В каталоге 183 730 навыков в 14 категориях.
Manage hierarchical task lists using the rune CLI tool. Create, update, and organize tasks with phases, subtasks, and st...
Expert in Elder Futhark runes, Norse mythology, runic divination, and historical runic practices
润滑：把中文消息写成圆融、熟络、有推动力的协调口吻，同时去掉 AI 味和空话。适用于用户要求“润滑一下”、学习业务协调式表达，或改写群聊、进展同步、催办、合作与婉拒消息时。保留原意、事实和明确边界，直接输出中文成稿。
This skill guides creation of UI components and pages that follow runi's design system.
The evidence rules for every runlab statement — what a given sample size supports, when a finding counts as established,...
Predict a race time from the athlete's own data, with an explicit evidence level, a range rather than a single number, a...
Check whether the running data is arriving cleanly — which channels the watch and the source actually deliver, sample co...
Render the full training overview — where the athlete stands, what the data supports, what it does not, and what to do n...
Analyse one run — pacing, efficiency decay, decoupling, mechanics, and how it compares with the athlete's own history at...
Set up runlab for this athlete — choose a data source, prove it can actually deliver, create the data root, and run the...
Short read-only situation report from the local running database — last run, data quality, open patterns, due tests, anc...
Fetch new runs into the local cache and report what actually arrived — counts, coverage per channel, gaps and duplicates...
Imported skill runloop from langchain
Runme.dev形式の実行可能マークダウン作成・編集用規約。使用タイミング:(1) マークダウンファイルに実行可能なコードブロックを追加（verify.md, README.mdなど）(2) Runme.devセル設定の追加・編集（nam...
Run, test, and profile Godot scenes using AgentBridge — use when you need to execute, observe, or benchmark a scene.
Supervise one spec run or one Batch from an interactive session: launch or rejoin it, explain each of its events to the...
Use when an open pull request must be driven to merge-ready - conflicts, unanswered review threads, or failing CI are ou...
Creates or hardens an unattended runner, the wrapper, pre-flight gate, permission profile, ledger, watchdog, and caps ar...
Use when symfony runner selection
Bootstrap Laravel projects by detecting Sail or host tooling, verifying dependencies and services, and choosing consiste...
Self-hosted GitHub Actions runner management via Podman Quadlet. Supports multi-instance pools with ephemeral storage, a...
Use when launching the Electron app for manual verification or UI smoke testing. This project uses the Unix launcher scr...
Run the linter against a file and show the real diagnostics
Executes language-agnostic test suites to validate behavioral correctness, enforce regression safety, and automatically...
How to run Node.js package binaries with npm/pnpm/npx. Use when installing global packages, running CLI tools, or config...
Turn an incident into organisational learning instead of individual punishment. Run blameless
Runs real-user QA, manual test plans, UX bug hunts, build sign-off, bug filing, and bug triage for web or iOS/iPadOS app...
Execute chaos engineering experiments to test system resilience.Use when performing specialized testing.Trigger with phr...
Segment data with clustering algorithms such as K-means, DBSCAN, or hierarchical clustering. Use for unsupervised groupi...
Analyze datasets by running clustering algorithms (K-means, DBSCAN, hierarchical) to identify data groups. Use when requ...
Weekly running coaching sessions that analyze training logs against the training plan, with primary focus on running and...
Reference catalog for all running coach AI skills, shared TypeScript contracts, safety guardrails, and telemetry convent...
Use this skill when working with CodeRabbit, such as running CodeRabbit reviews, generating and processing automated Cod...
Orchestrate an end-to-end data analysis or machine learning project from decision framing through reproducible handoff....
Run a high-quality decision process and produce a Decision Process Pack (decision brief/pre-read, options + criteria mat...
Help users run effective decision-making processes. Use when someone is facing a high-stakes decision, dealing with anal...
Run high-signal design reviews (design critique / design crit / design feedback) by producing a Design Review Pack: revi...
Help users run effective design reviews and critiques. Use when someone is giving design feedback, establishing design r...
Operates the Drive Automation Chain 1+2 system — a multi-agent Google Drive classification and routing pipeline backed b...
Execute end-to-end tests covering full user workflows across frontend and backend.Use when performing specialized testin...
Run effective 1:1s and skip-levels as a manager/leader and produce a 1:1 Operating System Pack (cadence plan, agendas, s...
Help users run effective one-on-one meetings. Use when someone is a new manager setting up 1:1s, struggling to make 1:1s...
Run effective meetings by producing a Meeting Pack (meeting brief, pre-read, agenda, facilitation script, notes + decisi...
Help users run more effective meetings. Use when someone is dealing with meeting overload, wants to improve meeting cult...
Breakdown の examples/ を実行し、ユーザー視点での動作確認を行う。
Cut GitHub Actions minutes and wall-clock time without losing coverage — the OS billing multiplier (macOS 10x / Windows...
Use when an agent needs to self-bootstrap agent-relay and autonomously manage a team of workers - covers infrastructure...
Execute integration tests validating component interactions and system integration.Use when performing specialized testi...
Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my...
Create and execute load tests for performance validation using k6, JMeter, and Artillery. Use when validating applicatio...
Persistent schema-driven running log with three-component architecture - quick-capture ideas, AI auto-detection, and bac...
