liliang-cn

Use CortexDB for local-first AI memory, vector search, RAG, knowledge graphs, SPARQL/RDFS/SHACL, corpus-to-graph workflows, external structured-data import (CSV / SQL dumps), and MCP/tool calling. Use when working with CortexDB, embeddings, memory, RAG, GraphRAG, knowledge graph, RDF, SPARQL, SHACL, data import, CSV/SQL dump import, memoryflow, graphflow, importflow, or MCP tools.

Use CortexDB for local-first AI memory, vector search, RAG, knowledge graphs, SPARQL/RDFS/SHACL, corpus-to-graph workflows, and MCP/tool calling. Use when working with CortexDB, embeddings, memory, RAG, GraphRAG, knowledge graph, RDF, SPARQL, SHACL, memoryflow, graphflow, or MCP tools.

Give a Python agent (such as Hermes Agent by Nous Research) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client PyPI package. Use when a Python agent needs to remember facts about a user across turns/sessions, recall them by meaning, store entities and relations, or answer multi-hop questions — and when the user mentions CortexDB, agent memory, long-term memory, RAG, knowledge graph, Hermes, or "remember this".

Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client npm package. Use when a Node agent needs to remember facts about a user across turns/sessions, recall them by meaning, store entities and relations, or answer multi-hop questions — and when the user mentions CortexDB, agent memory, long-term memory, RAG, knowledge graph, OpenClaw, or "remember this".

Use CortexDB for local-first AI memory, vector search, RAG, knowledge graphs, SPARQL/RDFS/SHACL, corpus-to-graph workflows, and MCP/tool calling. Use when working with CortexDB, embeddings, memory, RAG, GraphRAG, knowledge graph, RDF, SPARQL, SHACL, memoryflow, graphflow, or MCP tools.

Build AI agents in Rust using the harness-rs framework. Use this skill whenever the user is writing Rust code that imports any harness-rs-* crate (harness-rs, harness-rs-core, harness-rs-loop, harness-rs-models, harness-rs-tools-fs, harness-rs-tools-shell, harness-rs-context, harness-rs-skills, harness-rs-macros, harness-rs-hooks, harness-rs-compactor, harness-rs-sandbox, harness-rs-blueprint, harness-rs-sensors-rust, harness-rs-templates, harness-rs-mcp, harness-rs-daemon); when scaffolding a new agent with `harness new`; when adding custom tools, skills, guides, sensors, or hooks via the framework's proc-macros (#[tool]

A skill whose name violates the spec (uppercase + dir mismatch).

Greet a user by name. Use when the user explicitly asks for a friendly hello.

Build interfaces with tactile-css in plain HTML/CSS, React, Vue, or Tailwind. Use when a user wants to install this package, choose between raw CSS classes and framework wrappers, apply Tactile themes, or compose neumorphic UI with the library's exported components in another project.

Maintain and expand the Tactile CSS component library across its CSS source, generated dist files, React wrappers, Vue wrappers, TypeScript declarations, and README examples. Use when adding new components, updating existing components, changing class names, extending React/Vue exports, or keeping framework wrappers and docs in sync for this repository.

Release and version the Tactile CSS package, including lockfile sync, fnm/Node selection, build verification, npm pack checks, git commit creation, tag management, push, and publish preparation for this repository. Use when bumping versions, fixing CI/package-lock drift, creating or recreating tags, or preparing npm releases.

Use AgentGo (github.com/liliang-cn/agent-go/v2) as a Go library to build AI agents, RAG pipelines, and multi-agent teams. Use when the user is writing Go code that imports github.com/liliang-cn/agent-go/v2 and needs help with agent.New() / TeamManager / Tasks / TaskPlan / output lints / task checkpoints / memory / MCP / PTC, or when configuring providers in agentgo.toml or via the agentgo CLI.

Use AgentGo as a Go library to build AI agents, RAG pipelines, and multi-agent teams. Use when writing Go code that needs AI agent capabilities, document ingestion, semantic search, or multi-agent orchestration.

Exact trigger test skill for CLI verification

API operations for pets (6 endpoints)

Provides Search for pets

DRBD and LINSTOR expert - software-defined storage, high availability

Linux system administration expert

Create git commits with conventional commit format. Use when the user wants to commit changes.

Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"

SSH batch operation tool for executing commands, copying files, and managing multiple remote servers in parallel. Use when you need to run commands on multiple hosts, transfer files, or manage SSH-based infrastructure operations.

Perform comprehensive web searches and research using the MCP Web Search Server.

发布一个服务的新版本。当用户要"发版""上线新版本""出一个 release""部署到生产"时使用。

Automate a real logged-in browser — navigate, read the page, click, fill forms, log in, scrape, multi-step web tasks — with YOU (Claude) as the agent brain via the browser-use MCP's DIRECT tools. NO separate LLM API key. Uses a DEDICATED persistent Chrome profile (separate from the user's daily Chrome) so logins persist across sessions and Chrome's anti-automation restrictions don't apply. Use when the user says "use the browser", "go to site X and do Y", "log into X and …", "fill this form", "scrape/click through this page", "star/like/post on a site", "book/search/download", or wants browser automation with their login state. For a single static page, prefer WebFetch.