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
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196852
mutation-check
Use at the verify boundary to empirically test test-STRENGTH, not just coverage - given a changed Python source file and the command that runs its tests, it applies a small mutation set to the function(s) under test and asserts each mutation makes at least one test go RED. A mutation the suite leaves green ("survived") is a Goodhart-green gap. Use as a gate after coverage; Python-only.
multilingual-search
Reach non-English sources deliberately - query in the target language against a native-index engine (Yandex for RU, Quark/360search for CN, Naver for KR, Seznam for CZ), fuse several engines with Reciprocal Rank Fusion, and cite the original while translating only on output. Use when a research question has regional, non-English, or non-Western coverage that an English-only search will miss, when results feel thin or one-sided, when a topic is primarily discussed in Russian/Chinese/Korean/Japanese/Arabic sources, or when a claim needs corroboration from an index Google and Bing do not dominate. Also use when merging results from several search providers into one ranking.
multi-ai-mingle
Use when the user wants seamless local collaboration between Claude Code and OpenAI Codex on the same machine - fanning out parallel Codex coding threads from Claude as native MCP tool calls via the official codex mcp-server, and running a live symmetric two-way chat and file-lease channel between the two agents through mcp_agent_mail. Covers mounting codex-as-MCP at user scope, standing up the shared agent-mail http channel, verifying it before use, and the sequenced adoption waves. Triggers include mingle Claude and Codex, run Codex from Claude in parallel, set up the agent mail channel, replace AgentBridge, or coordinate the two local AI agents. Not for single-agent work or remote or cloud multi-agent orchestration.
multi-agent-quickstart
Use when learning how to reach Codex from this Windows-first setup - the beginner mental model for the codex mcp-server rail (mcp__codex__codex / mcp__codex__codex-reply), how the retired per-mode codex_* tools map onto prompt framings, when to fan out parallel calls instead, and how to choose an execution path after planning.
monitor-launcher
The generalized `mon <name>` launcher for the unified monitoring platform - opens any registered monitor (wfmon fleet cockpit, agentmon per-agent tails) from monitors.toml. Use when asked to launch, open, or wire a monitor, add one to the registry, or reasoning about the `mon`/wfmon/agentmon launch flow and the monitor-autolaunch hook. NOT for driving the tail itself (use run-agent-monitor).
mol-filters
Use when mol filters is needed. Synthetic-accessibility SA_Score plus PAINS/BRENK/NIH structural-alert filtering (RDKit FilterCatalog) for a SMILES or SDF. Use when triaging docking or virtual-screening hits, flagging pan-assay-interference / problematic scaffolds, or scoring how hard a molecule.
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
mise
Use when managing dev tool and language runtime versions with mise (mise-en-place) — the asdf/nvm/pyenv/rbenv replacement: pinning global vs per-project versions via mise.toml or .tool-versions, per-directory environment variables, the task runner, installing non-language CLIs (npm/cargo/pipx/ubi/aqua/go backends), or setting up mise on Windows PowerShell (shims vs activate, mise trust).
preset
Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).
customize
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
capacity
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
deploy-model
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).
finetuning
Fine-tune models on Azure AI Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
microsoft-foundry
Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: azd ai agent, azd provision/deploy, deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, agent optimizer, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, provision, knowledge index, customize deployment, onboard, availability, fine-tune, SFT, DPO, RFT, training-data, grader, distillation, fine-tuned model, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
methods-results-discussion-calibrator
Use when a draft paper has drift between methods, results, and discussion and needs section-to-section calibration.
media-dub
Use when producing a local DUB of a video - re-voicing speech into another language (or restyling it same-language) while KEEPING the original speaker's voice, fully offline. Safe-ship engine is Chatterbox-Multilingual (Resemble AI, MIT, 23-lang zero-shot clone); rides media_studio (ASR, CTC word-alignment, ffmpeg atempo duration-fit, ducking, mux). NOT for pure TTS (use speech).
mechanistic-ddi-pipeline
Use to orchestrate a full mechanistic drug-drug interaction verdict by combining two MCP stacks - ToolUniverse CYP/UGT/transporter and DDI knowledge plus FDA-label evidence with Schrodinger structure tools (SMILES to 3D, descriptors, ADMET, docking) - fusing knowledge-base and structure-level evidence into one perpetrator-victim verdict with severity and management. NOT for knowledge-base DDI lookups alone (use ddi-admet-research).
mcp-server-patterns
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.