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
productize-adaptive-planning-from-scenarios-to-strategic-actions
Adaptive planning from scenarios to strategic actions. Use when the user needs a product workflow for product strategy related to adaptive planning from scenarios to strategic actions. Trigger terms: strategic-planning, facilitation, product-management, decision-making, frameworks.
productize-actionable-user-research-decisions-from-project-insights
Actionable user research decisions from project insights. Use when the user needs a product workflow for user research related to actionable user research decisions from project insights. Trigger terms: user-research, decision-making, frameworks.
productize-actionable-user-profiles-with-tasks-and-constraints-from
Actionable user profiles with tasks and constraints from shallow personas. Use when the user needs a product workflow for user research related to actionable user profiles with tasks and constraints from shallow personas. Trigger terms: user-research, personas, ux.
productize-actionable-research-briefs-from-problem-statements-and
Actionable research briefs from problem statements and solutions. Use when the user needs a product workflow for user research related to actionable research briefs from problem statements and solutions. Trigger terms: user-research, research-brief, ux.
productize-actionable-product-improvements-from-survey-responses
Actionable product improvements from survey responses. Use when the user needs a product workflow for user research related to actionable product improvements from survey responses. Trigger terms: user-research, surveys, insights.
productize-actionable-job-stories-from-interview-transcripts
Actionable job stories from interview transcripts. Use when the user needs a product workflow for user research related to actionable job stories from interview transcripts. Trigger terms: user-research, jtbd, interviews.
productize-actionable-customer-interview-guides-from-research-topics
Actionable customer interview guides from research topics. Use when the user needs a product workflow for user research related to actionable customer interview guides from research topics. Trigger terms: user-research, interviews, discussion-guide.
productize-accessibility-review
Run a WCAG 2.1 AA accessibility audit on a design or page. Use when asked to audit accessibility, check a11y, determine whether something is accessible, or review color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.
productize-acceptance-criteria-for-ui
Acceptance criteria for UI. Use when the user needs a product workflow for technical related to acceptance criteria for ui. Trigger terms: quality-assurance, ui, acceptance-criteria, responsive-design, technical.
productize-ab-test-analysis
A/B Test Analysis. Use when evaluating A/B test results, checking statistical significance, validating sample size, reading confidence intervals, or deciding whether to ship, extend, or stop an experiment.
productize-aarrr-growth-diagnostics
Diagnose product or startup growth using AARRR pirate metrics, CAC, LTV, channel performance, activation, retention, referral, revenue, and growth engine fit. Use for funnel leakage, growth bottlenecks, SaaS conversion, and go-to-market growth analysis.
productize-0-1
Productize 0-1 orchestrator for turning a raw product idea or new capability bet into a working first product slice. Use for founder, PM, CPO, AI product leader, or AI builder work that must combine product framing, capability scoping, curated data, application setup, eval design, eval runs, behavior analysis, fixes, and ship/learn decisions.
fix-reviews
Executes provider-agnostic PR review remediation using existing review round files under .productize/tasks/<name>/reviews-NNN/. Use when resolving batched review issues, updating issue markdown files, implementing fixes, and verifying the result. Do not use for PRD task execution, review export/fetch, or generic coding tasks without review issue files.
final-verify
Enforces fresh verification evidence before any completion, fix, or passing claim, and before commits or PR creation. Use when an agent is about to report success, hand off work, or commit code. Do not use for early planning, brainstorming, or tasks that have not yet reached a concrete verification step.
execute-task
Executes one PRD task end-to-end using a provided task file, PRD directory, tracking file paths, and auto-commit mode. Use when a prompt includes a task specification that must be implemented, validated, and reflected in task tracking files. Do not use for PR review batches, generic coding tasks without a PRD task file, or standalone verification-only work.
create-techspec
Creates a Technical Specification by translating PRD business requirements into implementation designs through interactive technical clarification. Use when a PRD exists and needs a technical plan, or when technical architecture decisions need documentation. Do not use for PRD creation, task breakdown, or direct code implementation.
create-tasks
Decomposes PRDs and TechSpecs into detailed, independently implementable task files with enrichment from codebase exploration. Use when a PRD or TechSpec exists and needs to be broken down into executable tasks, or when task files need enrichment with implementation context. Do not use for PRD creation, TechSpec generation, or direct task execution.
create-prd
Creates a Product Requirements Document through interactive brainstorming with parallel codebase and web research. Use when starting a new feature or product, building a PRD, or brainstorming requirements. Do not use for technical specifications, task breakdowns, or code implementation.