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
dontbmad-compress-artifacts
Compress BMAD planning artifacts (PRDs, architecture docs, stories, project-context) into terse format to reduce input tokens when agents read them. Originals backed up as .original.md. Use when user says "compress artifacts", "compress planning docs", or "shrink the docs".
dontbmad-claude-design-to-bmad-uiux
Convert Claude Design output into a BMAD-compatible UI/UX handoff specification. Use when the user wants Claude Design to BMAD UX export, AC traceability, or ready-for-dev UIUX format.
dontbmad-caveman
Ultra-compressed communication mode. Cuts output tokens ~75% by speaking terse while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /dontbmad-caveman.
dontbmad-bmad-to-claude-design
Build a Claude Design-ready handoff brief from BMAD planning artifacts. Use when the user wants to move from PRD/architecture/epics/stories into Claude Design or asks for a BMAD to Claude Design template/export.
dontbmad-auto-sprint
Auto-implement ready-for-dev stories from the sprint plan. Impl and review run in fresh subagents; test verification runs inline. Auto-fix on test or review blockers is enabled by default (bounded). Use when user says "run auto sprint", "auto dev next story", or "implement next story automatically".
dontbmad-ai-tracking
暂无简介
bmad-validate-prd
Validate a PRD against standards. Use when the user says "validate this PRD" or "run PRD validation"
bmad-technical-research
Conduct technical research on technologies and architecture. Use when the user says they would like to do or produce a technical research report
bmad-sync-standards
Sync engineering standards from a central catalog into the current project's docs/standards/ folder, based on the project's engineering-standards.yml manifest. Also generates .cursor/rules/*.mdc and updates CLAUDE.md @imports for editor parity. Use when user says "sync standards", "pull standards", "update standards", or after editing engineering-standards.yml.
bmad-sprint-status
Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status"
bmad-sprint-planning
Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan"
bmad-shard-doc
Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
bmad-review-adversarial-general
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
bmad-retrospective
Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"
bmad-quick-dev
Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.
bmad-qa-generate-e2e-tests
Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]"
bmad-product-brief
Create or update product briefs through guided or autonomous discovery. Use when the user requests to create or update a Product Brief.