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. 79 437 files from 1 744 authors, of which 61 785 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.
> Summarize a sprint's worth of Claude Code activity — sessions grouped by project (cwd), per-model cost breakdown, token efficiency (cache hit rate, compaction baselines), subagent effectiveness from workflow API, velocity metrics (turn_count, turn_duration_ms), and tool diversity across the sprint.
> Discover when you are most active and most productive with Claude Code by bucketing sessions and events into hour-of-day and day-of-week bins from their timestamps, then flagging peak versus low-output windows. Uses the session list, per-session events, and analytics daily trends. Use when planning a schedule or deciding when to do deep work versus lighter tasks.
> Compile a weekly productivity report using Agent Monitor data — daily_sessions and daily_events trends, per-session costs from pricing engine, token volumes (input/output/cache_read/cache_write + baselines), tool usage top 20, session completion rates by status, and workflow intelligence metrics.
> Analyze workflow patterns using the Agent Monitor's workflow intelligence API — orchestration DAGs, tool flow transitions, subagent effectiveness, model delegation patterns, error propagation by depth, concurrency lanes, compaction impact, and agent co-occurrence. Produces prioritized optimization recommendations with quantified impact.
> Produce a detailed report on APIError events from Agent Monitor data — counts over time, which sessions and models are affected, and the likely root cause (rate limits, overload/529, or context-window pressure) inferred from each event's summary and data payload. Use when API errors spike or when you need to explain why requests are failing.
> Scan recent Claude Code activity for errors and failure signals across all sessions using Agent Monitor data — APIError events and PreToolUse→PostToolUse gaps (tools that started but never completed) — then group failures by tool and model and rank them by frequency. Use when checking for errors or asking "what's failing right now".
> Audit hook delivery health from Agent Monitor data — balance PreToolUse vs PostToolUse (a gap means tools that started but never reported back), detect missing Stop/SubagentStop terminators (sessions/subagents that never closed), and check for stale ingestion (no recent events). Use when hooks look unreliable or events seem to be dropping.
> Compare this period's reliability against the prior period using Agent Monitor data — error rate (APIError/total) and tool-failure rate (PreToolUse→PostToolUse gap) — flag any regression where reliability got worse, and optionally wire a persistent alert rule so the dashboard catches the next regression automatically. Use when checking whether reliability degraded.
> Define and check simple service-level objectives for Claude Code from Agent Monitor data — session completion rate, tool success rate (PostToolUse/PreToolUse), and error rate (APIError/total) — then compare each to its target and report the error budget remaining. Use when reporting reliability or when someone asks "are we meeting our SLOs?".
> Roll up Claude Code sessions by working directory (project) from Agent Monitor data — session count, total cost, total tokens, and last-active timestamp per cwd — so per-project activity can be compared at a glance. Use when summarizing where effort and spend went across projects.
> Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation. Use when tidying the monitoring database.
> Find Claude Code sessions tracked by the Agent Monitor by project (cwd), model, status, or date, then rank the matches by cost or recency. Pulls the session list and the distinct cwd / facet values so filters use real values rather than guesses. Use when locating a session — "find my EstateWise sessions", "which Opus runs errored this week", "most expensive sessions in /repo".
> Render an ordered timeline of one Claude Code session's events (every event type) with per-event durations and tool names, reconstructed from Agent Monitor data. Pairs PreToolUse with PostToolUse to compute tool durations and surfaces gaps, errors, and compaction points. Use when reconstructing what happened in a session step by step.
> Walk a Claude Code session transcript turn-by-turn from Agent Monitor data, summarizing each user, assistant, and tool message in order so a long conversation can be reviewed quickly. Anchors the recap to the session header (model, cost, turn_count). Use when reviewing what was actually said and done in a conversation.
> Report concurrency and parallelism for a session — how many agents ran in parallel, concurrency-lane utilization, peak parallel width, and serialization bottlenecks (sequential chains that could have run as parallel lanes) — using the Agent Monitor workflow intelligence API. Use when checking whether a multi-agent session used parallelism efficiently.
> Render the multi-agent orchestration DAG for a session — parent→child subagent edges, tree depth, and fan-out — from the Agent Monitor workflow intelligence API. Cross-checks the orchestration dataset against the raw agent records and session detail. Use when visualizing how a session's agent structure was organized.
