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

Grimblaz
Grimblaz/agent-orchestra

brainstorming

Structured Socratic questioning for exploring ideas and solutions. Use when exploring new features, evaluating approaches, or thinking through complex decisions. DO NOT USE FOR: architecture evaluation or SOLID analysis (use software-architecture), UI component design (use frontend-design), or coordinating implementation lanes (use parallel-execution).

前端开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

bdd-scenarios

Structured Given/When/Then scenario authoring with ID traceability and CE Gate coverage gap detection. Use when writing or reviewing BDD scenarios in Agent Orchestra, classifying scenarios as [auto]/[manual], managing scenario ID lifecycle, extracting scenario IDs for CE Gate pre-flight, generating Gherkin .feature files and step definitions for [auto] scenarios (Phase 2), or configuring framework runner dispatch for CE Gate (Phase 2). DO NOT USE FOR: general test strategy (use test-driven-development), or writing example-based unit tests.

★ 3
Grimblaz
Grimblaz/agent-orchestra

ai-first-documentation

Research-backed standards for documentation in AI-first codebases: context-file architecture (CLAUDE.md, skills, subagents, rules), multi-agent interop, and project-doc organization, with a tiered audit rubric. Use when authoring or auditing CLAUDE.md/AGENTS.md, deciding where guidance belongs, or running a documentation gap analysis. DO NOT USE FOR: post-implementation doc updates (use documentation-finalization) or reference sidecar setup (use project-references).

Skill与智能体开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

agent-memory-compaction

Compaction policy for an agent memory store's recall index, plus the sweep it runs on: the rules a compaction may not break, how an entry leaves and where that exit is recorded, the slate procedure and its dispositions, the size budget the index is held to, and a re-runnable check. Use when compacting, pruning, or repairing a memory index, when running or preparing a sweep of a store, or when relocating a line that carries several linked subjects. DO NOT USE FOR: individual memory entries; session-state or handoff markers (use session-memory-contract); repository docs (use documentation-finalization).

财务Skill与智能体开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

adversarial-review

Reusable adversarial review methodology for prosecution, defense, design challenge, and proxy review passes. Use when reviewing code, plans, designs, or external review ledgers with evidence-first rigor; also when prosecuting a remedy for the defect class it closes, when a change demotes or removes a signal, when judging whether a proposed guard or a substring pin actually holds, when a finding narrows a guard or hardens a selector, and when the thing under review is a newly built mechanism. DO NOT USE FOR: final judgment ownership, GitHub intake routing, or fix execution decisions (use review-judgment or code-review-intake).

★ 3
Grimblaz
Grimblaz/agent-orchestra

some-skill

a test skill with no table of contents

Skill与智能体开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

Skill-A

暂无简介

Skill与智能体开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

oversized-skill

test skill

Skill与智能体开发
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

skill-sync

Synchronizes skill metadata to AGENTS.md Auto-invoke sections. Trigger: When syncing skill metadata to AGENTS.md.

Skill与智能体开发
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

skill-creator

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Skill与智能体开发
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

skill-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

前端开发Skill与智能体开发
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

project-info

General monorepo structure and component overview. Trigger: When AI needs project context or component locations.

★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

frontend-context

Frontend architecture, patterns and conventions for the Next.js 15 app. Trigger: When working on frontend code, components, pages, or API integration.

开发工程师前端开发
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

express-mocks-testing

Unit testing pattern for Express 5 controllers using node-mocks-http and @prisma/client mocks. Trigger: When writing unit tests for backend controllers, testing Express routes, or avoiding Supertest/Server instantiation.

测试与质量后端与接口
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

backend-service

暂无简介

后端与接口
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

backend-schema

暂无简介

后端与接口
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

backend-router

暂无简介

后端与接口
★ 3
davidleonmayor
davidleonmayor/proyecto-grado-unimayor

backend-controller

暂无简介

后端与接口
★ 3