Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Use this skill when the user invokes /review-nvbench to review an NVBench pull request, PR branch, commit range, or diff. Supports context, feedback, and adversarial modes.
> 网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。
Build or edit a manufacture-realistic `.forge.js` model in a project, then validate it with run, render, inspect, and export evidence.
Create a ForgeCAD design brief, HLD, or LLD before coding by walking through use, assembly, interfaces, decisions, and verification.
Grade a ForgeCAD or CAD-as-code model against a requirement, brief, prompt, reference, or acceptance criteria with evidence and a 0-10 score.
Write builder-honest AI image prompts from a concrete ForgeCAD model, build brief, HLD, or LLD without hiding how the artifact is built.
Select, run, and interpret ForgeCAD inspection evidence for collisions, sections, wall thickness, components, masks, depth, normals, surface continuity, and fit.
Manage hosted ForgeCAD project sync from the CLI: init, clone, pull, push, file operations, members, publishing, and shares.
Reconstruct a readable parametric ForgeCAD model from an existing CAD or mesh file such as STL, OBJ, 3MF, STEP, or STP.
Reconstruct a real parametric ForgeCAD object from reference images by using images as evidence, not as a one-view facade.
Verify a ForgeCAD MJCF export in MuJoCo with dynamics, contacts, controls, joint travel, and rendered evidence before calling it simulation-ready.
ForgeCAD model authoring, editing, debugging, and execution guidance for .forge.js, SVG-import, assembly, and CLI workflows. Use when building or modifying ForgeCAD geometry, structuring multi-file projects, validating scripts, or using ForgeCAD export/render tooling.
> Help the user turn their Retentioneering ideas, friction reports, bug capturing and validating the idea, through minimal reproductions and issue drafts, to preparing, testing, and submitting a pull request that follows this repository's conventions. Use when the user says they found a bug, wants a feature, wrote a workaround worth upstreaming, or asks how to contribute, open an issue, or make a PR to retentioneering-tools.
> Analyze event logs, clickstreams, user paths, product funnels, retention, behavioral segments, transition graphs, step matrices, sequence patterns, and customer journeys using Retentioneering. Use when the user provides CSV, Parquet, pandas, or database event data containing user, event, and timestamp columns, or asks why users convert, churn, loop, abandon a flow, or follow particular product paths. Do not use for qualitative journey-mapping workshops or aggregate website traffic without user-level event sequences.
Expert guidance on setting up and maintaining a modern Android application architecture using Clean Architecture and Hilt. Use this when asked about project structure, module setup, or dependency injection.
Guidance on implementing the Data Layer using Repository pattern, Room (Local), and Retrofit (Remote) with offline-first synchronization.
Best practices for implementing Android ViewModels using Kotlin 2.3+ Explicit Backing Fields, StateFlow for UI state, and SharedFlow for one-off events.
Authoritative rules and patterns for production-quality Kotlin Coroutines onto Android. Covers structured concurrency, lifecycle integration, and reactive streams.
Expert guidance on setting up and using Retrofit for type-safe HTTP networking in Android. Covers service definitions, coroutines, OkHttp configuration, and Hilt integration.
Guide and execute the migration of asynchronous code from RxJava to Kotlin Coroutines and Flow. Use this skill when a user asks to convert RxJava (Observables, Singles, Completables, Subjects) to Coroutines (suspend functions, Flows, StateFlows).
Convert Android XML layouts to Jetpack Compose. Use when asked to migrate Views to Compose, convert XML to Composables, or modernize UI from View system to Compose.
Audit and improve Jetpack Compose runtime performance from code review and architecture. Use when asked to diagnose slow rendering, janky scrolling, excessive recompositions, or performance issues in Compose UI.
Production-ready scripts for Android app testing, building, and automation. Provides semantic UI navigation, build automation, log monitoring, and emulator lifecycle management. Optimized for AI agents with minimal token output.
Expert checklist and prompts for auditing and fixing Android accessibility issues, especially in Jetpack Compose.
Expert guidance on using Coil for image loading in Jetpack Compose. Use this when asked about loading images from URLs, handling image states, or optimizing image performance in Compose.
Implement navigation in Jetpack Compose using Navigation 3. Use when asked to build state-driven navigation, manage back stacks, scope ViewModels, implement adaptive layouts, or migrate from Navigation Compose.
