智能体工作流 Skills - 智能体工作流 Agent Skills推荐与安装 - 第48页 - AI导哈

cli-evalcheaper-inference/omnirouteCreate and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.1029 reference-decodepostplusai/post…s-skillsTurn reference videos, frames, or contact sheets into reusable hook and visual rules for new creative prompts, with clear imitation boundaries.1028 peft-fine-tuningorchestra-research/ai-research-skillsParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.1024 launch-tier-planneraaron-he-zhu/aa…g-skillsUse when the user asks to "plan my launch tier", "how big should this launch be", or "build a launch risk register with kill criteria"; produces a tier decision (Tier 1 flagship all-channel / Tier 2 targeted / Tier 3 changelog-level), a launch-type declaration (new-product / feature / relaunch / partnership with co-marketing split), an effort calibration matrix (tier to channel intensity and asset scope), D0/W1/M1 KPI targets (labeled Estimated), a risk register (likelihood x blast-radius, owners, mitigations, kill criteria / rollback thresholds), and a T-8w to T+4w timeline skeleton. Not for picking the launch date or window — use launch-window-planner; not for creator-channel launch campaigns — use campaign-planner. 发布分级/发布类型/风险登记册/kill criteria1023 comfyui-troubleshootermckruz/comfyui-expertDiagnose ComfyUI errors, workflow failures, and quality issues. Suggests fixes based on error patterns, missing dependencies, and community-known workarounds. Use when ComfyUI workflows fail or produce unexpected results.1022 participation-warmup-planneraaron-he-zhu/aa…g-skillsUse when the user asks to "plan the participation ramp before we promote", "how much account history or karma do we need in this community", or "design entry incentives and member lifecycle for our own Discord"; produces the per-community pre-promotion warming plan — account-history/tenure expectations (Estimated, named sources), a give-before-ask ledger spec, a per-community etiquette + rule digest with last-verified dates, and the warming → active graduation criteria that channel-registry requires as state-transition evidence — plus the owned-community variant (entry paths + member lifecycle for your own Discord/Slack/forum/企业微信私域). Not for launch-day submissions or T-0 threads — use community-launch-runner. 社区预热/先给后取/账号养成/毕业标准1021 momentum-planneraaron-he-zhu/aa…g-skillsUse when the user asks to "keep the launch momentum going after launch week", "plan a changelog / release-notes cadence as GTM", or "is this update worth a relaunch"; produces a T+1→T+30 momentum plan — a launch-moment calendar (milestone / shipped-loop / badge moments only), announcement-tier routing (major = full-channel, medium = targeted, minor = changelog-only), a relaunch legitimacy call, spike-to-owned handoff briefs, and the next Tier-1 moment with launch-stacking spacing. Not for the 30-day content-reuse map or paid amplification execution — use content-amplifier; not for planning the next launch end to end — use launch-tier-planner. 抗第二周断崖/changelog-as-GTM/relaunch/下一发布时刻1021 ralph-tui-create-beadssubsy/ralph-tuiConvert PRDs to beads for ralph-tui execution. Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads.1020 deep-interviewyeachan-heo/oh-…audecodeSocratic deep interview with mathematical ambiguity gating before explicit execution approval1017 graftschrepa/graftUse when building, refactoring, or documenting Graft apps and proxies, including when asked to create a tool server, API server, dual-protocol server, or MCP-HTTP bridge. Graft's core thesis: define tools once and serve them as both HTTP REST endpoints and MCP tools from the same server, with discovery, docs, and OpenAPI generated automatically. Covers concrete actions such as defining tools and handlers, configuring authentication middleware, setting up HTTP and stdio transports, generating OpenAPI documentation, wrapping existing APIs via proxy mode, and wiring up the full CLI workflow.1015 last-20-percentjuliusbrussee/skillsFinds and finishes the last 20% of a built solution — the experiential layer agents skip: what the output actually reads like, which pages or screens should exist, first-run and empty states, opinionated defaults, the golden path. Use when planning any build so the magic gets specced as concretely as the