Catalogue de skills·2420 skills
Tous les skills
Des skills prêts à l'emploi — copie le Markdown du skill et colle-le dans ton agent.
Compatible avec
Liste des skills du catalogue Arboris
2420 skills sur 2420
Skill
Description
Agents
Copier le skill
Stitch RemotionFrontend & UI70
Generate walkthrough videos from Stitch projects using Remotion with smooth transitions, zooming, and text overlays
Agentic OsAgents & Orchestration69Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.
Gitnexus Explorer (Nous Research)Données & Recherche69Serve an interactive codebase knowledge graph web UI.
Qnn Debug (Alibaba)Agents & Orchestration69
MNN QNN（高通 HTP/NPU）后端的问题定位、修复与算子适配。覆盖运行时报错（1002/6000/1003/6004）、模型转换/算子校验失败、推理结果异常、精度不达标、以及性能问题;并指导为 QNN 新增/适配算子。核心方法:用 MNN2QNNModel --dump_intermediate_outputs 一次性导出 QNN 全部中间张量,与 CPU(fwd=0) 基线逐张量对比,直接定位首个出错算子(旧的 testMNNFromOnnx.py 截断二分已降为回退手段);区分“真 bug/量化/HTP fp16 精度”;新增算子先查 SDK 算子文档(MasterOpDef/HtpOpDefSupplement)再实现。
Quarkus VerificationVérification69Verification loop for Quarkus projects: build, static analysis (Checkstyle, PMD, SpotBugs), tests with JaCoCo coverage, OWASP dependency and container security scans, GraalVM native compilation, health checks, and config validation. Use when verifying a Quarkus service before a PR, after major refactoring or dependency upgrades, or pre-deploy.
Vulkan Optimize (Alibaba)Données & Recherche69
MNN Vulkan 后端 kernel/算子性能优化与新特性集成。覆盖 benchmark 基线、kernel 优化迭代、集成验证全流程，以及 GLSL .comp + makeshader 双轨、conv1x1/attention dispatcher 多路径（coopMat/subgroup/nosubgroup）、cooperative matrix、packed weight 设计、pipeline cache、CPU 侧调度瓶颈、Adreno/Mali/Apple 多 vendor 真机验证等参考知识。
Audit Permissions (Microsoft)Auth & Sécurité68Audits existing table permissions on a Power Pages site by analyzing them against site code and Dataverse metadata, then GRADES the configuration with deterministic 1–5 scores across 3 security/usability/correctness categories (9 dimensions). Detection is anchored by a recurring-issue catalog so findings and severities stay consistent run-to-run. Generates an HTML report with an at-a-glance verdict and per-category scores in the Overview plus a single list of **major/minor** issues (each major issue labelled permissions-only or upstream-caused with a short justification), and suggested fixes. Use when the user wants to review, verify, check, score, or grade table permissions for security issues.
Browserbase UI TestTests68
AI-powered adversarial UI testing via the browse CLI. Analyzes git diffs to test only what changed, or explores the full app to find bugs. Tests functional correctness, accessibility, responsive layout, and UX heuristics. Use when the user asks to test UI changes, QA a pull request, audit accessibility, or run exploratory testing. Supports local browser (localhost) and remote Browserbase (deployed sites).
Django SecurityAuth & Sécurité68Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations. Use when reviewing Django authentication, authorization, input handling, or deployment settings.
Dotnet Trace Collect (.NET)Agents & Orchestration68
Guide developers through capturing diagnostic artifacts to diagnose production .NET performance issues. Use when the user needs help choosing diagnostic tools, collecting performance data, or understanding tool trade-offs across different environments (Windows/Linux, .NET Framework/modern .NET, container/non-container).
Flutter Dart Code ReviewFrontend & UI68Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture. Use when reviewing Flutter or Dart code, whatever state management library the project uses.
Hf Cloud Serving Image Selection (Hugging Face)Infra, Ops & Workflow68Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
Huggingface Paper Publisher (Hugging Face)Données & Recherche68Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Notion (Nous Research)Données & Recherche68Notion API + ntn CLI: pages, databases, markdown, Workers.
Snap (.NET)Infra, Ops & Workflow68
Perform a branch snap (release branch cut) for dotnet repos like dotnet/roslyn. Use when: snapping a branch, cutting a release branch, creating a release branch, merging main into release, updating VS insertion config, updating darc subscriptions for a snap, moving milestones, or asked about snap workflow.
Inherit Legacy StyleDocs & Écriture67
Prevent AI style drift on legacy projects by scanning the codebase for implicit conventions, resolving conflicts with the operator one at a time, and writing an enforceable .ai-style-rules.md (Golden Files, naming rules, DONTs) plus an optional CLAUDE.md hook. Use when onboarding an AI agent onto a hand-written legacy codebase or extracting a project's unwritten coding rules.
