Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Add SQLite local database storage to .NET MAUI apps using sqlite-net-pcl. Covers data models with ORM attributes, async database service with lazy init, DI registration, WAL mode, and file management. Works with any UI pattern (XAML/MVVM, C# Markup, MauiReactor). USE FOR: "SQLite database", "local database", "sqlite-net-pcl", "offline storage", "CRUD database", "database service", "WAL mode", "CreateTableAsync", "local data persistence", "ORM attributes". DO NOT USE FOR: REST API data fetching (use maui-rest-api), secure credential storage (use maui-secure-storage), or file picking (use maui-file-handling).
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Prepare Microsoft Store release readiness for Windows apps, desktop utilities, games, PWAs, and packaged software including package identity, MSIX/AppX packaging, Store listing, screenshots, age ratings, privacy, capabilities, in-app purchases, subscriptions, updates, certification, installer behavior, Windows integration, telemetry, crash quality, support links, and release rollout. Use when submitting or auditing products for Microsoft Store.
MLflow 3 (open-source, pinned to 3.15) for classic-ML MLOps — logging and registering models, promoting versions across dev/staging/prod, standing up a tracking server, evaluating with gates, and serving. Corrects the MLflow 2-era defaults a model reaches for (artifact_path, registry stages and get_latest_versions, top-level mlflow.evaluate with baseline_model, runs-URI registration, pickle serialization, mlruns file stores, MLServer serving) with the MLflow 3 idioms that replaced them (named LoggedModels, aliases and copy_model_version, models.evaluate plus validate_evaluation_results, skops/torch.export defaults, database backends, the FastAPI scoring server). Use when writing, reviewing, or migrating Python code that touches MLflow tracking, the model registry, evaluation, or serving.
Scaffold and create a Modular Monolithic Architecture project. Use when the user wants to create a new modular monolith, restructure a monolith into modules, design module boundaries, or set up a project following modular monolith best practices. Supports multiple languages and frameworks.
Orchestrate two or more local workers with independent boundaries, using Orca Run/Task/Dispatch, separate worktrees/sessions, or a tmux fallback, with the PM handling decomposition, dispatch, inspection, 429 stall recovery, independent acceptance, PR wrap-up, and cleanup of temporary resources; also used when the user explicitly asks for "parallel progress", "multiple workers", "PM as overall controller", or "Wave Autopilot", or to prevent the PM from escaping into direct implementation. Do not use for a single short task, pure status syncing, or work that only needs Git branch, commit, PR, or merge rules.
Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node_essentials and get_node_info, or learning common configuration patterns by node type.
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, or the validation loop process.
Turns product or tech specs into concrete Notion tasks that Claude code can implement. Breaks down spec pages into detailed implementation plans with clear tasks, acceptance criteria, and progress tracking to guide development from requirements to completion
(NS) GraphRAG process. Use for GraphRAG, knowledge graph over documents, multi-hop retrieval, entity/relationship extractors, indirect-link analytics, or grounded structured extraction — even if they only say RAG, NER, knowledge graph, or cited Q&A. Do NOT use for Postgres schema/mode alone (`ns-postgres-rag` first). Do NOT use for competing vector stores, free graph QL, or co-occurrence-as-edge.
OCPP protocol reference for EV charging infrastructure development. Covers OCPP 2.1, OCPP 2.0.1, and OCPP 1.6J. Use when working with OCPP messages, charging station code, CSMS/Central System backends, smart charging, transaction handling, or EV charging protocols. Activates on keywords: OCPP, charging station, charge point, CSMS, Central System, EVSE, charging profile, BootNotification, TransactionEvent, StartTransaction, StopTransaction, SetChargingProfile, or any OCPP message name. Also covers OCPP 2.1 features: DER control, V2X, bidirectional power transfer, tariff, battery swap, periodic event stream, device model, dynamic charging profile.
Shared OpenSpec workspace gate for OPSX workflows: locate project root, verify openspec/, and require exact native OPSX skills before delegation. Triggers - "OpenSpec workspace gate", "OPSX workspace locate", "OpenSpec native skill check" / OPSX workspace gate, OpenSpec project root, native skill gate. Do NOT use for Jira, Git, retry binding, or implementation orchestration.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Guide for developing CommonTools patterns (TypeScript modules that define reactive data transformations with UI). Use this skill when creating patterns, modifying existing patterns, or working with the pattern framework. Triggers include requests like "build a pattern", "fix this pattern error", "deploy this piece/patch", or questions about handlers and reactive patterns.
Optimize software performance through user-journey baselines, profiling, representative benchmarks, controlled experiments, and field verification. Use when asked to make an application, service, workflow, or hot path faster or more efficient, or to build the measurement loop first. Do not use for a reliability incident, capacity forecast, generic product A/B test, or operating a named telemetry or load-testing tool without an optimization objective.
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
Only use when the user explicitly invokes /plan-explain (or $plan-explain in Codex). Never auto-invoke. Reads a plan file such as those under `.sisyphus/plans/` and generates a structured summary report so a human can immediately grasp what that plan does. It only extracts facts and performs no interpretation, speculation or additional investigation.
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
This skill should be used when drafting GitHub issues for the Positron repository. It provides workflows for searching duplicates, selecting appropriate labels, gathering complete context through questioning, and writing terse, fluff-free issues that precisely describe what is needed or wrong. The skill prepares issues for manual submission by the user. Use this skill when the user asks to draft or prepare an issue for Positron.
Generate Power Automate flows from natural language. Reads connector schemas from work repo, outputs deployable solution files. USE WHEN user says 'create flow', 'power automate', 'automate workflow', or describes a business process to automate.
Only use when the user explicitly invokes /pr (or $pr in Codex). Never auto-invoke. Safely performs the whole sequence of Git operations from creating a feature branch to staging, committing, pushing and creating a Pull Request, while complying with branch rules (prefer develop, no direct commits to protected branches).
For scenarios involving batch pull requests to ruan-cat related repositories, syncing changes across repositories, planning a PR strategy for multiple cloned local repositories, and choosing a mixed execution approach of local git/Bash with the GitHub API/MCP. Trigger keywords include "批量 PR", "多仓库同步改动", "对 ruan-cat 的仓库发 PR" and "pr-ruancat-repo".
Only use when the user explicitly invokes /pr-stage (or $pr-stage in Codex). Never auto-invoke. Commits only changes that are already staged (already git added) and, if needed, goes as far as creating a feature branch, pushing and creating a PR. The authoritative procedures and safety guards live in the pr skill; this skill defines only the difference (it handles staged changes only) and is a thin wrapper.
Only use when the user explicitly invokes /pre-define (or $pre-define in Codex). Never auto-invoke. A skill for refining a user's vague request into concrete input that can be handed to detailed requirements definition (/define). It does not make specification decisions or define requirements itself; it investigates related existing specifications and asks simple questions repeatedly, aiming to eliminate miscommunication.
Prepare Sprint 0 (walking skeleton) for a project based on its Tech Design and ADRs: classify ADRs as cross-cutting or story-specific, define the route ownership map by role, write the skeleton's Definition of Done, propose a plan, and stop for human approval. Use when the LEAD (or user) needs to prepare, plan, or initialize a project's Sprint 0 / walking skeleton before any user story is built.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.