Catalogue de skills·2424 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
2424 skills sur 2424
Skill
Description
Agents
Copier le skill
Project Flow OpsAgents & Orchestration100Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or GitHub-to-Linear coordination.
Project Knowledge (Alibaba)Agents & Orchestration100
LoongCollector project knowledge: architecture, terminology, codebase map, and coding standards (C++/Go).
Project Management (.NET)Infra, Ops & Workflow100
GitHub issue and project-board management for the dotnet/msbuild repo. Use when asked to file/triage/update issues, post comments, amend issue bodies, move sprints, bulk-update project board fields, or audit items by sprint/status/assignee.
Prompt Scanner (Alibaba)Agents & Orchestration100
使用 agent-sec-cli 扫描 prompt 文本中的注入攻击和越狱尝试，返回结构化 JSON 扫描结果。当用户提到 prompt 安全、prompt 注入检测、越狱检测、提示词攻击检测，或者需要判断一段文本是否包含恶意 prompt 注入时，都应使用此技能。即使用户没有明确说"扫描"，只要涉及评估 prompt 文本的安全性，也应触发此技能。
Psl Ast Layers (Prisma) — ContribAgents & Orchestration100
How to use the PSL syntax tree layers (green tree, red tree, strongly-typed AST classes) correctly. Use for any PSL-related work: PSL interpreters (contract-psl), helpers inside the psl-parser package, the language server, formatters, or anything else that consumes `parse()` output from @internal/psl-parser.
Psl Ast Layers (Prisma) — Contrib 2Frontend & UI100
How to use the PSL syntax tree layers (green tree, red tree, strongly-typed AST classes) correctly. Use for any PSL-related work: PSL interpreters (contract-psl), helpers inside the psl-parser package, the language server, formatters, or anything else that consumes `parse()` output from @prisma-next/psl-parser.
Pt2 Bug Basher (PyTorch)Données & Recherche100
Debug PyTorch 2 compiler stack failures including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches. Use when encountering torch.compile errors, BackendCompilerFailed exceptions, recompilation issues, Triton kernel failures, FX graph problems, or when the user mentions debugging PT2, Dynamo, Inductor, or compiled model issues.
Publish Npm Version (Prisma) — ContribBackend & API100
Cuts the next minor release of Prisma Composer: bumps the root package.json version, propagates it to every workspace package in lockstep, and opens a PR titled "chore(release): v<next-version>". When a maintainer merges the PR, the `Publish to npm` workflow runs automatically and ships the new version to npm under dist-tag `latest`, plus a matching GitHub Release with auto-generated notes. Use when a maintainer asks to "cut the next minor", "bump to the next version", "open a release PR", or "prepare a publish PR".
Publish Npm Version (Prisma) — Contrib 2Backend & API100
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to <next-version>". When the maintainer merges the PR, the `Publish to npm` workflow runs automatically and ships the new version to npm under the dist-tag its shape implies (`latest`; RC releases get a pre-release GitHub Release), plus a matching GitHub Release. Use when a maintainer asks to "cut the next RC", "cut the next release", "bump to the next version", "open a release PR", or "prepare a publish PR".
Publish Npm Version (Prisma) — Contrib 3Backend & API100
Cuts the next release of the unified Prisma CLI: bumps the root package.json version (on the Prisma 8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every lockstep workspace package, and opens a PR titled "chore(release): bump to <next-version>". When the maintainer merges the PR, the `Publish to npm` workflow ships @prisma/cli-engine and @prisma/cli under dist-tag `latest` (RC versions get a pre-release GitHub Release). Use when a maintainer asks to "cut the next RC", "cut the next release", "bump to the next version", "open a release PR", or "prepare a publish PR".
Publish Npm Version (Prisma) — Contrib 4Frontend & UI100
Cuts the next minor release of Prisma Next: bumps the root package.json version, propagates it to every workspace package, and opens a PR titled "chore(release): bump to <next-version>". When the maintainer merges the PR, the `Publish to npm` workflow runs automatically and ships the new version to npm under dist-tag `latest`, plus a matching GitHub Release. Use when a maintainer asks to "cut the next minor", "bump to the next version", "open a release PR", or "prepare a publish PR".
Pyrefly Type Coverage (PyTorch)Données & Recherche100
Migrate a file to use stricter Pyrefly type checking with annotations required for all functions, classes, and attributes.
Python Appservice Deploy (Microsoft)Infra, Ops & Workflow100Deploy Python (Flask/Django/FastAPI) code to Azure App Service Linux. WHEN: \"Flask App Service\", \"Django App Service\", \"FastAPI App Service\", \"deploy Python to App Service\". DO NOT USE FOR: Container Apps, Functions, non-Python, Terraform/Bicep/IaC, full infra — use azure-prepare.
