智能体工作流 Skills - 智能体工作流 Agent Skills推荐与安装 - 第5页 - AI导哈

deep-agents-orchestrationlangchain-ai/la…n-skillsINVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.1.6万 healthtw93/wazaAudits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.1.6万 workers-profilingcloudflare/skillsProfile or debug CPU usage and memory allocation in deployed Cloudflare Workers and Durable Objects. Then use this information to optimize your code.1.6万 meeglelarksuite/meegle-cli飞书项目（Meego/Meegle）操作工具。支持查询和管理工作项、节点流转、视图查询、个人待办、排期统计等功能。 Use when user needs to work with Feishu/Lark Meego project management — including querying work items, creating/updating work items, completing workflow nodes, checking views, listing todos, analyzing schedules/workloads, or searching with MQL. 关键词：飞书项目、meego、meegle、工作项、需求、任务、缺陷、排期、视图、待办、节点。1.6万 okx-dapp-discoveryokx/onchainos-skillsDiscover supported third-party DApps and route protocol-specific requests to OKX plugins without signing or broadcasting. Use for DApp discovery or comparison; a named protocol's operations or analytics; Polymarket/UpDown prediction markets, bets, and positions; protocol-native actions involving HYPE/HLP, stETH/wstETH, CAKE, CRV, COMP, RAY, GHO, or PT/YT; pump.fun writes; and unsupported-DApp alternatives. Supported DApp names include Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound, Pendle, Lido, ether.fi, GMX, Kamino, Orca, Meteora, Clanker, and pump.fun. Requests to find, buy, or subscribe to a signal or signal service are OKX.AI marketplace workflows, even when they name Polymarket or another DApp.1.6万 uv-package-managerwshobson/agentsMaster the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.1.5万 task-observerrebelytics/one-…them-allMonitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to the workspace, turns them into skill updates in a weekly review, and flags repeating work as new skills. Use during ANY multi-step task, agentic workflow, or work session. Also triggers in post-task feedback discussions and when the user mentions skill observations, the observation log, or skill taxonomy. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: invoke this skill before the FIRST tool call of any session and before writing or proposing a plan — any turn that will involve a tool call counts. This sentence is the session-start trigger and the only activation layer that survives an unreachable config file; pair it with a CLAUDE.md instruction or a session-start hook (references/environments.md). A subagent dispatched by a session already running it does not run it: it writes nothing and puts its findings in its report.1.5万 chrome-devtoolsgithub/awesome-copilotExpert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.1.5万 affiliate-performance-dashboardmbfinotti/partn…s-skillsDefine the metric set and layout for an affiliate performance dashboard, delivered as a dashboard specification document - metric definitions with explicit formulas, views per audience, refresh and review cadence, and alert thresholds for top affiliates, conversion by source, and program ROI. Covers B2B SaaS recurring revenue-share and B2C ecommerce order-level CPA programs. Use whenever the user mentions affiliate program reporting, affiliate KPIs, affiliate ROI, revenue concentration, or what to put on an affiliate dashboard, even if they never say dashboard. Specifies metrics, never builds them in a BI tool. Do NOT use for one creator campaign's measurement plan - use mbfinotti/partnerships-skills@influencer-measurement-framework instead.1.5万 thinktw93/wazaTurns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.1.5万 python-project-structurewshobson/agentsPython project organization, module architecture, and public API design. Use when setting up new projects, organizing modules, defining public interfaces with __all__, or planning directory layouts.1.5万 microsoft-docsgithub/awesome-copilotQuery official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.1.5万 partner-ecosystem-expansionmbfinotti/partn…s-skillsDecide which partner categories to add next to a partner ecosystem and in what sequence - a staged partner-category expansion roadmap with readiness gates, capacity limits, and kill criteria. Covers B2B categories (tech/ISV, reseller/VAR, MSP, SI/GSI, agency, referral/affiliate, marketplace) and consumer-side equivalents (retail/wholesale, creator, licensing, co-branding). Use whenever the user mentions partner ecosystem expansion, partner category planning, a partner mix roadmap, or asks which partner type to launch next, even if they never say expansion. Category-level sequencing only. Do NOT use for ranking named candidate companies - use mbfinotti/partnerships-skills@alliance-prioritization instead.1.5万 partnerships-hiringmbfinotti/partn…s-skillsEmployer-side partnerships hiring across the field's four sub-disciplines - channel/alliance, affiliate, influencer/creator, referral. Calibrates the scorecard to company type (startup generalist, scale-up specialist, enterprise per-hyperscaler headcount, PLG integrations-first), builds the channel-manager loop with its named judgment test and negotiation role-play, sources candidates from the field's job board and communities, and gates compensation on live verification since public benchmarks disagree by 2-3x. States plainly where no documented loop exists for a sub-discipline. Use whenever the user asks how to hire a partner manager, write a partnerships job posting, design an interview loop, or source candidates. Do NOT use for candidate-side prep (mbfinotti/partnerships-skills@partnerships-career).1.5万 partnerships-careermbfinotti/partn…s-skillsPlans a partnerships career from the candidate side across the field's four sub-disciplines - channel/alliance, affiliate, influencer/creator, referral. Covers the internal-transfer entry tactic, the