> Audit model delegation and subagent effectiveness for a session — which models handled which subagent types, per-type success rates and average durations, and wasted delegations (heavy models on trivial work or types that consistently fail) — using the Agent Monitor workflow intelligence API. Use when reviewing how a session delegated work across models and subagents.
> Trace error propagation through a multi-agent session by agent depth — where failures originated, the depth at which they appeared, and how they cascaded up to parent agents — using the Agent Monitor workflow intelligence API and the session event stream. Use when a multi-agent run failed and you need to find the origin and blast radius of the failure.
> Summarize Workflow-tool fleet runs from the Agent Monitor — these fleets emit no hooks and are ingested from on-disk run journals. List recent runs with status and agents-per-run, then drill into a single run's per-agent detail. Reconciles against the live run-state endpoints. Use when reviewing Workflow() fleets rather than hook-instrumented interactive sessions.
Audit a component or page for accessibility issues and fix them
Audit screens for UX issues using Nielsen's heuristics and modern mobile UX best practices
Build a screen with StyleSeed's composed design method — choose or compile an output grammar, apply a brand recipe plus domain/page/profile/lock constraints, then run the code and pixel gates before presenting.
Generate a new UI component following the StyleSeed design conventions
Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone
Turn ONE design axis up or down as a coordinated, deterministic transform — "denser", "sharper corners", "more muted", "bolder", "flatter", "livelier". Not a vibe the model reinterprets each time; a defined ramp that moves many tokens together, respects the guardrails (8px grid, a11y floors, single accent, nested-radius), updates the lock, and re-runs the gate. Use this when a human saying "more X" would otherwise get an inconsistent one-off.
Add appropriate user feedback states (loading, success, error, empty) to a component or page
Design user flows and navigation structure following proven UX patterns
Quick automated lint — detects common design system violations in seconds
Apply a named StyleSeed motion to a component — either one of the 5 personality seeds (Spring/Silk/Snap/Float/Pulse × entrance/exit/hover/press/layout) or a distinctive keyword move from the motion library (toggle-flip, toggle-curtain, reveal-blur, pop-in, shimmer, …). Translates vibe words into framer-motion code from one source of truth.
Scaffold a new product page or screen from the compiled StyleSeed output grammar, surface adapter, brand recipe, and project lock.
Generate a composed UI pattern from the active StyleSeed grammar and brand recipe using existing primitives.
Compile screenshots, URLs, Figma exports, or an existing UI into a project-local StyleSeed output grammar with evidence, tokens, confidence, anti-patterns, and a validation screen. Use when the user supplies a design reference that StyleSeed does not already model.
Compile a small, deterministic StyleSeed rule bundle for one agent, output grammar, surface adapter, domain, page type, brand recipe, and optional profile. Use before setup or build, when STYLESEED.md changes, when updating StyleSeed, or whenever an agent would otherwise load the full rule handbook.
Apply one optional StyleSeed aesthetic profile without changing the selected output grammar, product job, or core design judgment.
Review UI code for design system compliance, accessibility, and best practices
Score a visual artifact's implementation quality 0-100 against its composed StyleSeed rule set — category breakdown, evidence, and prioritized fixes.
Configure StyleSeed by selecting the output grammar, domain, page type, brand recipe, optional aesthetic profile, and bounded brand tokens before scaffolding a first screen.
View, add, or modify design tokens in the StyleSeed design system
Update StyleSeed engine in your project — analyzes what's outdated and updates safely
The VISUAL gate — render a UI or visual artifact through its surface adapter, inspect the actual pixels, then fix and re-render until it passes the composed StyleSeed rule set.
Reviews UI/frontend code and tells you exactly why it "looks AI-generated" — then how to fix it. Use it when a React/Tailwind/HTML interface looks off, generic, or unfinished, when you want a design score before shipping, or when asked to make UI look more professional, polished, or "designed, not generated." Self-contained; based on the open-source StyleSeed design engine.
> Applies motion design principles to create emotionally-driven, technically sound animations and transitions. Provides timing, easing, choreography, and Disney animation principles adapted for UI. Use when creating animations, transitions, micro-interactions, loading states, page transitions, scroll-triggered effects, or any motion work. Works with CSS, Framer Motion, GSAP, Lottie, Spring, or any animation system.
