0
PGCodeLLM
PGCodeLLM/harbor

generate-greeting

Generate a greeting message and write it to a file.

★ 0
PGCodeLLM
PGCodeLLM/harbor

runtime-proof

Write the proof file for the Harbor runtime skill injection example.

★ 0
PGCodeLLM
PGCodeLLM/harbor

bundled-keep

Existing task skill that should remain after job-level skill injection.

★ 0
llmops-databricks-1
llmops-databricks-1/llmops-databricks-course-hfung4

git-commit

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

★ 0
hov172
hov172/SimpleMDM-MunkiReport

ckm:ui-styling

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.

设计师视觉设计
★ 0