智能体工作流 Skills - 智能体工作流 Agent Skills推荐与安装 - 第50页 - AI导哈

provider-framework-migrationhashicorp/agent-skillsMigrate Terraform provider resources and data sources from Plugin SDKv2 to the Plugin Framework: muxing both plugins in one provider (terraform-plugin-mux, tf5to6server), per-resource migration workflow, SDKv2-to-Framework schema mapping (ForceNew, ValidateFunc, DiffSuppressFunc, Default, Timeouts, blocks), null-vs-zero-value behavioral traps, and state-compatibility verification. Use when converting or translating SDKv2 resources to the Framework, setting up a muxed provider server, deciding whether a resource should be migrated at all, or debugging plan diffs and state errors that appeared after a migration.964 architectjsmastery-pro/j…nt-skillThink through what you are about to build like a senior engineer before writing any code. Surfaces decisions, aligns on language, and produces a clear implementation plan you confirm before anything starts.963 dt-obs-network-devicesdynatrace/dynat…e-for-aiAnalyze SNMP-monitored network devices (switches, routers, firewalls, load balancers) in Dynatrace. Three data layers: Smartscape topology (`EXT_NETWORK_DEVICE` / `EXT_NETWORK_INTERFACE` nodes, `belongs_to` and `calls` edges); `com.dynatrace.extension.network_device.*` metrics (CPU, memory, uptime, throughput, saturation, errors); and logs (SNMP traps, syslog, auto-discovery). Use to inventory devices, find down or saturated interfaces, check device CPU/memory/uptime, map topology and neighbors, detect interface errors, and investigate traps and syslog events. Trigger: "network device", "switch", "router", "firewall", "SNMP", "interface status", "interface down", "interface utilization", "link saturation", "device CPU", "device memory", "device uptime", "device neighbors", "LLDP", "CDP", "SNMP trap", "syslog". Do NOT use for network flow/traffic or top talkers (use dt-obs-network-flows), host NIC throughput (use dt-obs-hosts), or service request/latency (use dt-obs-services).962 airflow-hitlastronomer/agentsBuilds human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching. Use when a DAG needs a human in the loop - an approval or reject step, sign-off before a task runs, a decision or approval UI, branching on a human choice, or collecting form input mid-run; also on mentions of ApprovalOperator, HITLOperator, HITLBranchOperator, HITLEntryOperator, or HITLTrigger. Requires Airflow 3.1+. Not for AI/LLM task calls (see migrating-ai-sdk-to-common-ai).961 llamaguardorchestra-research/ai-research-skillsMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.961 skypilot-multi-cloud-orchestrationorchestra-research/ai-research-skillsMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.960 autogpt-agentsorchestra-research/ai-research-skillsAutonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.960 mcp-builderjnmetacode/supe…owers-zh在构建 MCP 服务器或 MCP 工具时使用 —— 系统化的生产级 MCP 构建方法论，覆盖工具设计、错误处理、传输层选择与测试，让 AI 助手连接外部能力955 create-phone-numbervapiai/skillsPlan, provision, import, route, update, and verify Vapi phone numbers through the public API. Use for Vapi-hosted US PSTN numbers, explicitly requested SIP addresses, Twilio/Vonage/Telnyx or BYO carrier numbers, secure credential handling, assistant or squad routing, area-code requests, outbound limitations, and phone-provider troubleshooting.951 cli-demo-generatordaymade/claude-…e-skillsGenerates professional animated CLI demos as GIFs using VHS terminal recordings. Use to create terminal demos, record CLI workflows as GIFs, generate animated documentation, build demo tapes for README files, or showcase any command-line tool visually: record terminal / VHS tape / demo GIF / animate my CLI.951 teams-channel-post-writerdaymade/claude-…e-skillsWrites educational Teams channel posts about Claude Code features and best practices, using templates emphasizing concrete examples and underlying principles (e.g. context engineering). Use when writing a Teams post or announcement to teach colleagues Claude Code usage, announce a feature, share a tip, or document a lesson learned.945 workflow-runnerjnmetacode/supe…owers-zh在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。