Skill rating

INVOKE THIS SKILL when creating, deploying, running, or operating Managed Deep Agents in LangSmith. Covers deepagents-cli, the Python and TypeScript SDKs, React useStream, REST fallbacks, MCP tools, i

Classify or explain Momentic test run results using Momentic MCP tools. Use when the user asks to categorize a failure, understand why a run failed, triage test results, or compare run results to past

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

When the user wants to create or update their Unreal Engine project context document. Use when the user says 'project context,' 'set up context,' 'UE context,' 'configure project,' or wants to avoid r

Golang struct and interface design patterns — composition, embedding, type assertions, type switches, interface segregation, dependency injection via interfaces, struct field tags, and pointer vs valu

Google Gemini File Search for managed RAG with 100+ file formats. Use for document Q&A, knowledge bases, or encountering immutability errors, quota issues, polling failures. Supports Gemini 3 Pro/Flas

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)

WeChat binding: QR scan, bind, unbind, reconnect, status check. Use when setting up or repairing WeChat delivery (e.g. connect WeChat, scan QR, why isn't WeChat pushing, disconnect WeChat).

Advanced search options in GrepAI. Use this skill for JSON output, compact mode, and AI agent integration.

Use this skill when retrieving Jira tickets, analyzing requirements, updating ticket status, adding comments, or transitioning issues. Provides Jira API patterns via MCP or direct REST calls.

Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste /orchestrate custom prompts. Generative only — never invokes /orchestrate i

Guides the agent through adding Swift Package Manager support to an existing Capacitor plugin. Covers Package.swift, CAPBridgedPlugin conversion, bridge cleanup, and package manifest updates. Do not u

Create handoff documentation for work-in-progress sessions. Use when handing off work to another agent to supplement history compaction and and progress summarization.

AI image editing prompting patterns for Qwen-Image-Edit. Use when editing photos while preserving identity, reframing cropped images, changing clothing or accessories, adjusting poses, applying style

Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware app

Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent ac

Create Convex queries, mutations, and actions with proper validation, authentication, and error handling. Use when implementing new API endpoints.

Audits agent skill instructions and system prompts for vulnerabilities to prompt hijacking and indirect injection. Use when designing new agent skills or before deploying agents to public environments

LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.

Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP constraints.

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-te

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence

Nuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /re

Format and parse values for display using the FormatStyle and ParseableFormatStyle protocols and Foundation's concrete styles. Use when formatting numbers (integers, floating-point, decimals), currenc

Guides architectural decisions for LangGraph applications. Use when deciding between LangGraph vs alternatives, choosing state management strategies, designing multi-agent systems, or selecting persis

Find and fix issues from Sentry using MCP. Use when asked to fix Sentry errors, debug production issues, investigate exceptions, or resolve bugs reported in Sentry. Methodically analyzes stack traces,

Server-driven architecture patterns for Inertia Rails + React. Load this FIRST when building any Inertia page or feature — it routes to the right skill. Decision matrix for data loading, forms, naviga

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pip

Harden SSH configuration on VPS servers by disabling root login, enforcing SSH key authentication, and creating non-root sudo users to prevent unauthorized access.

Look up startups across SEC Form D, GitHub, Hacker News, Companies House, YC, and Wikidata in one command — including the SEC fundraising data hidden behind paid Crunchbase tiers. Trigger phrases: `lo

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.

Routes Snowflake-related operations to Cortex Code CLI for specialized Snowflake expertise. Use when user asks about Snowflake databases, data warehouses, SQL queries on Snowflake, Cortex AI features,

Security-first vetting for OpenClaw skills. Use before installing any skill from ClawHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate,

Use this skill when adding, placing, configuring, or fixing the Customware support chat widget in the Customware React Router client-only SPA template. It covers root.tsx/root document script loading,

Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent", "wake agent", "install plugin", "show ag

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up eve

Formats and executes dbt CLI commands, selects the correct dbt executable, and structures command parameters. Use when running models, tests, builds, compiles, or show queries via dbt CLI. Use when un

哈耶克 × 米塞斯 × Claude 三人对话。奥派经济学视角的多角色讨论。 触发方式：/dbs-chatroom-austrian、/chatroom-austrian、/奥派、「奥派聊天室」 Austrian economics chatroom. Hayek × Mises × Claude debate. Trigger: /dbs-chatroom-austrian, /chatroom

Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief,

Background context for the Electronic Bookkeeping Act (電子帳簿保存法) in the shinkoku tax filing plugin. Contains requirements for electronic bookkeeping, scanner storage, mandatory electronic transaction d

INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.

You MUST invoke this skill before saying "I don't know," guessing, or treating any topic as new, no matter how trivial the question seems. It supplements other memory systems, which only hold partial

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained genera

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to acc