plumbing, before calling any build "done", when a solution works but feels like a demo, or when the user says "last 20%", "finish this", "make it actually good", "is this actually done", or "why does this feel flat".1014 ghost-exoghostsecurity/skillsThe single interface for building, improving, and debugging exo workflows. Routes to one of three intents. BUILD takes a rough idea, or an agent template slug from the ghostsecurity.ai catalog, through interrogation, assessment, resource creation in dependency order, and one manual run, then hands off. IMPROVE runs the observe-and-iterate loop over recent runs, proposing and applying changes behind two gates. DEBUG diagnoses one failed or misbehaving run by walking the dependency graph of everything it touched. Use whenever the user wants to create a new exo workflow, iterate on or improve an existing one, or find out why a specific run failed.1013 senior-prompt-engineerdavila7/claude-…emplatesWorld-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.1011 memory-ci-capturebasicmachines-co/basic-memorymemory-ci-capture — an installable skill for AI agents.1011 agentmail-toolkitagentmail-to/ag…l-skillsAdd AgentMail tools to agent frameworks with the TypeScript or Python AgentMail Toolkit. Use for Vercel AI SDK, LangChain, OpenAI Agents SDK, LiveKit Agents, or MCP adapters; do not use for direct mailbox operations, raw SDK implementation, CLI usage, or MCP client setup.1011 ray-trainorchestra-research/ai-research-skillsDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.1008 muapi-workflowsamuraigpt/gene…a-skillsBuild, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.1008 public-relationskostja94/market…g-skillsWhen the user wants to plan PR, write a press release, or manage media relations. Also use when the user mentions "public relations," "PR," "press release," "media relations," "news release," "journalist," "media coverage," "product announcement," or "earned media." For on-site "As Seen In" or logos page, use press-coverage-page-generator.1007 debugging-mwaa-workflowaws/agent-toolk…-for-awsDiagnoses and root-causes Amazon MWAA workflow failures across Provisioned (Python DAG) and Serverless (YAML workflow) environments. Provisioned uses aws mwaa invoke-rest-api, CloudWatch log groups, and get-environment; Serverless uses aws mwaa-serverless API (GetWorkflowRun, ListWorkflowRuns, GetTaskInstance) and CloudWatch logs. Covers failed runs and tasks, DAGs not appearing, import errors, worker OOM, IAM denials, and dependency drift. Triggers on: DAG failed, task failed, workflow run failed, MWAA error, debug my DAG, why did my workflow fail, DAG not showing up, MWAA import error, requirements failing, worker crashed, serverless run failed. Not applicable to authoring workflows (handled by authoring-mwaa-workflow), running or smoke-testing a workflow (handled by testing-mwaa-workflow), or CI-CD deploy failures.1006 aem-workflowadobe/skillsSingle entry point for all AEM as a Cloud Service Workflow skills. Covers workflow model design, custom process step and participant chooser development, launcher configuration, workflow triggering, and production support including debugging stuck/failed workflows, triaging incidents with Cloud Manager logs, thread pool analysis, and Sling Job diagnostics for the Granite Workflow Engine.1005 dispatcheradobe/skillsSingle entry point for all AEM as a Cloud Service Dispatcher skills. Covers config authoring, technical advisory, incident response, performance tuning, security hardening, and full lifecycle orchestration for the Adobe Dispatcher Apache HTTP Server module and its HTTPD/dispatcher configuration.1003 authoring-mwaa-workflowaws/agent-toolk…-for-awsAuthors and deploys MWAA workflow artifacts: Python Airflow DAGs for provisioned environments or YAML workflow files for Serverless. Covers operator selection, timeout design, retry strategy, scheduling, failure notifications, idempotency, and MWAA Serverless schema compliance. Deploys the artifact (S3 DAG upload or Serverless CreateWorkflow/UpdateWorkflow), creates an environment inline when approved, and redeploys fixes, then optionally hands off to testing-mwaa-workflow. Triggers on: create a DAG, write a pipeline, build a workflow, orchestrate tasks, Airflow DAG, data pipeline, schedule a job, deploy