Best practices for building UI with Jetpack Compose, focusing on state hoisting, detailed performance optimizations, and theming. Use this when writing or refactoring Composable functions.
Use when you need to run ASO controller CRUD tests or sample tests, verify recordings play back correctly, or re-record after changes.
**WORKFLOW SKILL** — Migrate JSON-based golden file test scenarios (TestGolden) to programmatic Go unit tests in the pipeline package. USE FOR: converting testdata/<GroupName>/*.json scenarios into Go tests that construct types with astmodel and run specific pipeline stages. DO NOT USE FOR: adding new test scenarios from scratch, fixing existing Go unit tests, or code review.
Use when creating polished ASO release notes by automatically determining changes from git history since the last release tag.
Use when creating a new ASO release, including pre-checks, release notes generation, draft GitHub release creation, documentation updates, and ROADMAP changes.
Use when ASO controller CRUD tests or sample tests fail during playback or recording, to diagnose the failure and re-record if needed.
**WORKFLOW SKILL** — Migrate an Azure resource group from legacy to hybrid versioning mode in ASO. USE FOR: moving a group (e.g., appconfiguration, cache, network) from VersionMigrationModeLegacy to VersionMigrationModeHybrid in the code generator, updating samples, renaming CRUD tests, and re-recording sample tests. DO NOT USE FOR: adding new resources (use new-resource.instructions.md), general debugging, or code review.
Create and record scripted browser demo videos with webreel. Generates MP4, GIF, or WebM recordings with cursor animation, keystroke overlays, and sound effects from a JSON config. Use when the user wants to record a demo, create a browser video, edit a webreel config, generate a screen recording, preview a demo, or work with webreel in any way.
Converts a double-precision Simulink system or subsystem to single precision using DataTypeWorkflow.Single (Fixed-Point Designer). The single conversion replaces all user-specified double-precision data types, as well as output data types that compile to double precision, with single-precision data types. Use this skill when converting Simulink systems to single precision, reducing memory usage of a Simulink system, optimizing for embedded targets. Do NOT use for standalone MATLAB .m code single conversion.
Builds and edits Simulink, System Composer, Stateflow, and Simscape models. Use when modifying model structure, parameters, ports, connections, or Stateflow chart internals.
Guide users through creating and managing .satk/block-policy.json for controlling which blocks the agent can use, which are excluded, and which block parameters the agent should not modify. Use when setting up block usage policy for a project.
Guide users through curating the library knowledge index — reviewing block categories, marking common/important blocks, and improving block descriptions via agent inference for better agent block selection.
Generate a standalone bug report that another developer can use to reproduce, investigate, and fix an issue. Use when the user says 'file a bug', 'write a bug report', 'report this issue', or asks to document a defect for handoff.
Generates draft requirements from Simulink models. Use when drafting or updating requirement artifacts from a model. Prefers Requirements Toolbox (.slreqx) when available; falls back to structured YAML.
>- source control configuration, and project lifecycle. Use when creating projects, adding models/dictionaries/requirements to projects, configuring labels for automation, fixing broken model references, or setting up source control for Simulink artifacts.
Register, add, or update existing custom Simulink block libraries and configure block policy and knowledge index. Use when a user wants to register, set up, configure, or add existing .slx library files for agent-assisted model building. Do NOT use when the user wants to create or author a new library from scratch — that requires building-simulink-models.
Runs Simulink models programmatically for data exploration, parameter sweeps, and custom analysis using sim() with SimulationInput/SimulationOutput. Use when calling sim(), parsim, setExternalInput, setModelParameter, setVariable, or accessing logsout — any task producing simulation results for analysis (not pass/fail tests).
Specify algorithms for Model-Based Design: system specs, architecture specs, implementation plans, test plans. Use when creating specifications for controllers, signal processing, diagnostics, estimators, or other algorithms authored in Simulink, Stateflow, System Composer, or MATLAB Function blocks.
Specify plant models for closed-loop simulation: system specs, architecture, build plans, validation plans. Use when creating, updating, or reviewing plant model specifications, planning plant model architecture, or planning plant model validation.
Common steps for building multi-layer system architecture models using System Composer. Use when implementing architecture models or when interacting with interface dictionaries, allocation sets, stereotypes, and requirements for architecture components.
