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
fabric-optimization-review
Review and optimize data storage, data models, and semantic models in Microsoft Fabric lakehouses. Covers Delta table optimization (V-Order, Z-Order, compaction, partitioning), data model anti-pattern detection, semantic model DAX review, relationship optimization, AI/agentic readiness (descriptions, synonyms, linguistic schema, display folders), workspace audit (Fabric best practices, dimensional modeling, Direct Lake), and actionable recommendation reports. Use when: optimization, performance, review, tuning, best practices, V-Order, Z-Order, partitioning, compaction, DAX optimization, data model review, AI readiness, agentic, NLQ, Copilot, natural language, workspace audit, Direct Lake, dimensional modeling, audit.
fabric-metadata-creation
Create reviewable metadata proposals for Microsoft Fabric lakehouse tables and semantic models. Covers schema analysis, concise technical and business descriptions, glossary terms, classifications, Purview-like sensitivity label proposals, PII and sensitive data detection, relationship and lineage hints, data quality rules, CDE candidates, data products, JSON/PDF output, and steward review questions. Use when: metadata creation, data catalog, Purview mapping, glossary inference, data classification, sensitivity labels, stewardship review, governance metadata.
fabric-data-cleaner
Algorithm reference and self-contained PySpark notebook templates for cleaning Microsoft Fabric lakehouse tables. Covers profiling, duplicate detection, null analysis, type validation, statistics, IQR outlier detection, date format validation, Spanish DNI/NIE checksum validation, and email/phone format checks. Each notebook can be uploaded and run independently in Fabric.
start-chaos
Orchestrate the full Chaos Studio v2 workflow: auth → workspace → scenario → run. Shares a single state file and supports resume.
setup-scenario
Discover recommended scenarios, build and validate a ScenarioConfiguration, and auto-fix resource permissions.
run-scenario
Execute a ScenarioConfiguration and stream ScenarioRun status with per-action breakdown until terminal state.
create-workspace
Provision a Microsoft.Chaos/workspaces resource (v2), bind a managed identity, set scopes, and grant Reader RBAC on the scope.
chaos-study
Guided help for running a Chaos Studio study against an Azure workspace scope: frame a steady-state question with you, discover live which actions Chaos Studio offers for that region, freeze a plan, run a validated scenario configuration only with your explicit consent, collect the before/during/after signals you chose, and write a self-contained HTML report for your review. Start here for questions like 'what happens to my service when X?' or 'is my service resilient to X?'.
chaos-study-scope
Frame a Chaos study before anything runs: resolve or create a Chaos Studio V2 workspace, read the resources the service discovered inside its scopes, discover live which actions and scenarios are available for that region, express a falsifiable steady-state predicate, verify the action fits what is in scope, then freeze and hash the study plan.
chaos-study-run
Execute a frozen Chaos study plan against Azure using Chaos Studio V2: verify plan integrity, create and validate a scenario configuration, require an explicit typed consent phrase, collect baseline evidence, execute the scenario run, collect during and post-recovery evidence, and always clean up the configuration. Dry-run by default.
chaos-study-report
Render the evidence collected by an executed Chaos study as a self-contained HTML report for your review: steady-state verdict label, tests run, evidence tables, findings with severity labels, stated limitations, and remediation suggestions. Pure read of collected evidence — executes nothing.
chaos-study-history
List, inspect, compare, and re-run past Chaos studies from the dated study store. For 'did we fix it?' questions, diffs the recorded findings between two comparable studies of the same scope, and prints the exact command to re-run a study as a new one.
chaos-study-design
Help decide what a Chaos study could test. Reads the system's code, deployment and telemetry first, then interviews the customer about what they want to learn, and only then suggests a ranked set of Chaos Studio V2 scenario candidates tied to the dependency edges it found. Writes a durable study brief that feeds chaos-study-scope without retyping.
chaos-impact
Synthesize an Azure Monitor impact report for a Chaos Studio v2 ScenarioRun: pulls the run, walks targeted resources, queries metrics/logs/activity-log/alerts over the run window ± buffer, and renders a Markdown + JSON impact card.
decision-interview
Interview a request owner about an unclear request or idea before work is planned. Use when the user says "interview me", "shape this request", or shares a vague request that needs decisions before a brief or issue. Do not use for questions that have a factual answer in the source.
session-format-validator
Validate new or changed GitHub Copilot Train-the-Trainer session directories before they are added to the curriculum. Use this skill whenever a user creates, adds, updates, reviews, or asks whether a session under sessions/session-* follows the repository's repeatable format, including required materials, catalog metadata, navigation, and lab access or fallback guidance. Use it even when the user only asks to check a session README or lab.
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.