a DAG, deploy a workflow, YAML workflow. Not applicable to converting or migrating existing DAGs between provisioned and serverless (conversion is out of scope), running or smoke-testing a deployed workflow (handled by testing-mwaa-workflow) or diagnosing a failed run (handled by debugging-mwaa-workflow).1003 testing-mwaa-workflowaws/agent-toolk…-for-awsTests Amazon MWAA workflow execution end-to-end: trigger a run and monitor it to completion for Provisioned (Python DAG, via Airflow REST API) and Serverless (YAML workflow, via StartWorkflowRun). Verifies the artifact is deployed and parse-ready, triggers with confirmation, polls to terminal state, and on failure delegates diagnosis to debugging-mwaa-workflow and artifact/redeploy fixes to authoring-mwaa-workflow, then retests up to a capped number of attempts. Triggers on: test my DAG, test my workflow, run my DAG, trigger a test run, does my DAG work, smoke-test the pipeline, verify my workflow runs, execute my DAG to check it. Not applicable to writing or deploying a new workflow (handled by authoring-mwaa-workflow), or for diagnosing why a run failed or root-causing an error (handled by debugging-mwaa-workflow).1002 value-creation-plananthropics/fina…servicesStructure post-acquisition value creation plans with revenue, cost, and operational levers mapped to an EBITDA bridge. Includes 100-day priorities, KPI targets, and accountability frameworks. Use when planning post-close execution, preparing operating partner materials, or building a board-ready value creation roadmap. Triggers on "value creation plan", "100-day plan", "post-close plan", "EBITDA bridge", "operating plan", or "value creation levers".1001 upgrading-mwaa-environmentsaws/agent-toolk…-for-awsUpgrades an MWAA environment to a newer Airflow version — within 2.x, within 3.x, or across the 2.x-to-3.x boundary. Computes the version-jump path, inserting the 2.11.x stepping-stone and Python-transition step when needed. Chooses an approach by whether run history and the same environment (URL/ARN) must be kept: a new-environment upgrade (blue-green), a rehearsed in-place upgrade validated on a test copy, or a direct in-place upgrade. Runs Ruff scanning and deprecation-warning log scans for 3.x moves, plus Docker validation, batched deployment, and switchover. Saves a resumable upgrade plan for multi-session work. Triggers on: upgrade MWAA, upgrade Airflow, migrate to Airflow 3, MWAA Airflow 3, Airflow 2 to 3, preserve Airflow history, keep same MWAA environment, blue-green cutover, validation environment before cutover. Not for authoring new DAGs (authoring-mwaa-workflow), debugging unrelated DAG failures (debugging-mwaa-workflow), or MWAA Serverless YAML workflows (provisioned Python DAGs only).1001 claude-md-progressive-disclosurerdaymade/claude-…e-skillsOptimizes or restructures CLAUDE.md/AGENTS.md with progressive disclosure and zero information loss. Use when the user asks to optimize, audit, 精简/瘦身/重构, or split instruction files, asks for their best practices (最佳实践), sees Memory files taking a large share of /context, reports rules in instruction files being ignored, or a task starts moving instruction sections. Not for generic task drift unless instruction files are in scope; not for moving memory entries into docs (use claude-code-ops-router).998 education-programkostja94/market…g-skillsWhen the user wants to plan, implement, or optimize student and education discount programs. Also use when the user mentions "student discount," "education discount," "student plan," "for students," ".edu discount," "academic pricing," "student verification," "SheerID," "UNiDAYS," or "education program." For startup pricing page, use startups-page-generator.997 unslothorchestra-research/ai-research-skillsExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization997 crewai-multi-agentorchestra-research/ai-research-skillsMulti-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.996 media-routerpostplusai/post…s-skillsRoute audio, video, transcript, subtitle, and edit-prep requests into the right media-understanding workflow before execution. Use this when the user wants transcription, subtitle generation, beat mapping, B-roll planning, or edit-ready outputs and the first question is which skill and model chain should run.992