Skills your agents can run

Linear issue management. MUST USE when: (1) user mentions LOBE-xxx issue IDs (e.g. LOBE-4540), (2) user says 'linear', 'linear issue', or 'link linear', (3) creating PRs that reference Linear issues. Provides workflows for retrieving issues, updating status, and adding comments.

Enterprise DevOps with Kubernetes 1.31, Docker 27.x, Terraform 1.9, GitHub Actions, monitoring with Prometheus/Grafana, and cloud-native architectures

Create FastAPI application factory with lifespan, middleware, pagination, and router configuration

Static Application Security Testing (SAST) for code vulnerability analysis across multiple languages and frameworks

Query and analyze Datadog logs, metrics, APM traces, and monitors using the Datadog API. Use when debugging production issues, monitoring application performance, or investigating alerts.

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

Monitors research topics for new papers, conferences, and journals.

Build source-derived writing-style profiles from real posts, essays, launch notes, documents, or site copy, and reuse that profile across content, outreach, and social workflows. Use this when a user wants consistent voice without common AI-writing tropes.

Web search using the Brave Search CLI (`bx`). Use for ALL web search requests — including "search for", "look up", "find", "what is", "how do I", "google this", and any request needing current or external information. Prefer this over the built-in web_search tool whenever bx is available. Also use for: documentation lookup, troubleshooting research, RAG grounding, news, images, videos, local places, and AI-synthesized answers.

Horizontal-Vertical Analysis (横纵分析法) deep-research Skill. Proposed by the digital-life figure "Kazik" (数字生命卡兹克), it integrates Saussure's diachronic–synchronic analysis, social-science longitudinal–cross-sectional study designs, business-school case-method thinking, and core ideas from competitive-strategy analysis. Use this when a user wants a systematic, in-depth study of a product, company, concept, technology, or person. The core is a two-axis analysis: the vertical axis traces the full life course from origin to present (presented as a narrative), while the horizontal axis performs a systematic cross-sectional comparison at the present time against competitors/peers. Crossing the two axes yields original insights. The final deliverable is a professionally formatted PDF research report. Trigger phrases include but are not limited to: "horizontal-vertical analysis", "research this", "help me analyze", "deep research", "do some research", "investigate this", "competitive analysis", "take a look at this product/company/thing", "what's this product/company/concept about", "help me figure this out", "help me understand", "do a deep research for me". Even if the user only says "help me understand XX" or "what's the story behind XX", it should trigger when the context implies a need for systematic, in-depth research (rather than a simple definition). It also applies when a user drops a product, company, or technology name and says "research this". Do not use for simple noun definitions (when the user only asks "what is XX"), do not use for writing WeChat public-account articles, and do not use for generating pure titles or summaries.

Create irresistible offers and pitches using Alex Hormozi's methodology from $100M Offers. Guides through value equation, guarantee frameworks, pricing psychology, and creating offers "too good not to take" for any product or service.

Use when interpreting Culture Index surveys, CI profiles, behavioral assessments, or personality data. Supports individual interpretation, team composition (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Handles PDF vision or JSON input.

Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio. Expert in quantization formats (GGUF, EXL2) and local AI privacy.

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Run a local Agent Memory Service for persistent self-improvement with proper Ed25519 cryptography. Fixed signature implementation for reliable memory storage and retrieval.

Build LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangChain, LangGraph, LCEL, RAG, retrieval, agent chain.

Automated context health management for OpenClaw. Monitors token usage, snapshots memory, and resets sessions to maintain performance. Authored by Sophie.

JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination and connection pooling in Spring Boot.

A testing guide using Vitest. Use it when writing tests (.test.ts, .test.tsx), fixing failing tests, improving test coverage, or debugging test issues. It applies to test creation, test debugging, mock setup, and test-related questions.

Master Java 21+ with modern features like virtual threads (Project Loom), pattern matching, and Spring Boot 3.x. Expert in the latest Java ecosystem including GraalVM, Project Loom, the foreign function & memory API, and cloud-native patterns.