> Compute aerospace environment properties including atmosphere (ISA, COESA, NRLMSISE-00, non-standard, CIRA), gravity (spherical harmonic, WGS84, zonal, centrifugal), horizontal wind (HWM), magnetic field (WMM, IGRF), geoid height, geocentric radius, space weather data, planetary ephemeris, Earth orientation (polar motion, nutation, delta-UT1, CIP). Use when computing atmospheric density, temperature, pressure, gravity vectors, wind profiles, magnetic field components, geoid undulation, solar flux indices, planet positions, or Earth orientation parameters for aerospace vehicle analysis, spacecraft environment modeling, or navigation corrections.
> Perform aerospace unit conversions, time conversions, coordinate frame transformations, and rotation representations using Aerospace Toolbox. Use when converting units (length, velocity, angle, acceleration, angular velocity, force, mass, pressure, temperature, density), computing Julian dates or decimal years, transforming between coordinate frames (ECEF, ECI, LLA, flat Earth, geodetic/geocentric, NED, body, wind, stability), or working with rotation representations (Euler angles, DCM, quaternion, Rodrigues vector). Also use when the user asks about aerospace coordinate systems, reference frames, or rotation conventions.
> Use this skill to classify tabular data end-to-end in MATLAB — load a dataset, prepare and clean it, select promising classifiers, train them, and compare accuracies with cross-validation, holdout, or hyperparameter optimization plus statistical tests. classifier accuracy, run cross-validation or a holdout evaluation, or find the best model with statistical uncertainty. regression model, is training a specific neural network architecture (use matlab-train-network), or wants cost-sensitive learning or an arbitrary class-prior vector (this skill only supports the built-in uniform-prior toggle for imbalanced data).
> Create an experiment for the MATLAB Experiment Manager app from user code, script, or problem description. or hyperparameters, asks to compare configurations, or describes a problem suitable for experimentation. or already has a working experiment set up.
> Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, models rebuilt as dlnetwork for lean hardware, (2) direct C/C++ code generation from PyTorch and LiteRT models. Both patterns support all targets (Cortex-M/A/R, x86, GPU). neural networks; compress AI models for MCU; integrate AI in Simulink for system-level simulation; import PyTorch/ONNX/TensorFlow models for embedded deployment; optimize AI for resource-constrained hardware; or use loadPyTorchExportedProgram, loadLiteRTModel, importNetworkFromPyTorch, importNetworkFromONNX, importNetworkFromTensorFlow, importNetworkFromKeras, dlquantizer, exportNetworkToSimulink, or Embedded Coder with AI models.
> Import PyTorch, ONNX, or Keras 3 / TensorFlow 2.16+ deep learning models into MATLAB as dlnetwork objects. Use when importing .pt2 exported programs, traced .pt files, .onnx models, or Keras 3 models via matlabsaver. Covers importNetworkFromPyTorch, importNetworkFromONNX, importNetworkFromKeras, importNetworkFromTensorFlow, torch.export.export, PyTorchInputSizes, InputDataFormats, matlabsaver, tf_keras downgrade, numeric validation against PyTorch or ONNX Runtime, and placeholder/custom layer implementation. Applies when user mentions any of these functions, file formats, or encounters import errors, unsupported operator warnings, 0 learnables, or uninitialized networks.
> Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.
Use when the user wants to train, compare, or export machine learning models using Classification Learner or Regression Learner — including opening the app, loading data, training models, evaluating metrics, comparing results, visualizing plots, testing on held-out data, exploring model interpretability, and exporting trained models. Programmatic access to Classification Learner and Regression Learner apps via AppController.
> Build Simulink models that co-simulate with Eclipse SUMO traffic simulator. Use when creating SUMO-Simulink co-simulation, traffic simulation, TraCI connection, vehicle-in-the-loop testing, or ADAS scenario validation with SUMO. Covers Server/Client setup, Reader/Writer/Actor block configuration, random traffic generation, ego vehicle control, and SUMO file creation. Also use when the user mentions SumoInterfaceLibrary, .sumocfg files, or wants to connect Simulink to an external traffic simulator.
Import recorded driving sensor data (GPS, camera, lidar, actor tracks, lanes) into scenariobuilder.* objects (GPSData, CameraData, LidarData, ActorTrackData, Trajectory, laneData) and run preprocessing — synchronize, offset correction, crop, normalizeTimestamps, convertTimestamps. Also: compute actor tracks from lidar when no annotations exist, attach camera/lidar mounting + intrinsics, export to MAT/workspace/timetable/script. Use for raw driving dataset files (KITTI, nuScenes, Waymo, Pandaset, ROS/ROS2 bags, .mat, .csv, .mp4) or driving/vehicle/sensor logs that need wrapping. drivingLogAnalyzer (DLA) is OPT-IN ONLY — invoke only on explicit user request ('DLA', 'open in DLA', 'inspect/explore/analyze the recording') or reported sensor problem (sync drift, timestamp mismatch, overlay misalignment). NEVER auto-launch DLA after wrapping (Rule 0). For 'build scenario / export to RoadRunner / drivingScenario / OpenSCENARIO / Unreal / simulate', hand off to matlab-scenario-builder.
