Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.
Orchestrate worker fleets over OpenClaw issues and PRs: prove root causes, prefer clean refactors over quick patches, land verified repairs, and close items proven fixed or no…
Investigate `pnpm test` memory growth, Vitest worker OOMs, and suspicious RSS increases in OpenClaw using the `scripts/test-parallel.mjs` heap snapshot tooling.
Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.
Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.
Optimize OpenClaw token usage and cost by auditing context injection, trimming workspace files (AGENTS.md/SOUL.md/MEMORY.md and daily memory), enabling prompt caching, heartbeat,…
Connector-agnostic Postgres + pgvector memory ingestion and retrieval with incremental cursor history.
Provision a fresh Hetzner VPS from scratch to run an OpenClaw multi-agent stack with Discord chat as the visible I/O layer.
🚨【高危预警 / IMPORTANT WARNING】这不是工具Skill，而是系统级架构升级！部署前务必备份工作区！This is NOT a standard tool skill, but a system-level architecture upgrade! Backup workspace before deployment! 虾滑…
Delegate coding tasks to OpenCode CLI agent for feature implementation, refactoring, PR review, and long-running autonomous sessions.
Collaborate with OpenCode via ACP protocol for code modifications, refactoring, and feature implementation.
Delegate a coding task to the OpenCode CLI as a background implementer, then review its diff and land it yourself.
Browse and recall OpenCode local memory stored on the user's machine: local sessions, plans, conversations, prompt history, and project context.
Run OpenCode (MiniMax) and Claude code reviews iteratively until both find no issues. Use after making changes and before committing.
Query and interact with Open Collective's GraphQL API v2. Browse collectives, view budgets/transactions/expenses, manage memberships, submit expenses, and explore the open-source…
Use when reading or writing property records and comps — sales, leases, unit rents, listings, parcels, owners, assessments, valuations — in an OpenComps database, via the supabase…
Computer vision for bio-image preprocessing, feature detection, real-time microscopy. Color conversion, morphology, contour/blob detection, template matching, optical flow on…
Implement production-grade computer vision pipelines using OpenCV (C++ and Python) with CUDA acceleration.
Deploy Integration for OpenEvidence. Trigger: "openevidence deploy integration".
Reference Architecture for OpenEvidence. Trigger: "openevidence reference architecture".
Use when when you need to make OpenMS C++ classes, functions, or data structures callable from Python code, or when verifying that a newly bound C++ component can be imported and…
OpenObserve is an open-source, cloud-native observability platform for logs, metrics, traces, and Real User Monitoring (RUM).
OpenOCD skill for embedded hardware debugging. Use when configuring OpenOCD for JTAG or SWD targets, flashing firmware, connecting GDB to bare-metal targets, setting hardware…
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO en — from…
Use the OpenPond CLI to create repos, watch deployments, and run tools without the web UI.
Use run_shell with inline Python as a fallback when execute_code_sandbox fails for openpyxl/spreadsheet operations
Develop plugins for OpenRCT2 - JavaScript/TypeScript scripting, game actions, UI windows, hooks, multiplayer sync
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3.
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3.
Implement audit logging for OpenRouter API calls. Use when building compliance trails, debugging production issues, or tracking model usage.
Implement caching for OpenRouter API responses to reduce cost and latency. Use when optimizing repeat queries, building RAG systems, or reducing API spend.
Diagnose and fix common OpenRouter API errors. Use when encountering error codes, unexpected failures, or debugging API responses.
Configuration validation and testing utilities for OpenRouter API. Use when validating API keys, testing model availability, checking routing configuration, troubleshooting…
Create debug bundles for troubleshooting OpenRouter API issues. Use when diagnosing failures, unexpected responses, or latency problems.
Send your first OpenRouter API request and understand the response. Use when learning OpenRouter, testing setup, or verifying connectivity.
Understand and handle OpenRouter rate limits. Use when hitting 429 errors, building high-throughput systems, or implementing retry logic.
Design production architectures using OpenRouter as the LLM gateway. Use when planning system design, reviewing architecture, or scaling AI applications.
Use when diagnosing OpenSearch or Elasticsearch cluster issues - slow queries, memory pressure, shard imbalance, red/yellow health, k-NN problems, thread pool saturation, or when…
Node lifecycle management with focus on safe drain procedures, automated-vs-manual infrastructure decisions, and node failure diagnosis.
OpenSite UI component library patterns. Use when creating, editing, or reviewing components in @opensite/ui (opensite-ai/opensite-ui), the Semantic UI Engine, page-speed-*…
protocol service器构建器指导创建生产级connector(Model Context…
解答与开源产品有关的深度技术问题，输出图文并茂的 Markdown 技术文章。触发条件：用户提出与开源项目（如 PostgreSQL、Redis、Kafka、Kubernetes、ClickHouse、Flink 等）相关的技术问题，并提供源码目录或 URL、deepwiki repo…
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements.
Design and plan fixes/refactoring for an OpenSpec change from confirmed reviewer findings without editing code.
Submit compact Open Targets Platform GraphQL requests for target, disease, drug, variant, study, and search data, including associated-disease datasource heatmap matrices — from…
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, naming conventions, error handling, performance,…
Platform-agnostic OpenTelemetry reference — signal selection (traces/metrics/logs), span design, context propagation (W3C TraceContext), sampling strategies, and OTLP exporter…
Use when adding distributed tracing, debugging missing spans, fixing W3C traceparent propagation, configuring OTLP exporters (gRPC vs HTTP), choosing sampling strategies, setting…
Aggregates OpenTelemetry trace spans from Jaeger and Zipkin backends into unified flame graphs. Uses the OTLP gRPC exporter SDK to correlate distributed service calls across…
Instrument distributed systems and microservices with OpenTelemetry (OTel) across Python, Node.js, and Go.
OpenTofu is an open-source infrastructure as code tool that lets you declaratively manage cloud and on-premises resources.
Python API v2 for Opentrons OT-2/Flex liquid handlers: protocols as Python files with metadata and run(); control pipettes, labware, and modules (thermocycler, heater-shaker,…
Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler.
Build generative UI apps with OpenUI and OpenUI Lang — the token-efficient open standard for LLM-generated interfaces.
OpenUI generative UI with C# ASP.NET Core Minimal API backend. Direct OpenAI API SSE streaming via HttpClient on .NET 10.
OpenUI generative UI with a PHP (Laravel 13.x) backend. Forwards OpenAI's SSE stream verbatim via response()->stream().
OpenUI generative UI with Python FastAPI backend. OpenAI and Anthropic SDK variants.
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO — from…
Set up and improve WebF app tests with Vitest and React Testing Library. Use when the user mentions Vitest, React Testing Library, unit tests, component tests, “testing trophy”,…
Write and verify Open WebUI Python tools — the single-file `Tools` class pasted into Workspace > Tools.