Python PatternsLangages & Runtimes100Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications. Use when writing or reviewing Python code and idiomatic structure, typing, or PEP 8 is in question.
Python TestingTests100Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements. Use when writing pytest tests — fixtures, mocks, parametrization, or coverage.
Pytorch Fsdp (Nous Research)Données & Recherche100Fully sharded data-parallel training for large models.
Pytorch Lightning (Nous Research)Données & Recherche100Clean training loops with built-in distributed support.
Pytorch PatternsDonnées & Recherche100PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Use when writing or reviewing PyTorch training loops, model architectures, or data loading, or when a run will not reproduce.
Pytorch Runners Routing (PyTorch)Données & Recherche100
How PyTorch CI jobs in .github/workflows/ resolve to a specific runner, AND which infrastructure that runner lives on: the two infras (legacy ALI Lambda-autoscaled EC2 vs current OSDC ARC-on-EKS) and the dot-vs-dash prefix split (linux./lf./c. = old EC2; mt-/lf-/c-mt- = OSDC ARC). Covers the runner determinator (fleet prefixes mt- default / lf- / c-mt- plus the separate amd-do-), the test-infra #5132 experiment config (lf, amd-do), the now-unconditional EC2->ARC label translation via .github/arc.yaml and map_ec2_to_arc.py (the meta_only_runners H100/B200 override and the onnx exclusion), build-vs-test runner decoupling, and the _runner-determinator.yml / _linux-build.yml / _linux-test.yml flow. Old-infra ownership spans test-infra/terraform-aws-github-runner, test-infra scale-config.yml / lf-scale-config.yml, and pytorch-gha-infra/runners; OSDC ownership lives in the osdc repo (clusters.yaml + modules/arc-runners*). Applies to ~/meta/pytorch. LOAD THIS SKILL for ANY question about PyTorch CI runners, runner labels, test matrices, runs-on values, runner prefixes (mt-, lf-, c-mt-, amd-do-, or legacy linux./lf./c.), WHICH infra a label runs on ("does lf.linux.2xlarge run on ARC or EC2?", "mt- vs lf- vs lf.?", "old ALI vs OSDC runners", "where is this runner defined?"), experiments (lf / amd-do), the determinator, ARC fleet routing, H100/B200/ A100 placement, or how a job gets assigned to a runner pool.
Qualcomm (PyTorch)Données & Recherche100
Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend. Use when working on backends/qualcomm/, building QNN (use backends/qualcomm/scripts/build.sh), adding new ops or passes, running QNN delegate tests, or exporting models for Qualcomm HTP/GPU targets. Also exposes a Buck-vs-CMake parity workflow — invoke as `/qualcomm buck-fix`, `/qualcomm buck-cmake fix`, `/qualcomm buck-parity`, or any user request to fix `test-qnn-buck-build-linux` CI failures or check buck/cmake drift in backends/qualcomm/. Also covers QNN intermediate-output / per-layer accuracy debugging — trigger on phrases like "QNN accuracy issue", "QNN output doesn't match CPU", "debug per-layer for QNN", "find which QNN layer is wrong".
Qualification Report (Microsoft)Agents & Orchestration100Summarize the synthetic qualified pipeline and recommended review actions without conversion claims.
Quality Dashboard (Microsoft)Agents & Orchestration100Reproduce the deterministic Care Gap Agent — quality dashboard workflow from packaged synthetic evidence.
Quality NonconformanceAgents & Orchestration100Quality control and non-conformance management for regulated manufacturing (FDA 21 CFR 820, IATF 16949, AS9100): NCR lifecycle and disposition, 5-Why/Ishikawa/fault-tree/8D root cause analysis, CAPA systems, SPC interpretation, AQL sampling, and supplier quality audits. Use when investigating non-conformances, performing root cause analysis, managing CAPAs, interpreting SPC data, or handling supplier quality issues.
Quarkus PatternsBackend & API100Quarkus 3.x LTS architecture patterns with Camel for messaging, RESTful API design, CDI services, data access with Panache, and async processing. Use for Java Quarkus backend work with event-driven architectures. Use when building or reviewing a Quarkus service, especially with Camel messaging or Panache data access.
Quarkus SecurityAuth & Sécurité100Quarkus security implementation patterns: JWT and OIDC authentication, @RolesAllowed RBAC and SecurityIdentity checks, Bean Validation and custom validators, parameterized Panache queries, BCrypt password hashing, CORS and security headers, rate limiting, audit logging, Vault or environment-variable secrets, and dependency CVE scanning. Use when adding authentication or authorization, validating input, managing secrets, or hardening a Quarkus application.
