AI & ML

zuoguyoupan2023 Skill

Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state (gstack)

zuoguyoupan2023 Skill

Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.

zuoguyoupan2023 Skill

REST API server and MCP protocol integration

zuoguyoupan2023 Skill

案号识别与溯源，用于从文书、备忘、聊天记录或其他长文本中提取案号并回源案件线索。Use when：用户已经有一段文本，想识别其中的案号、批量抽取案号，或核查案号对应案件信息。NOT for：按争议主题检索案例、法条识别、法规主题检索。要求不得编造案号、法院名称与日期，全部基于当次 MCP 返回。

zuoguyoupan2023 Skill

Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.

zuoguyoupan2023 Skill

Apply LaunchDarkly SDK onboarding: install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile. Nested under sdk-install; next is run.

zuoguyoupan2023 Skill

12 regulatory & QM agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. ISO 13485 QMS, MDR 2017/745, FDA 510(k)/PMA, ISO 27001 ISMS, GDPR/DSGVO, risk management (ISO 14971), CAPA, document control, auditing. Python tools (stdlib-only).

zuoguyoupan2023 Skill

Detects your Python environment and guides you through installing plugin dependencies. Use on first-time setup or when MCP server fails to start.

zuoguyoupan2023 Skill

Write idiomatic application code with the ClickHouse Node.js client (`@clickhouse/client`). Use this skill whenever a user is *building* against the Node.js client — configuring the client, pinging, inserting rows in JSON or raw formats, selecting and parsing results, binding query parameters, managing sessions and temporary tables, working with data types or customizing JSON parsing. Do NOT use for browser/Web client code.

zuoguyoupan2023 Skill

Instrument a Java application with the Elastic Distribution of OpenTelemetry (EDOT) Java agent for automatic tracing, metrics, and logs. Use when adding observability to a Java service that has no existing APM agent.

zuoguyoupan2023 Skill

Cross-model benchmark for gstack skills. (gstack)

zuoguyoupan2023 Skill

Query the LLM Wiki — reads index.md first, drills into 3-10 relevant pages, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back as a new comparison or synthesis page. Usage /wiki-query "<question>"

zuoguyoupan2023 Skill

类案检索报告与办案备忘工作流，用于把案例检索压缩成可讨论、可转发、可复核的备忘文本，包含案例样本、案号核验与链接增强。Use when：律师、争议解决团队或合规调查团队需要快速形成“类案要点 + 可核验线索 + 交付版备忘”的标准产物。NOT for：仅要单条案例原文、仅做案例列表罗列、或不需要对比分析的场景。要求关键信息必须可追溯到当次 MCP 返回，避免无依据的裁判倾向推断。

zuoguyoupan2023 Bundle

一键安装/配置北大法宝（pkulaw.com）MCP 服务。当用户需要安装北大法宝 MCP、配置 pkulaw MCP、给新设备/新用户配置北大法宝法律检索工具时使用此技能。必须保护用户 Token，不在聊天、日志或公开仓库中写入真实凭证。触发词：安装北大法宝MCP、配置pkulaw、北大法宝一键安装、pkulaw setup、MCP安装。

zuoguyoupan2023 Skill

检索司法案例与裁判文书资料。当前本机只订阅 `case-keyword`（检索司法案例-关键词），不得假定 `case-semantic`、`case-number` 等旧 MCP 可用。Use when：用户明确要找类案、裁判样本、裁判文书线索，或希望围绕一个争议问题先看法院如何处理。NOT for：法规检索、已知法条的精准全文查询、案号识别溯源、以及未经过检索就直接概括“法院通常怎么判”的任务。须已配置并订阅法宝 MCP；禁止无检索依据编造案号、法院名称、裁判日期或裁判要旨。

zuoguyoupan2023 Skill

精准查找法条，用于在已知法规名称与条号的前提下取回条文原文或可回源的条文内容。Use when：用户已经明确给出法规名称和条号，希望核对条文原文、脚注引用或文书引注。NOT for：模糊主题检索、从长文本自动识别法条、案例检索。要求必须基于当次 MCP 返回作答，禁止编造条文、条号或补写未返回内容。

