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

repo-management

Reconcile repository issues, pull requests, merge requests, local git state, commits, and pushes across GitHub, GitLab, Gitea, Forgejo, Codeberg, Bitbucket, Azure DevOps, and SourceHut.

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

logo-design

Creates SVG logos with scalable geometry, color theory, and variant generation. Use when designing logos, icons, or brand marks, generating favicons or social avatars, or reviewing a logo for scalability, color, or variant coverage.

设计师视觉设计图像与多媒体
★ 0
projectious-work
projectious-work/processkit

prompt-engineering

Prompt design patterns — few-shot, chain-of-thought, structured output, injection defense. Use when crafting or refining LLM prompts, designing system prompts for agents, requesting structured output, defending against prompt injection, building reusable prompt templates, or iterating on prompt quality.

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

feature-engineering

Feature engineering for ML — encoding, imputation, scaling, selection, time-series features. Use when preparing data for an ML model, encoding categoricals, handling missing data, building time-series features, or selecting features from a wide table.

数据分析师
★ 0
projectious-work
projectious-work/processkit

i-have-adhd

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

★ 0
projectious-work
projectious-work/processkit

standard-spec-driven-development

暂无简介

★ 0
projectious-work
projectious-work/processkit

standard-security

Company security and software-supply-chain standard. Use when handling untrusted input, paths, subprocesses, secrets or sensitive data, adding or updating dependencies, signing or attesting releases, or responding to a vulnerability.

★ 0
projectious-work
projectious-work/processkit

standard-roadmap

Company product roadmap and development-evidence standard. Use when creating or changing roadmap.yaml, starting or finishing a roadmap phase or feature, changing an item's status (idea, planned, in_progress, done, released, cancelled), writing development notes, or preparing a release.

产品经理
★ 0
projectious-work
projectious-work/processkit

standard-release-engineering

Company verification and release-engineering standards, including human-controlled host phases. Use when defining test layers or verification gates, preparing or publishing a release, building release artifacts and provenance, or running release work that needs the host outside the dev container.

★ 0
projectious-work
projectious-work/processkit

standard-public-docs

Company open-source documentation and AI-agent accessibility standards. Use when writing or restructuring a public README, documentation site, community files, changelog, release notes, gh-pages deployment, llms.txt or other generative-discovery files, or a product's read-only MCP resource server.

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

standard-git-branching

Company Git branching and release standard (GitHub Flow with Conventional Commits). Use when creating or naming feat/fix/chore/spec branches, choosing a merge target, writing a squash-merge title, cutting a release/* branch, tagging, maintaining lts/* lines, or cherry-picking fixes.

★ 0
projectious-work
projectious-work/processkit

standard-architecture

Company software architecture, code design, and refactoring standards. Use when designing module boundaries, ports and adapters, use cases, writing architecture docs (arc42, C4, ADR), splitting large files, extracting libraries, or doing any refactoring larger than a rename.

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

standard-application-engineering

暂无简介

★ 0
projectious-work
projectious-work/processkit

standard-agent-interfaces

暂无简介

Skill与智能体开发
★ 0
zero8urn
zero8urn/agentic-goo

to-syllabus

Turns a topic, a fixed experienced-developer audience, and a domain into a learning syllabus and a companion technical guide. Use when someone says "syllabus this" or asks to create a learning path framed inside a domain.

开发工程师
★ 0
zero8urn
zero8urn/agentic-goo

to-icebox

Transforms a stream of thoughts, rough conversation, or scattered ideas into a structured feature request document. Use when someone says "icebox this".

★ 0
zero8urn
zero8urn/agentic-goo

righting-software

Juval Löwy's "The Method" (Righting Software, 2019) as an operating procedure. Decompose a system by axes of volatility, never by functionality; classify components into the fixed taxonomy (Client, Manager, Engine, ResourceAccess, Resource, Utilities); validate by call chains; then design the project that builds it. Use when the user asks for system design, architecture review, service decomposition, "The Method", volatility-based decomposition, or asks how long/costly a build will be.

设计师视觉设计
★ 0
zero8urn
zero8urn/agentic-goo

documentation-writer

Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.

★ 0