> Synthesize new waveforms from scratch for Simulink inports using createInputDataset. Use ONLY when the user asks to generate, create, or synthesize signals (step, ramp, sine, chirp, pulse, noise) to populate a Dataset for External Inputs or Signal Editor. Covers timeseries and timetable formats with correct data type, interpolation, units, and dimensions. Also covers function-call and trigger inport timing setup. Do NOT use when the user wants to load, import, or read existing data from files (MAT, CSV, spreadsheet) — even if that data will be used as model input. Do NOT use for running simulations or plotting outputs.
> Import data into the Simulation Data Inspector (SDI) from MAT, CSV, or Excel files, from workspace variables, or from a Simulink simulation. Use when the user wants to view a logged file in SDI, load a bench-test log, or verify what a just-completed `Simulink.sdi.createRun` or `sim(model)` produced. Covers the `'file'`, `'vars'`, and `'namevalue'` sources of `createRun`, the auto-populate behavior after `sim()`, and post-import verification. Not for comparing existing runs (use `Simulink.sdi.compareRuns`); not for streaming data live during a running simulation (use `Simulink.sdi.createRunOrAddToStreamedRun` — a separate API); and not for authoring Gherkin or Simulink Test test cases, assertions, or regression tests (use `testing-simulink-models`). Do not activate on test-authoring or verification prompts even when no test-authoring skill is available — say so and stop.
> Author or upgrade Model Advisor checks for Simulink and System Composer models. Use when creating new checks (edit-time, standard batch, config-parameter, auto-fix) or converting legacy StyleOne/StyleTwo/StyleThree checks to modern DetailStyle. Covers DetailStyle callbacks, ResultDetail reporting, sl_customization registration, and edit-time EdittimeCheck classes.
Use this skill when the user asks to check Simulink model compliance against a standard (MISRA, MAB, JMAAB, ISO 26262, ISO 25119, DO-178C, DO-254, IEC 61508, IEC 62304, EN 50128, CERT C/CWE, AUTOSAR), wants to run Model Advisor checks, or needs a compliance report with fix suggestions. For JMAAB/MAB, supplement deterministic checks with agentic review of uncheckable guidelines.
Add, configure, and manage faults on Simulink, Simscape, and System Composer model signals for robustness analysis and safety validation. Use when injecting faults (stuck, noise, gain, offset) onto block inports/outports, enabling fault simulation, or analyzing fault effects. Covers sensor failures, signal corruptions, actuator faults, FMEA validation, and robustness testing. Requires Simulink Fault Analyzer.
Create, populate, and manage safety analysis spreadsheets (FMEA, FHA, HARA, custom) and fault trees (FTA) in Safety Analysis Manager. Use when the user asks to perform FMEA, hazard analysis, fault tree analysis, safety analysis, or work with Safety Analysis Manager documents. Requires Simulink Fault Analyzer.
Use when asked to run Design Error Detection (quick defect scan), find design errors in a Simulink model, perform root cause analysis on DED findings, fix division-by-zero, overflow, dead logic or out-of-bounds defects detected by SLDV, or diagnose why missing coverage cannot be achieved (dead logic blocking coverage objectives). Do NOT use for requirement verification, test generation, Inf/NaN detection, active logic analysis, or coverage measurement.
Tests Simulink models using either ephemeral Gherkin-based tests (model_test) for quick validation or persistent tests (Simulink Test API) authored from requirements or behavioral specs. Requires Simulink Test.
Use when integrating a CuTeDSL/CUTE DSL kernel into cuDNN Frontend as a frontend-only Python API, including APIBase wrappers, lazy cudnn exports, optional cutedsl dependencies, FE OSS documentation, and pytest coverage.
Use when retiring old logic, collapsing duplicate owners, removing fallbacks, or touching schema, persistence, or source-of-truth boundaries while deciding whether to delete old paths, retain compatibility, or stop for confirmation.
Use when defining new features, product behavior, UI/component design, architecture choices, contract changes, or ambiguous medium/high-complexity work before implementation, or when the user asks to grill or pressure-test a plan or design.
Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when the user asks to establish shared project language or project work exposes a resolved, vague, conflicting, renamed, or deprecated domain term that needs active semantic modeling.
Claude Skills — questions
Answers built from the skills we actually parsed.