944 crontap-recurring-agent-endpointcrontap/skillsSchedule an HTTP endpoint that a deployed application uses to start its own agent workflow, then monitor completion with a heartbeat. Use when a user has an application-owned agent runtime that needs a durable external clock.938 crontap-schedule-http-jobcrontap/skillsCreate, update, and verify recurring Crontap HTTP requests with cron or plain English, timezones, headers, and JSON bodies. Use when a user wants to schedule a webhook, API call, or cloud function through MCP or REST.937 planning-with-filessickn33/agentic…e-skillsWork like Manus: Use persistent markdown files as your "working memory on disk."936 eol-checklistdeanpeters/prod…r-skillsBuild a phase-gated EOL checklist sized to the sunset, with a named owner on every item. Use when the decision to retire is made and you need the operational plan.935 agile-product-owneralirezarezvani/…e-skillsAgile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use when writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing the backlog.933 eol-processdeanpeters/prod…r-skillsRun a product sunset end to end — decide, align, plan, prepare, announce, close. Use when you need the whole EOL process, not just one artifact.930 eol-stakeholder-sequencedeanpeters/prod…r-skillsPlan who to talk to about a sunset, in what order, and what each conversation must cover. Use when an EOL decision is made and you want the landmines found before the announcement.928 blockbench-usejasonjgardner/b…-projectLoad before Blockbench MCP calls that create, modify, or export content. Discover the active format and tools, route to modeling, UV/texturing, animation, particle, PBR, or Hytale guidance, and verify the requested result.927 forge-idiomatic-engineerisala404/forgeForge-focused engineering workflow for Rust applications with generated frontend bindings. Activate this skill for repositories containing a `forge.toml` file, Forge macros, or code generated by the Forge CLI.927 floor-plan-generationeachlabs/skillsGenerate floor plans and architectural layouts using each::sense AI. Create apartment designs, house layouts, office spaces, retail stores, restaurants, and 3D visualizations with furniture arrangements and measurements.927 capacitor-mcpcap-go/capgo-skillsConnect AI agents (Claude Code, Claude Desktop, Cursor, VS Code, Cline, Codex) to Capacitor and Ionic tooling over Model Context Protocol. Covers the awesome-ionic-mcp server (Ionic component APIs, Capacitor plugin docs, Ionic/Capacitor CLI tools), the Capgo hosted MCP at https://api.capgo.app/mcp, the local Capgo CLI MCP (npx @capgo/cli@latest mcp), and Xcode's MCP bridge (xcrun mcpbridge) for building the iOS app from an agent. Use when the user wants to add, configure, verify, or troubleshoot an MCP server for a Capacitor project, or sees errors like "GitHub API rate limit exceeded", "unable to find utility \"mcpbridge\"", or an MCP server that connects with no tools. Do not use for Capgo account operations themselves (capgo-cloud, capgo-cli-usage), app debugging (debugging-capacitor), device logs (ios-android-logs), choosing plugins (capacitor-plugins), or Ionic UI work (ionic-design).923 subagent-creatortech-leads-club/agent-skillsGuide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent, specialized agent, verifier, debugger, or orchestrator that requires isolated context and deep specialization. Works with any agent that supports subagent delegation. Triggers on "create subagent", "new agent", "specialized assistant", "create verifier". Do NOT use for Cursor-specific subagents (use cursor-subagent-creator instead).919 inspector-workbenchcopilotkit/copilotkitRuns Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't use for docs-only Callout updates (load inspector-docs), runtime or core changes with no Inspector UI, showcase cell work, or reading Inspector as a consumer inside an app.916 product-managementvasilyu1983/ai-…s-publicGuides founder-PM discovery, roadmaps, prioritization, and PMF measurement. Use when planning product strategy, metrics, or roadmaps.914 google-drive-automationsickn33/agentic…e-skillsLightweight Google Drive integration with standalone OAuth authentication. No MCP server required. Full read/write access.914 tax-loss-harvestinganthropics/fina…servicesIdentify tax-loss harvesting opportunities across taxable accounts. Finds positions with unrealized losses, suggests replacement securities, and tracks wash sale windows. Triggers on "tax-loss harvesting", "TLH", "harvest losses", "tax losses", "unrealized losses", or "year-end tax planning".914 supermemorysupermemoryai/skillsBuild with the Supermemory v5 API and SDKs (TypeScript `supermemory` 5.x, Python `supermemory` 5.x, `@supermemory/tools` 3.x). Use when an application needs persistent memory across sessions, per-user personalization, a maintained user profile, or semantic search over documents. Covers the namespace-scoped endpoints, exact SDK call shapes, search and ingestion options, typed filters, and the legacy names that must not be emitted.912 experiment-tracking-swanlaborchestra-research/ai-research-skillsProvides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.912