智能体工作流 Skills - 智能体工作流 Agent Skills推荐与安装 - 第34页 - AI导哈

5-buildchallengepost/l…i-basicsTurn the approved plan into ordered working build steps, then build the app step by step — verifying and committing each one — in learn mode or fast mode. Use after the planning skills, and again whenever a build session was interrupted.1832 4-specchallengepost/l…i-basicsTurn the approved PRD into a technical blueprint the build can follow — stack, where it runs, components, data, file structure — calibrated to the learner and sized to a proof of concept. The last planning step before code. Run after 3-prd.1831 2-scopechallengepost/l…i-basicsFind or sharpen the project idea and write the scope doc. The first and most important planning conversation — a focused flipped-interaction interview that pulls the idea out of the learner's head, then cuts it down to a coherent proof of concept. Run after 1-start.1831 Autodesksfkislev/flueControl Autodesk desktop apps - 3ds Max and friends - from the shell via Flue, without an MCP server.1830 vss-manage-alertsnvidia/skillsUse for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.1830 custom-metricslaunchdarkly/ai-toolingCreate, track, retrieve, update, and delete custom business metrics for configs. Covers full lifecycle: define metrics with the LaunchDarkly MCP server, emit events via SDK, and query results.1821 snippetslaunchdarkly/ai-toolingCreate and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.1818 migratelaunchdarkly/ai-toolingMigrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.1818 agent-graphslaunchdarkly/ai-toolingCreate and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.1816 p9tanweai/puaP9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.1815 cli-bridgestarchild-ai-agent/official-skillsManage short-code bundles that authorize the local starchild CLI to talk to this agent, including the agent-shell local-exec channel and the local MCP proxy (stdio MCP servers on the user's machine). Use when connecting or disconnecting the starchild CLI (e.g. mint a CLI bridge code, list my CLI bundles, revoke an old CLI session, let the agent run shell commands on the user's own machine, or drive a local app via a stdio MCP server — Blender, Figma, Godot, computer-use, etc.).1815 astrale-domainastrale-os/cliCreate, modify, test, migrate, or debug Astrale Domains: Schema, Policies, Action/Workflow runtime, integrations, Views, Datasets, and deployment. For a new Domain follow the phased workflow; for focused work load only the relevant references.1815 InDesignsfkislev/flueControl Adobe InDesign from the shell via Flue - ExtendScript bridges without an MCP server.1809 para-memory-filespaperclipai/paperclipUse a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions. Trigger on saving facts, daily notes, entity records, weekly synthesis, recall, tacit user patterns, or plan memory.1802 p7tanweai/puaP7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8. Produces: implementation plan + code + 3-question self-review, delivered via [P7-COMPLETION].1801 plan-payrollanthropics/know…-pluginsRuns the payroll-confidence chain end to end — forecasts cash across the payroll window with cash-flow-snapshot, ranks and drafts overdue-invoice reminders with invoice-chase to close any gap, then assembles timesheets, flags every anomaly, and stages the run with payroll-prep. On Gusto the run is staged for the owner to submit; on QuickBooks Payroll, or with no payroll system, the last step is a validated run sheet the owner keys in. This chain never presses the payroll button. Builds on the ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books), with Gmail or M365, PayPal, Square, Stripe, and either Gusto or QuickBooks Payroll adding detail, and falls back to CSV and timesheet uploads. Use it whenever payroll is the worry, including "can I make payroll," "payroll is due Friday," "plan payroll," "will I have enough to pay the crew," or "I need to run payroll but money is tight." Accepts optional horizon and payroll-date arguments.1800 rivet-actorsrivet-dev/skillsActors: The primitive for agent orchestration.1799 alan-plansupatest-ai/alan-skillsCreate an implementation plan artifact in Alan1797 sequential-thinkingmrgoonie/claude…t-skillsUse when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.1792 hicks-lawowl-listener/de…r-skillsApply Hick's Law — decision time grows with the number of simultaneous choices. Use when a screen offers too many options at once. For how many items survive in memory afterwards, use `millers-law`.1792 nemo-rl-brev-etiquettenvidia/skillsBrev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.1790 ce-agent-native-architectureeveryinc/compou…g-pluginBuild applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.1783 millers-lawowl-listener/de…r-skillsApply Miller's Law — chunk information into groups of about four to fit working memory. Use when grouping fields, menu items, or steps. For reducing the number of choices offered, use `hicks-law`.1780 workflow-automationhubspot/agent-cli-skillsList, inspect, create, update, and delete HubSpot workflows (v4 flows API) from the `hubspot` agent CLI, not the `hs` developer CLI. Classic v3 contact-based workflows are not covered.1777 conducting-user-interviewsrefoundai/lenny-skillsHelp users run better customer and user interviews. Use when someone is preparing for user research, planning discovery interviews, writing interview questions, analyzing interview findings, or trying to understand customer needs.1771 r3f-texturesenzed/r3f-skillsConfigure textures in React Three Fiber, including color spaces, UV channels, sampling, video, and render targets. Use for texture appearance or memory issues; use loader guidance for model-loading workflows.1771 nv-segment-ct-finetunenvidia/skillsRuns standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT NIfTI image/label datasets, with optional MONAI-native MLflow tracking and checkpoint evidence. Uses softmax for predefined, mutually exclusive classes; keeps the standard workflow when point prompts or runtime-variable classes are needed. Not for clinical validation.1770 investigate-anythinguseosint/skillsStart-here router and tradecraft baseline for any investigation into a person, company, domain, image or selector. Sets authorised scope, turns a vague request into an answerable intelligence question, writes a collection plan, picks the right workflow for the starting selector, and applies source grading and competing-hypothesis discipline. Use for "investigate this person or company", "do OSINT on X", "where do I start", or any open-source intelligence, due diligence, background or attribution task. Applies across due diligence, fraud, threat intelligence, journalism and compliance. Reference at useosint.com/skills/investigate-anything.1768 using-n8n-mcp-skillsczlonkowski/n8n-skillsUse when building, editing, validating, testing, or debugging an n8n workflow through the n8n-mcp MCP server — designing a flow, configuring a node, writing an expression or Code node, wiring credentials, or fixing one that misbehaves. The entry-point skill for the n8n-mcp-skills pack: it routes you to the right specialist skill, gives working knowledge of every n8n-mcp tool from turn one, and states the rules that keep workflows from breaking in production. Always consult it first on any n8n, workflow, node, or automation task — even a quick one-off, and even when the user names no skill — because n8n's surface drifts between versions and the specialist skills prevent silent failures.1755 ralph-loopgiuseppe-trisciuoglio/developer-kitRalph Wiggum-inspired automation loop for specification-driven development. Orchestrates task implementation, review, cleanup, and synchronization using a Python script. Use when: user runs /loop command, user asks to automate task implementation, user wants to iterate through spec tasks step-by-step, or user wants to run development workflow automation with context window management. One step per invocation. State machine: init → choose_task → implementation → review → fix → cleanup → sync → update_done. Supports --from-task and --to-task for task range filtering. State persisted in fix_plan.json.1748