Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks. Use when debugging microservices, analyzing request flows, or implementing observability for distributed systems.
Initializes the project for the DO Framework: analyzes it, inventories installed skills and MCP servers (reporting gaps), and writes the framework's local context file `.do/context.md` (summary, conventions, commands, skills and MCPs). Never edits an existing project instructions file (CLAUDE.md, AGENTS.md, .github/copilot-instructions.md, .cursor rules); when the project has none, offers to create one with project content only (no framework, skill or MCP references). Installs the orchestration agents and commands. Arguments: "agents" (install agents/commands only), "refresh" (re-detect skills/MCPs only). Use to initialize or configure the agent-assisted environment. Not for PRDs, implementation, review or QA.
Apply these opinionated .NET 8 architecture conventions whenever structuring or reviewing a backend service: clean architecture layering and which direction dependencies point, when CQRS with MediatR is worth it, cross-cutting concerns as pipeline behaviours, minimal APIs grouped by feature, keeping DbContext in Infrastructure, health checks and structured logging, WebApplicationFactory integration tests, and when AOT pays off.
Use dspy.RLM (Recursive Language Model) for reasoning over contexts too large to fit in an LLM's working window — entire codebases, long logs, massive documents, or multi-step data exploration that needs a sandboxed Python REPL. Use when the input is >100k tokens, needs recursive chunking, or benefits from the LLM writing and running code to probe data.
This skill should be used when the user asks to "review code", "review my changes", "check effect patterns", "run effect review", "effect review", "review for effect best practices", or wants a comprehensive code review against Effect-TS conventions, branded types, observability, error handling, test coverage, and UI quality.
Authoritative Python-FFmpeg parameter integration reference ensuring type safety, accurate parameter mappings, and proper unit conversions. PROACTIVELY activate for: (1) ffmpeg-python library usage, (2) Python subprocess FFmpeg calls, (3) Caption/subtitle parameter mapping (drawtext, ASS), (4) Color format conversions (BGR, RGB, ABGR, ASS &HAABBGGRR), (5) Time unit conversions (seconds, centiseconds, milliseconds), (6) Type safety validation (int, float, string), (7) Coordinate systems, (8) Parameter range enforcement, (9) Frame pipe handling, (10) Error detection for type mismatches. Provides: Complete parameter type reference, color format conversion tables, time unit conversion formulas, validation patterns, working Python examples with proper typing.
Build, edit, and deploy Salesforce Data Capture Flows (processType DataCaptureFlow) — Field Service mobile / offline forms. Use when authoring flow-meta.xml with runtime_service_fieldservice:dc* components, Repeater loops (.AllItems), master-detail child record persistence, visual polish (gradient banners, progress bars, callouts), supporting objects with FLS/permsets, debugging DataCaptureFlow deploy errors, or troubleshooting why a deployed form doesn't appear on the FSL Mobile Forms tab (DDC/WorkPlan OWD + AssignedResource sharing prerequisites).
Selects a base model and fine-tuning technique (SFT, DPO, or RLVR) for the user's use case by querying SageMaker Hub. Use when the user asks which model or technique to use, wants to start fine-tuning, or mentions a model name or family (e.g., "Llama", "Mistral") — always activate even for known model names because the exact Hub model ID must be resolved. Queries available models, validates technique compatibility, and confirms selections.
Invoke when the user works with Godot Engine or asks about GDScript, scene composition, signals, resources, shaders, GDExtension, physics, or Godot UI. Triggers on: "Godot", "GDScript", "scene tree", "signals", ".tscn", ".tres", "GDExtension", "project.godot". Do NOT invoke for engine-agnostic architecture (use game-technical-director) or Unity/Unreal questions (use the appropriate engine specialist). Part of the AlterLab GameForge collection.
Best practices for building AI agents with Google's Agent Development Kit (ADK) in Python, covering agent design, tools, sessions, memory, artifacts, evaluation, and deployment. Use when building LLM agents or multi-agent systems with ADK, defining ADK tools, wiring up sessions/state/memory, working with ADK artifacts, writing agent evals, or deploying ADK agents to Vertex AI Agent Engine or Cloud Run.
A high-intensity questioning interview about a plan or design (adversarial design review / grill session) that exposes flawed assumptions and missing constraints, while maintaining a domain model (glossary and ADRs) throughout. Invoke manually with /grill-me.
This skill MUST be used when a bug's root cause is unknown and requires investigation, or when the user explicitly requests investigate or root-cause analysis. SHOULD be used for unexplained failures, regressions, or intermittent behavior: 根因調查, 為什麼會這樣, 壞掉了, failing, broken, flaky. MUST NOT treat an apparently obvious cause as confirmed without evidence. When evidence already establishes the cause, proceed to targeted verification and repair without restarting the investigation.
Collaborative workflow for handling GitHub issues. Use when a user receives an issue that needs analysis and a reply. Through the four-step method "diagnose → classify → decide → reply", it produces an accurate root-cause analysis and a professional user reply from a single issue, avoiding misjudging the problem type or giving an unprofessional reply.
Diagnose Kanban flow problems and design board operating models. Load this when your team is struggling with throughput, cycle times are unpredictable, multiple stakeholders compete for the same engineers, or you're wondering if Kanban is right for you. Do not use this skill for unrelated requests; route to the nearest named specialist.
Work with Lapian Notes / 拉片笔记 (github.com/bkingfilm/lapian-notes) — a local-first React/Vite tool that turns a film into an editable shot-by-shot study notebook: local frame extraction, AI-assisted structure analysis (bring your own AI, no API key required), story-line swimlane timeline, structure tree, and audience-emotion curve. Use when the user asks about Lapian Notes, "拉片笔记", "拉片" (shot-by-shot film analysis) tooling, cloning/running this repo (npm run dev, run.bat/run.command), the AI-analysis-package (ZIP) round-trip workflow, or contributing a PR to lapian-notes. Not for generic video editing (use `opencut` for that) or generic film-analysis theory unrelated to this codebase.
Load automatically when user asks to learn Astro framework development (e.g., "teach me how to build with Astro", "guide me through Astro", "I want to learn Astro", "quiero aprender Astro", "how do I get started with Astro"). Interactive guided tutorial where Claude acts as a co-pilot, guiding the user through building a real personal blog with Astro step-by-step. Trigger this skill whenever the user expresses interest in learning Astro from scratch, even if they don't say "tutorial" explicitly.
Apply this opinionated workflow when modernizing legacy systems: strangler fig pattern, branch by abstraction, characterization tests, incremental monolith decomposition, framework upgrades, feature-flagged migration with rollback.
Integrates Apache ECharts into UniApp and UniAppX projects for cross-platform data visualization (H5, mini-programs, native App). Supports line, bar, pie, scatter, radar, gauge, funnel, heatmap, and more chart types. Use when the user needs to create ECharts charts in UniApp/UniAppX or configure interactive data visualizations for mobile and web.
Structured observability with Pydantic Logfire and OpenTelemetry. Use when: (1) Adding traces/logs to Python APIs, (2) Instrumenting FastAPI, HTTPX, SQLAlchemy, or LLMs, (3) Setting up service metadata, (4) Configuring sampling or scrubbing sensitive data, (5) Testing observability code.
MATLAB/GNU Octave numerical computing: matrices, linear algebra, ODEs, signal processing, optimization, statistics, scientific visualization. MATLAB-syntax examples run on both. For Python use numpy/scipy; for statistical modeling use statsmodels.
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.