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

duc-duy-1612
duc-duy-1612/Online-Delivery-Systems-Web

ai-red-teaming

Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.

Skill与智能体开发
★ 0
rubicanjr
rubicanjr/FinCognis

elasticsearch-patterns

Mapping design, query optimization, aggregation patterns, index lifecycle management, and search relevance tuning.

视觉设计
★ 0
duc-duy-1612
duc-duy-1612/Online-Delivery-Systems-Web

ai-pipeline-orchestration

Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.

★ 0
rubicanjr
rubicanjr/FinCognis

docker-ops

Dockerfile best practices, multi-stage builds, docker-compose, container networking, volume management, and image optimization.

运维与部署图像与多媒体
★ 0
rubicanjr
rubicanjr/FinCognis

django-verification

暂无简介

★ 0
rubicanjr
rubicanjr/FinCognis

django-tdd

Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.

测试与质量
★ 0
rubicanjr
rubicanjr/FinCognis

django-security

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.

后端与接口
★ 0
rubicanjr
rubicanjr/FinCognis

django-patterns

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.

后端与接口视觉设计
★ 0
duc-duy-1612
duc-duy-1612/Online-Delivery-Systems-Web

ai-inference-service-mesh

Use service mesh patterns for AI inference traffic management, mTLS, canary releases, policy enforcement, and cross-cluster resilience.

★ 0
rubicanjr
rubicanjr/FinCognis

differential-review

Security-focused differential code review with blast radius analysis, risk-adaptive depth (DEEP/FOCUSED/SURGICAL), git history correlation, and structured finding format. Adapted from Trail of Bits. Use when reviewing PRs, commits, or code changes for security implications.

代码审查
★ 0
scitex-ai
scitex-ai/scitex-agent-container

hello

暂无简介

★ 0
rubicanjr
rubicanjr/FinCognis

diff-review-strategy

PR size-based review depth, performance review checklist, architecture conformance checks, and framework-specific review patterns.

前端开发后端与接口
★ 0
rubicanjr
rubicanjr/FinCognis

design-to-code

Figma-to-code translation, design tokens, spacing/typography scales, responsive breakpoints, and design system bridge patterns.

开发工程师设计师视觉设计
★ 0
rubicanjr
rubicanjr/FinCognis

describe_pr

Generate comprehensive PR descriptions following repository templates

★ 0
scitex-ai
scitex-ai/scitex-agent-container

scitex-agent-container

[WHAT] `spec.yaml` selects Claude, Codex, Hermes or OpenCode in Apptainer; A2A inbound (`POST /v1/turn`), SSH deploy and JSON status. [WHEN] Agents, fleets, Hermes profiles, goal_judge errors, MCP, A2A; `sac agents start`, `scitex-agent-container`, `spec.yaml`. [HOW] `pip install scitex-agent-container`; `sac agents start <name>` or `import scitex_agent_container`.

Skill与智能体开发
★ 0
duc-duy-1612
duc-duy-1612/Online-Delivery-Systems-Web

ai-coding-agent-guardrails

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.

代码审查Skill与智能体开发
★ 0
rubicanjr
rubicanjr/FinCognis

deep-interview

Mathematically rigorous Socratic interview system that drives ambiguity below 20% before any code is written. One question per message, weighted ambiguity scoring, brownfield-aware, outputs a complete PRD. Replaces discovery-interview with a stricter protocol.

产品经理人力资源
★ 0
scitex-ai
scitex-ai/scitex-agent-container

example-skill

[WHAT] Project-specific context and reusable knowledge for this agent — coding conventions, tool usage patterns, domain vocabulary. [WHEN] Always loaded at agent startup; provides background the agent needs to work effectively in this codebase. [HOW] Place one `.md` file per topic in this directory; each file is loaded into the agent's context via the skills system.

Skill与智能体开发
★ 0