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

testing-strategy

Testing approach — unit vs integration vs E2E, coverage goals, organization. Use when deciding what to test, choosing between unit/integration/E2E tests, planning a test strategy for new functionality, or setting coverage goals.

测试与质量
★ 0
projectious-work
projectious-work/processkit

terraform-basics

Infrastructure-as-code with Terraform/OpenTofu — resources, state, modules, plan/apply. Use when writing `.tf` files, managing cloud infrastructure with Terraform or OpenTofu, handling state and backends, or reviewing IaC code.

运维与部署
★ 0
projectious-work
projectious-work/processkit

tdd-workflow

Test-driven development workflow — red-green-refactor, naming, doubles, when to apply. Use when writing code with TDD, practicing the red-green-refactor cycle, deciding between TDD and test-after, naming tests, choosing test doubles, or exploring property-based and mutation testing.

代码审查测试与质量
★ 0
projectious-work
projectious-work/processkit

tailwind

Tailwind CSS v4 — utility-first styling, responsive design, dark mode, and component extraction. Use when building or reviewing Tailwind-based UIs, setting up Tailwind v4, or designing responsive or dark-mode styling.

视觉设计
★ 0
projectious-work
projectious-work/processkit

system-design

System design methodology — requirements, capacity estimation, component design, trade-offs. Use when designing a new distributed system, evaluating an existing architecture for scalability or cost, performing back-of-envelope capacity estimation, or preparing for a system design review.

设计师视觉设计
★ 0
projectious-work
projectious-work/processkit

status-update-writer

Generates clear, structured status updates for stakeholders — from project context, backlog state, or a brief description of recent work. Use when asked to write a status update, weekly report, progress summary, or team briefing about a project or initiative.

★ 0
projectious-work
projectious-work/processkit

state-machine-management

Define and customize StateMachine entities — the state/transition graphs used by WorkItems, DecisionRecords, and other primitives with lifecycle. Use when a project needs to customize the default state machine for a primitive (add states, change transitions) or define a state machine for a custom entity type.

★ 0
projectious-work
projectious-work/processkit

standup-context

Writes a structured standup update as a session.standup LogEntry — capturing what was done, what is in progress, what comes next, and any blockers. Use when the user says "write a standup", "standup update", "what did I do today", "write a status update for the team", or at the end of a session on projects that run daily standups.

★ 0
projectious-work
projectious-work/processkit

sql-style-guide

SQL style — snake_case, singular tables, named constraints, one-clause-per-line formatting. Use when writing or reviewing SQL, designing schemas, or naming tables, columns, constraints, and migrations.

数据分析师后端与接口
★ 0
projectious-work
projectious-work/processkit

sql-patterns

SQL query patterns, schema design, and optimization — joins, CTEs, window functions, indexing, and anti-patterns. Use when writing or optimizing SQL queries, designing or reviewing a relational schema, reading EXPLAIN plans, choosing indexes, or implementing pagination, deduplication, or analytical queries.

数据分析师后端与接口
★ 0
projectious-work
projectious-work/processkit

software-modularization

Designs and evaluates module and package boundaries — keeping software in small, independently-loadable units optimised for both maintainability and AI agent context limits. Use when asked to split a monolith, design package structure, evaluate module boundaries, reduce coupling between components, or when a codebase has grown too large for an agent to reason about in one context window.

视觉设计
★ 0
projectious-work
projectious-work/processkit

software-architecture

Codebase architecture analysis — patterns, ADRs, structural review, C4 diagrams. Use when evaluating a codebase's architecture, choosing a pattern for a new project, writing an Architecture Decision Record, reviewing for layer violations, or generating C4 diagrams.

★ 0
projectious-work
projectious-work/processkit

skill-reviewer

Review an existing processkit skill against the 5 Skill Killers, the Agent Skills standard frontmatter rules, processkit's structural conventions, and Anthropic's troubleshooting playbook. Use when the user says "review this skill", "check the X skill", "audit skills/", "is this skill good", "what's wrong with the X skill", "lint the X skill", or "generate gotchas for X". Produces a categorized findings report (must-fix, should-fix, nit) and, when the Gotchas section is missing or weak, generates draft gotchas based on the skill's content.

Skill与智能体开发
★ 0
projectious-work
projectious-work/processkit

skill-finder

Navigation aid for the processkit skill catalog — maps natural-language cues and task types to the right skill. Read this when you are unsure which skill applies to the current task, when the user names a task without naming a skill, or at session start when orienting to an unfamiliar project. Always the first skill to consult; never the last.

Skill与智能体开发
★ 0
projectious-work
projectious-work/processkit

skill-builder

Interactive guide for creating new processkit skills end-to-end. Walks the user through use-case interview, frontmatter generation in Agent Skills standard format, body section drafting, mandatory Gotchas authoring, the 5 Skill Killers self-check, and trigger test generation. Use when the user says "create a new skill", "build a skill for ...", "scaffold a skill", "I want to teach Claude (or any agent) how to do X", "draft a skill that ...", or "add a skill for ...". Produces a complete skill folder under src/skills/ ready to commit.

Skill与智能体开发
★ 0
projectious-work
projectious-work/processkit

shell-scripting

Bash scripting — strict mode, quoting, arg parsing, traps, shellcheck compliance. Use when writing or reviewing bash scripts, adding error handling and argument parsing, or fixing shellcheck warnings.

内容创作者写作与文案
★ 0
projectious-work
projectious-work/processkit

session-handover

Writes a structured end-of-session handover as a session.handover LogEntry — capturing current state, open threads, next recommended action, and git context — so the next session can resume without losing track. Use when the user says "write a handover", "prepare for shutdown", "save context before closing", or when a container restart is imminent.

★ 0
projectious-work
projectious-work/processkit

seo-optimization

SEO — on-page, technical, structured data, Core Web Vitals, and mobile-first indexing. Use when optimizing a website for search engines, adding meta tags or structured data, fixing Core Web Vitals, or auditing technical SEO.

市场营销营销推广
★ 0