> Generate Euro NCAP test scenarios and variants using the ADT Euro NCAP support package. Use when creating NCAP seed scenarios, generating variants, translating between drivingScenario and RoadRunner, plotting scenario descriptors, computing NCAP scores, or exporting reports. ScenarioDescriptor, ScenarioDescriptorPlot, ncapScore, ncapReport, exportReport, configureVUT, assessmentTable, Euro NCAP, CCRs, CCRm, CCRb, CCFtap, CCCscp, CPNA, CPFA, CBNA, variant generation.
Generate driving scenes, scenarios, road surfaces, and 3D content from scenariobuilder.* sensor data (GPS, camera, lidar, actor tracks) using Scenario Builder for Automated Driving Toolbox. BUILD, EXPORT, or AUGMENT a virtual scenario/scene/map: ego or actor trajectories, trajectory smoothing, OpenCRG road-surface extraction, 3D asset generation, static-object placement, point-cloud georeferencing + elevation, lane-based ego localization, sensor-fusion tracking, scenario-event extraction (cut-ins, hard brakes, near-misses, ADAS disengagements), or export to RoadRunner, drivingScenario, OpenDRIVE, OpenCRG, OpenSCENARIO, or Unreal Engine. Also: log-to-scenario, scenario harvesting, accident/near-miss reconstruction, SOTIF (ISO 21448) and ISO 26262 scenario coverage, USGS-aerial-lidar augmentation, traffic-sign placement, vision-based vehicle classification for actor assets. NOT for raw-data import or multi-sensor sync/crop/offset/timestamp normalization — route those to matlab-driving-data-importer.
> RoadRunner asset path lookup tables for map format conversions in MATLAB. Maps lane markings, signs, signals, barriers, objects, and lane types to RoadRunner asset paths. Use when converting map formats to RRHD, resolving asset paths, or assigning visual assets to HD Map objects.
> Build a RoadRunner Scenario programmatically from an OpenSCENARIO 1.x (.xosc) file using the `roadrunner-scenario-authoring` skill. Use when the user wants to recreate a scenario from a .xosc file, interpret an OpenSCENARIO file and build it programmatically, reconstruct a .xosc as a RoadRunner scenario, generate a MATLAB script from a .xosc file, or convert an OpenSCENARIO file to MATLAB code. Do NOT use when the user says "import" a .xosc file — that means they want RoadRunner's built-in importScenario API, not programmatic reconstruction. Handles position translation (LanePosition and RoadPosition to world coordinates), construct mapping, relative references, trajectory/route handling, parameter expressions, catalog references, and phase logic topology.
> Convert Lanelet2 maps (.osm) to RoadRunner HD Map (.rrhd) format using MATLAB. Use when converting Lanelet2 maps into RoadRunner Scene Builder, building driving scenes from open-source map data, or transforming road network definitions for simulation.
Foundation skill for all RoadRunner workflows: MATLAB path setup, connection, project/scene/scenario lifecycle, world settings, handle management, status, and close. Use when connecting to RoadRunner, managing projects/scenes/scenarios, setting world origin, checking status, closing RoadRunner, or when any downstream RoadRunner skill needs initialization.
> Import HD Map or OpenDRIVE files into a RoadRunner scene using MATLAB. Use when loading driving scenes in RoadRunner or RoadRunner Scene Builder, importing RRHD, OpenDRIVE, or other RoadRunner-supported formats for simulation, or verifying Lanelet2-to-RRHD conversion results visually. Requires rrApp handle from roadrunner-core.
> Build RoadRunner HD Map entities in MATLAB — lanes, boundaries, markings, junctions, signs, signals, barriers, parking. Use when creating driving scenes from scratch, authoring road networks for simulation and testing automated driving systems, or assembling RRHD maps from Lanelet2 or other HD map sources.
Claude Skills — questions
Answers built from the skills we actually parsed.