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

projectious-work
projectious-work/processkit

fastapi-patterns

FastAPI patterns — dependency injection, Pydantic models, async endpoints, middleware, and testing. Use when building FastAPI applications, designing API endpoints, adding authentication, or reviewing FastAPI code.

测试与质量
★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-b

Linear-B. Test fixture; describes itself for parity checks across both runtimes.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-a

Linear-A. Test fixture; describes itself for parity checks across both runtimes.

★ 0
projectious-work
projectious-work/processkit

event-driven-architecture

Event-driven systems — pub/sub, event sourcing, CQRS, sagas, broker selection, reliability. Use when designing or migrating to an event-driven system, choosing a message broker, implementing event sourcing or CQRS, designing sagas, or reviewing async architectures for reliability and ordering.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-a

InvTA-Team-A. Test fixture; describes itself for parity checks across both runtimes.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

app-b

InvTA-App-B. Test fixture; describes itself for parity checks across both runtimes.

★ 0
projectious-work
projectious-work/processkit

error-handling

Error handling across languages — Result types, exceptions, retries, circuit breakers, and structured error responses. Use when designing error handling for a module or service, choosing between Result types and exceptions, building error hierarchies, implementing retries or circuit breakers, or reviewing code for missing or poor error handling.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-b

InvOT-Team-B. Test fixture; describes itself for parity checks across both runtimes.

★ 0
projectious-work
projectious-work/processkit

domain-driven-design

Domain-Driven Design strategic and tactical patterns — bounded contexts, aggregates, value objects, context mapping. Use when modeling a complex business domain, defining microservice boundaries, designing aggregates, establishing a ubiquitous language, or refactoring a big ball of mud into well-defined contexts.

设计师视觉设计
★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

org-a

InvOT-Org-A. Test fixture; describes itself for parity checks across both runtimes.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-b

Disc-B. Test fixture; describes itself for parity checks across both runtimes.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-a

Disc-A. Test fixture; describes itself for parity checks across both runtimes.

★ 0
projectious-work
projectious-work/processkit

dependency-management

Cross-language dependency management — lockfiles, version pinning, automated updates, security, and licenses. Use when setting up or reviewing lockfile strategy, configuring automated dependency updates, auditing dependencies for security or license issues, handling monorepo dependencies, or deciding whether to vendor.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-d

Diamond-d. Test fixture; describes itself for parity checks across both runtimes.

★ 0
projectious-work
projectious-work/processkit

dependency-audit

Audit project dependencies for vulnerabilities and outdated packages. Use when checking the security posture of dependencies, planning updates, or running a pre-release dependency review.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-c

Diamond-c. Test fixture; describes itself for parity checks across both runtimes.

★ 0
carlosmarte
carlosmarte/ai-agent-artifacts

team-b

Diamond-b. Test fixture; describes itself for parity checks across both runtimes.

★ 0
projectious-work
projectious-work/processkit

debugging

Systematic debugging — reproduce, read the error, isolate, hypothesize, fix, verify, document. Use when tracking down a bug, unexpected behavior, or test failure — including phrases like "this doesn't work", "why is this failing", or "help me debug".

★ 0