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。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
tunit-playwright-ui-testing
Comprehensive guidance for writing coded end-to-end UI tests in C# using TUnit.Playwright. Tests inherit from PageTest — the base class manages all browser lifecycle. Covers NuGet setup, PageTest inheritance, Page Object Model, browser configuration, parallelism limiting, and CI integration. Based on the official TUnit docs at https://tunit.dev/docs/examples/playwright.
triage
Task classification, decomposition, dependency mapping, and routing skill. Invoked by the triage-agent to break any user request into discrete, independently-routable work items with assigned priorities and agent chains.
system-design
Expert system design skill. Use PROACTIVELY to design systems, review architectures, and assist software engineers in learning design principles and implementing them in the code with design patterns.
spec-driven-development
Manages the full lifecycle of a feature specification — from collaborative drafting to enforcement during implementation and testing.
sonarqube-pr-quality-gate
Structured workflow for enforcing SonarQube quality gate on HypermediaEngine pull requests. Covers sonar-project.properties configuration, SonarScanner GitHub Action, PR decoration, quality-gate-failure as a blocking status check, and integration with the existing sonarqube-cli MCP tooling. Invoked by the devops-engineer agent when SonarQube must gate PRs.
skills-sync
Detects and resolves drift between .claude/skills/<name>/SKILL.md and .github/skills/<name>/SKILL.md. Also validates that every skill has a matching command (.claude/commands/<name>.md) and prompt (.github/prompts/<name>.prompt.md). Invoked exclusively by the agent-manager agent.
skill-management
Creates, updates, and lists skill files (.claude/skills/*/SKILL.md) and (.github/skills/*/SKILL.md) for the HypermediaEngine multi-agent system. Invoked exclusively by the agent-manager agent.
security-review
Security-focused review workflow for HypermediaEngine. Use for auth, data exposure, input validation, dependency risk, and vulnerability checks.
rules-management
Create, modify, delete, and sync Claude rules files (.claude/rules/*.md) and GitHub Copilot instruction files (.github/instructions/*.instructions.md) safely using a discovery-first, non-destructive workflow. Invoked by agent-manager whenever a rules or instructions file lifecycle operation is requested.
rules-instructions-sync
Detects and resolves drift between .claude/rules/*.md (Claude rules) and .github/instructions/*.instructions.md (Copilot instructions files). Ensures every rule has a matching instructions file and vice versa. Invoked exclusively by the agent-manager agent.
review
Structured code review workflow for HypermediaEngine. Use to assess branch/PR/file changes and produce severity-ranked findings.
qwen-nsfw-pose
暂无简介
research
Structured external-knowledge and codebase-exploration research skill for HypermediaEngine. Invoked by the research-assistant agent to clarify the question, select authoritative sources (context7 for library docs, web search/fetch for general information, Grep/Glob/Read for codebase exploration), triangulate findings, and produce a cited findings report with confidence assessment.
requirement-analysis
Structured requirement elicitation for HypermediaEngine. Use before architecture or implementation when scope is new, vague, or ambiguous.
product-planning
Product backlog management and release planning skill. Invoked by the product-manager agent to add items, review backlog health, re-prioritize, plan releases, or update item status. Reads and writes docs/backlog/backlog.md as the persistent source of truth.
playwright-mcp-ui-testing
AI-driven browser UI testing using the Playwright MCP server. Guides the sqa-engineer to perform autonomous browser interactions, assertions, and evidence capture through the Playwright MCP tools. Use ONLY when the change involves UI or frontend components.
nuget-package-deployment
Structured workflow for publishing HypermediaEngine NuGet packages to nuget.org. Covers SemVer with preview/prerelease suffixes, dotnet pack, dotnet nuget push, secret-based API key handling, symbol packages (.snupkg), Source Link, package metadata in .csproj, and the difference between stable and preview release flows. Invoked by the devops-engineer agent during release execution.
mono-color
Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster, monochrome editorial poster, duotone print, or asks to use the mono-color style. It uses an adaptive white, gray, or pale-beige substrate, no more than two printing inks, active negative space, terse human language, and strong serif/grotesk/mono typography without making retro styling the default or copying a source composition, wording, logo, or artwork. Produce both the final generation prompt and the generated raster image unless the user explicitly asks for prompt only.