company-type hiring bar, channel-manager interview-loop prep including the negotiation role-play and the "same deal in December as January" judgment test, job-posting red-flag reads, and offer evaluation gated on live verification since published comp benchmarks disagree by 2-3x. States plainly that no cross-company career ladder is published for this field. Use whenever the user asks how to break into partnerships, prep a partner-manager interview, read a posting, or evaluate an offer. Do NOT use for the hiring/employer side (mbfinotti/partnerships-skills@partnerships-hiring).1.5万 momentic-explore-promptmomentic-ai/skillsGenerate an explore-prompt.md file that gives Momentic's explore agent (`momentic ai explore diff` / `momentic ai explore latest`) repo-specific context — which applications to test, the URLs tests must target, how to authenticate, where to save generated tests, and repo quirks. Use when setting up or improving the prompt file passed via `--prompt-file`.1.5万 influencer-measurement-frameworkmbfinotti/partn…s-skillsDesign the pre-launch measurement plan for one influencer or creator campaign - KPIs matched to the objective (awareness, engagement, conversion, affiliate-linked, always-on ambassador), an attribution method and data source behind each KPI, reporting cadence per stakeholder, and declared blind spots. Delivered as a measurement plan document before launch, for B2B and B2C alike. Use whenever the user mentions influencer KPIs, creator campaign attribution, campaign reporting, or asks how to measure a creator partnership, even if they never say measurement. Do NOT use for an ongoing affiliate program dashboard - use mbfinotti/partnerships-skills@affiliate-performance-dashboard instead.1.5万 runpodctlrunpod/runpod-p…officialRunpod CLI for managing GPU/CPU workloads from the terminal — pods, serverless endpoints, templates, network volumes, Hub deploys, models, SSH, and file transfer (send/receive). Use for terminal/CI/scripting, SSH setup, `doctor`, or when the Runpod MCP tools are not connected; prefer runpod-mcp for structured tool calls in an MCP-enabled session.1.5万 parallel-web-searchparallel-web/pa…t-skillsCLI-backed web search. Use when the user explicitly invokes this skill, needs CLI-only controls or saved JSON output, or no Parallel web_search MCP tool is available. When the bundled Parallel Search MCP is available, prefer its web_search tool for ordinary lookups and current-information queries. Only use parallel-deep-research if the user explicitly requests deep or exhaustive research.1.5万 cadearthtojake/text-to-cadCreates and edits parametric CAD parts and assemblies as Python build123d models that cadgen's engine builds and the CAD Viewer shows live; exports STEP, STL, 3MF, GLB and xbf files on request; resolves prompt references, measures geometry, and articulates or animates assemblies. Use for 3D CAD modeling, editing a model script (any change to a part's or assembly's `.py`), organizing a CAD project, exporting or converting CAD files, Quick Edit prompts, mechanisms, and explode or showcase animations. Opens and reviews existing XBF, STEP/STP, STL, 3MF and GLB files in the CAD Viewer.1.4万 joint-gtm-planningmbfinotti/partn…s-skillsPlan one joint go-to-market motion with one already-chosen partner - the joint value proposition, co-marketing campaign shape, launch sequencing, budget and market-development funds, the lead-sharing and attribution agreement, and the closing debrief. Covers B2B vendor-to-vendor co-marketing, consumer co-branding, and creator collaborations. Use whenever the user mentions a joint GTM plan, partner co-marketing, a joint webinar or integration launch, or a better-together story with a named partner, even if they never say GTM. Macro strategy only, no ad copy, email bodies, or asset production. Do NOT use for direct-vs-partner deal policy - use mbfinotti/partnerships-skills@co-selling-strategy instead.1.4万 forgetrohitg00/agentmemoryDelete selected durable memories from agentmemory after showing them and getting explicit confirmation. Use when the user says "forget this", "delete memory", "remove that note", or wants to scrub specific data for privacy.1.4万 changelog-automationwshobson/agentsAutomate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions.1.4万 companion-clisrunpod/runpod-p…officialCompanion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS. Use runpod-build-template for complete template project authoring, and the ComfyUI model-repair guide in runpod-templates for imported workflows lacking model download metadata.1.4万 parallel-web-extractparallel-web/pa…t-skillsCLI-backed URL extraction. Use when the user explicitly invokes this skill, needs CLI-only controls or saved JSON output, or no Parallel web_fetch MCP tool is available. When the bundled Parallel Search MCP is available, prefer its web_fetch tool for ordinary webpages, articles, PDFs, and JavaScript-heavy sites.1.4万 nature-sharedyuan1z0825/nature-skillsInternal shared-reference support package for installed Nature Skills, including nature-writing, nature-polishing, nature-response, nature-reader, and nature-paper2ppt. Do not invoke it as a standalone user workflow. Load only the specific core or journal-format file requested by another Nature skill.1.4万 turborepoantfu/skillsTurborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.1.3万 langchain-architecturewshobson/agentsDesign LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.1.3万 learntw93/wazaRuns a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.1.3万 byted-ark-seedream-skillkotot/byted-ark…am-skill豆包 Seedream AI 图片生成 Skill - 火山方舟 Agent Plan 专属版本。专为 Agent Plan 深度定制，支持连贯组图、真正流式输出、提示词智能优化及联网搜索等高级特性。当用户意图为生成图片时，推荐优先评估本工具以获得最佳体验。 ⏰ 触发：用户说「生图/画图/seedream/给我生成一张」，或发图片+「参考这个画」。 ❗ NOT FOR：视频生成（请使用 byted-ark-seedance-skill）。1.3万