zuoguyoupan2023 Skill

北大法宝原生 MCP 的总路由法律研究 Skill。当前本机已配置三个 MCP：`law-keyword`（检索法律法规-关键词）、`fatiao`（精准查找法条-关键词）和 `case-keyword`（检索司法案例-关键词）；不得假定案号识别、引用核验、超链、语义检索等旧 MCP 可用。Use when：用户只说“帮我查法律依据/案例”，但尚未明确该走法规关键词、精准法条还是案例关键词；或你需要在原生 MCP 能力之间分流。NOT for：网页端登录、网页详情页点击、复制详情页 URL、机构/IP 登录核验；这些应转用户自建的 `pkulaw-legal-search` 网页/Computer Use 流程。须已配置并订阅北大法宝 MCP；禁止无检索依据编造法条、案号、裁判要点或引用结论。

zuoguyoupan2023 Skill

使用 `semantic-nlsql` 做跨库语义检索与综合法律资料召回。Use when：用户问题同时跨法规、案例、法条或多类材料，希望先用一次自然语言检索拿到综合候选结果。NOT for：只查单一法规、只查单一案例、已知法规名加条号的精准查询，以及未完成 `serverPaths.semantic-nlsql` 配置的环境。必须先确认实例路径可用；未配置时只能提示配置与替代方案，不得伪造结果。

zuoguyoupan2023 Skill

Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.

zuoguyoupan2023 Bundle

Create and configure LaunchDarkly feature flags in a way that fits the existing codebase. Use when the user wants to create a new flag, wrap code in a flag, add a feature toggle, or set up an experiment. Guides exploration of existing patterns before creating.

zuoguyoupan2023 Skill

Show recent entries from the LLM Wiki log (wiki/log.md). Uses the standardized

zuoguyoupan2023 Skill

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)

zuoguyoupan2023 Bundle

Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints, interruption-aware streaming responses, or voice-enabled chat agents that connect developer-owned server logic to ElevenLabs speech-to-text and text-to-speech.

zuoguyoupan2023 Skill

通用法律答复草稿工作流，用于把已检索到的法规、案例和引用核验结果整理成可复核、可转发、可继续修改的答复文本。Use when：律师、法务、合规或法律运营需要回复客户、业务、领导或内部群，且问题不明显属于某个已单独建模的垂直场景。NOT for：纯资料探索、仅需检索列表、不需要形成答复草稿的任务；以及已有更合适垂直 Skill（如劳动用工回复）时。要求先补齐关键事实，再检索后结论；未核验的具体法条不得写成确定依据。

zuoguyoupan2023 Skill

法条识别与溯源，用于从合同、函件、答复、备忘或其他长文本里识别潜在法规引用，并给出可继续核查的来源线索。Use when：用户已经有一段文本，想自动识别其中提到的法规名、条号或引用表达。NOT for：法规主题检索、已知法规名加条号的精准全文查询、案例检索。要求禁止编造法规名、条号与溯源链接，识别结果必须以当次 MCP 返回为准。

zuoguyoupan2023 Skill

Dispatched sub-agent that runs a periodic health check on an LLM Wiki vault. Runs mechanical checks via scripts (orphans, broken links, stale pages, missing frontmatter, duplicate titles, log gaps), does semantic checks (contradictions, stale claims, cross-reference gaps, concepts missing their own page), and produces a markdown report with suggested actions. Spawn weekly, after batch ingests, or when the user says "check the wiki" / "lint my wiki" / "audit the vault".

zuoguyoupan2023 Skill

Financial analyst agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Ratio analysis, DCF valuation, budget variance, rolling forecasts. 4 Python tools (stdlib-only).

zuoguyoupan2023 Skill

Instrument a Python application with the Elastic Distribution of OpenTelemetry (EDOT) Python agent for automatic tracing, metrics, and logs. Use when adding observability to a Python service that has no existing APM agent.

zuoguyoupan2023 Skill

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

zuoguyoupan2023 Bundle

Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.

zuoguyoupan2023 Bundle

Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.

zuoguyoupan2023 Bundle

Diagnose HPC runtime and scheduler problems for materials simulations, including MPI/OpenMP/GPU layout, modules, CUDA/Kokkos hints, scratch paths, walltime, job arrays, restart strategy, scheduler portability, and resource mismatch. Use when jobs fail, run slowly, get killed, or behave differently on a cluster than on a workstation.

zuoguyoupan2023 Bundle

Control LaunchDarkly feature flag targeting including toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag configurations between environments. Use when the user wants to change who sees a flag, roll out to a percentage, add targeting rules, or promote config between environments.

zuoguyoupan2023 Skill

Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop

zuoguyoupan2023 Bundle

Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server.

zuoguyoupan2023 Skill

Execute decomposed fullstack tasks with layer-aware agent routing