QueryDonnées & Recherche100
Run SQL queries against the attached DuckDB database or ad-hoc against files. Accepts raw SQL or natural language questions. Uses DuckDB Friendly SQL idioms.
Query Bridge Agent (Alibaba)Agents & Orchestration100
Quickly extract a typed GPU-Wiki query intent from prose. Never inspect or query a knowledge store.
Query Pipeline (.NET)Agents & Orchestration100
Implementation details for EF Core LINQ query translation, SQL generation, and bulk operations (ExecuteUpdate/ExecuteDelete). Use when changing expression visitors, SqlExpressions, QuerySqlGenerator, ShaperProcessingExpressionVisitor, UpdateExpression, DeleteExpression, or related classes.
R2 Outage Toggle (PyTorch)Tests100
Disable or re-enable Cloudflare R2 (download-r2.pytorch.org) usage in manage_v2.py during R2 outages. Can toggle R2 off/on for nightly builds, prod/stable builds, or both. The affected packages are PT_FOUNDATION_PACKAGES (torch, torchvision, torchaudio, fbgemm_gpu, fbgemm_gpu_genai, triton, pytorch_triton, pytorch_triton_rocm, pytorch_triton_xpu).
Ralphinho Rfc PipelineDocs & Écriture100Split an RFC into a multi-agent execution DAG — decompose into work units with dependencies and acceptance tests, run research, plan, implement, test, and review per unit, then merge through a queue with re-based branches and final system verification. Use when a feature is too large for a single agent pass, orchestrating RFC-driven multi-agent execution, or managing merge queues across agent-built units.
React DB (TanStack)Frontend & UI100
React bindings for TanStack DB. Prefer useLiveQuery({ query }) with derived structured query identity. Provide queryKey only for opaque functional query variants or very hot render paths. Dependency arrays are legacy and warn before 1.0 removal. useLiveSuspenseQuery for React Suspense with Error Boundaries (data always defined). useLiveInfiniteQuery for cursor-based pagination (pageSize, fetchNextPage, hasNextPage, isFetchingNextPage). usePacedMutations for debounced React state updates. Return shape: data, state, collection, status, isLoading, isReady, isError. Import from @tanstack/react-db (re-exports all of @tanstack/db).
React Hook Form (Supabase)Frontend & UI100
Correct React Hook Form usage anywhere in the monorepo — data flow, subscriptions,
React Microfrontend Patterns (Microsoft)Frontend & UI100Use when building a React frontend that dynamically loads independent bundles sharing a single React instance via import maps, needs frecency-based autocomplete, dynamic schema-driven forms, or Zustand state with localStorage.
React Native PatternsFrontend & UI100React Native and Expo app patterns — Expo Router navigation, state separation (server/client/route/form), TanStack Query data fetching with Zod, performant lists, NativeWind/StyleSheet styling, native APIs, and secure storage. Use when building or editing React Native / Expo screens, components, navigation, or data layers.
React Rendering (TanStack)Frontend & UI100
Render Markdown source or a MarkdownDocument with @tanstack/markdown/react using Markdown, renderMarkdownReact, component replacements, and React static SSR. Load for React article components, emitted-tag mappings, pre-parsed documents, custom elements, or renderer parity.
Read Eval Logs (Hugging Face)Langages & Runtimes100View and analyse Inspect evaluation log files using the Python API. Trigger whenever you need to look at a .eval file yourself without using pre-written scripts.
Realsig Codegen (.NET)Infra, Ops & Workflow100
Debug and fix --realsig+ (RealInternalSignature) codegen bugs in IlxGen — MethodAccessException / FieldAccessException / TypeAccessException at runtime, IL `private` vs `assembly` visibility, closure and TLR-lift placement (cloc / NestedTypeRefForCompLoc / effectiveCloc / moduleCloc). Use when a program compiles cleanly but crashes only under --realsig+, when IL accessibility differs between realsig modes, or when reasoning about where compiler-synthesized closures/state-machines/quotation helpers are nested.
Rebuild Restart Storybook (Storybook)Agents & Orchestration100
Rebuild and restart the internal Storybook UI after changes to internal Storybook code (core, addons, frameworks, renderers, libs, etc.), then optionally display a UI review. Use after editing any package in the Storybook monorepo's code/ directory, or when the user asks to rebuild and/or restart Storybook.
Recipe Backup Sheet As CsvAgents & Orchestration100
Export a Google Sheets spreadsheet as a CSV file for local backup or processing.