Osdc Runners Nodepools (PyTorch)Données & Recherche67
OSDC runners, NodePools, BuildKit, GitHub Actions constraints, EKS node taints, image mirroring, and the runner/nodepool change checklist. Applies to ~/meta/ci-infra/osdc. Load when modifying runners, nodepools, BuildKit, or node configurations.
Qwenpaw Usage (Alibaba)Infra, Ops & Workflow67
QwenPaw 命令行使用技巧：涵盖心跳（Heartbeat）配置、定时任务管理、Docker 打包部署、工作区导出迁移等操作。当用户要求添加心跳任务、配置定时自检、打包 QwenPaw 实例、部署到其他服务器、生成 Dockerfile 或 docker-compose 文件时使用本 skill。
Setup Datamodel (Microsoft)Agents & Orchestration67Creates Dataverse tables, columns, and relationships for a Power Pages site based on a data model proposal. Use when the user wants to set up the data model, create database tables, or build the Dataverse schema for their site.
Skill ComplyAuth & Sécurité67Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines. Use when checking whether agents actually follow the skills, rules, and definitions they were given, rather than assuming they do.
Agent Payment X402Agents & Orchestration66
Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk, X Layer through OKX Payments / OKX Agent Payments Protocol, and Solana plus multi-network EVM through the upstream x402 packages with facilitator-based settlement. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.
Nemo Gym Pivot Datasets (Nous Research)Données & Recherche66Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts. Covers Gym Responses-style row conversion, pivot selection, single-step tool-use configs, agent_ref alignment, verifier knobs, expected-action row contracts, and train/eval usage.
Refactor Memory (vinta)Agents & Orchestration66Use when refactoring Claude Code or Codex memories to remove stale or derivable entries, resolve contradictions, promote standing instructions, or reorganize recall. Not for standalone CLAUDE.md, AGENTS.md, or rules cleanup
Safety GuardAuth & Sécurité66Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze locks writes to one directory, and Guard combines both. Advisory: the agent applies these rules itself; no hook ships with it. Use when working on production systems, running agents autonomously, restricting edits to a directory, or during migrations, deploys, and data changes.
Tldraw Offline (Nous Research)Données & Recherche66Drive and script tldraw offline canvases with an agent.
Ast Grep (Nous Research)Données & Recherche65AST-aware structural code search and rewrite via ast-grep.
Flow Analysis (.NET)Agents & Orchestration65
Analyze VMR codeflow health using maestro MCP tools and GitHub MCP tools. USE FOR: investigating stale codeflow PRs, checking if fixes have flowed through the VMR pipeline, debugging dependency update issues, checking overall flow status for a repo, diagnosing why backflow PRs are missing or blocked, subscription health, build freshness, URLs containing dotnet-maestro or "Source code updates from dotnet/dotnet". DO NOT USE FOR: CI build failures (use ci-analysis skill), code review (use code-review skill), general PR investigation without codeflow context, tracing whether a specific commit/PR has reached another repo (use flow-tracing skill). INVOKES: maestro and GitHub MCP tools, flow-health.cs script.
Hf Cloud Aws Context Discovery (Hugging Face)Agents & Orchestration65Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.
Segment Anything Model (Nous Research)Données & Recherche65SAM: zero-shot image segmentation via points, boxes, masks.
Azure Cost (Microsoft)Infra, Ops & Workflow64Azure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: \"Azure costs\", \"Azure bill\", \"cost breakdown\", \"how much am I spending\", \"forecast spending\", \"optimize costs\", \"reduce spending\", \"orphaned resources\", \"rightsize VMs\", \"cost spike\", \"reduce storage costs\", \"AKS cost\". DO NOT USE FOR: deploying resources, provisioning, diagnostics, or security audits.
Browserbase Safe BrowserTests64
Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.
Code Review (Alibaba)Agents & Orchestration64
在进行 Code Review 时，使用这个技能对 LoongCollector 变更进行安全导向、架构一致性优先的深度代码评审。
Contrib PR (Prisma) — ContribBackend & API64
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
Contrib PR (Prisma) — Contrib 2Frontend & UI64
Open a high-quality external contributor PR against prisma-next. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
Data Scraper AgentDonnées & Recherche64
Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
Fal IA MediaAgents & Orchestration64Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
Global Greenwashing Claim Auditor (Microsoft)Produit & Go-to-market64Use this skill whenever the user asks to audit, scan, review, classify, or de-risk environmental, sustainability, climate, circularity, recycling, emissions, or green marketing claims in pasted conversational content, CSV files, XLSX workbooks, DOCX documents, PPTX presentations, or website URLs. Report universal vocabulary risks separately from Canadian (CA), European Union (EU), and United Kingdom (UK) legal and guidance findings.
Hyperliquid (Nous Research)Données & Recherche64Hyperliquid market data, account history, trade review.