Execute mutation testing to evaluate test suite effectiveness.Use when performing specialized testing.Trigger with phras...
Help users plan and run effective team offsites. Use when someone is organizing a team retreat, planning a strategy offs...
Plan and run a high-signal team offsite/retreat and produce an Offsite Pack (offsite brief, agenda + run-of-show, prewor...
Run OpenMed models fully on-device with the MLX (Apple Silicon), CoreML (iOS/macOS), or ONNX/WebGPU (cross-platform/brow...
Use this skill when working with OpenStudio 3.10 .osm models to adjust HVAC systems, equipment, thermal zones, schedules...
Execute load testing, stress testing, and performance benchmarking.Use when performing specialized testing.Trigger with...
Performs placebo-in-time sensitivity analysis to validate causal claims. Use when checking model robustness, verifying l...
Runs Python scripts and manages projects using uv. Use when asked to run a python script, execute python code, run pytes...
Runs and reads AQVEN series without making the owner the monitor: probes and a dev smoke first, fixed size, a background...
Execute fast smoke tests validating critical functionality after deployment.Use when performing specialized testing.Trig...
Use when the user asks for subagent review, fresh-context review, multiple review rounds or passes, several reviewer age...
Executes test suites with proper error reporting and failure analysis. Use when verifying implementations, debugging tes...
Use when asked to run tests in the dd-sdk-ios project — whether a full module suite, a specific test class, or a single...
Run tests to ensure code functionality and correctness.
Orders AQVEN work from request to reliable flow: measurable contract, simplest flow, cases, traces, hypotheses, Explore...
Execute self-correcting validation workflow. Use when validation fails, tests fail, or build breaks.
Sets up and maintains visual regression testing: what to snapshot, baseline strategy, masking dynamic regions, threshold...
Research, verify, and draft runner-facing WeChat public-account articles about road running, marathons, trail running, t...
Translate Unix commands to Windows equivalents when working on Windows systems. Use when paths start with drive letters...
Launches workflow engine runs in the background, monitors progress via session files, and reports status. Use when runni...
Extract arbitrary, custom entity types from clinical or biomedical text with no fine-tuning using OpenMed's GLiNER / GLi...
Generate supported images, videos, audio, and 3D models via RunningHub API and run RunningHub AI Applications by webappI...
RunPod integration for AI agents via ClawLink — browser login, no API key setup. Connect RunPod through ClawLink's hoste...
Use when running GPU compute on RunPod and deciding between Pods (hourly, always-on) and Serverless (per-second, autosca...
Cloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images, managing GPU...
Provision, diagnose, and clean up paid RunPod compute for robotics workloads.
Deploy GPU workloads to RunPod serverless and pods - vLLM endpoints, A100/H100 setup, scale-to-zero, cost optimization....
Use when adding or changing a "Run on Runpod" launch card for an article, writing or editing runpod/profiles/<id>.yaml,...
Manage Runpod infrastructure — pods, serverless endpoints, jobs, templates, network volumes, container-registry auth, GP...
Provision, manage, and terminate RunPod GPU instances for LLM training. Use when user says "spin up GPU", "create RunPod...
Execute a project from a folder of raw materials. Use when the user drops messages, screenshots, documents, drafts, and...
Search and book flights, hotels, and travel via RunRelay API. Covers 300+ airlines including low-cost carriers (Ryanair,...
Grep/wc replacement for .runs artifacts. Use for: count, extract, Machine Summary, receipt reading, marker counts. Null-...
Update index.json status. Use for: upsert index.json, update status/last_flow/updated_at. Deterministic writes - stable...
This skill should be used when the user asks about "Effect Runtime", "ManagedRuntime", "Effect.Tag", "custom runtime", "...
Evaluates the inference latency and computational runtime of transformer models and individual MLX operations across dif...
Generates ephemeral Playwright tests for web UI and HTTP API projects during review
将用户合法拥有或已获授权的 CUDA 应用中的 Runtime 层迁移到 CANN Runtime，包括 API、类型、错误码、初始化、内存、stream、event、IPC、构建配置和兼容层适配。仅在处理 Runtime 层迁移或可行性分...
Use when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. U...
Call the Mendix M2EE admin API on port 8090 directly — OQL, runtime info, and the rest, with curl examples. Use when que...
Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Func...
Explains how to use Synapse RuntimeContext API. Use when the user asks about "RuntimeContext", "ctx.", "logging", "progr...
Run local system diagnostics and model benchmarks across CPU, memory, GPU, NPU, Docker, and Kubernetes; use when asked t...
通过执行系统命令快速汇总当前宿主机的操作系统版本、内核信息及硬件配置，并以结构化表格形式呈现。
Explains runtime errors and compilation failures with actionable debugging guidance. Use when Python or Java code throws...
Default entry of the debug skill family when runtime observation is needed: static analysis stalled, a fix did not work,...
Runtime HAL for multi-runtime agent orchestration. Detects active AI assistant (Claude Code, Codex, Gemini, Cursor) and...
为 CANN Runtime 的指定接口、函数、分支、缺陷或当前代码变更设计、编写并验证 LLT，支持通过 coverage_threshold 指定覆盖率门槛，未指定时默认 80%。用户要求“写对应的 LLT”“生成对应的 LLT”“补充...
Emit info-level logs to file during task execution, similar to logger.info() calls in code