Work with GitHub Actions CI/CD workflows - read live syntax, monitor runs, and debug failures. Use when writing, running, or debugging GitHub Actions workflows.

Adding custom commands to the Webiny CLI using CliCommandFactory. Use this skill when the developer wants to create a custom CLI command, add a data migration script, build a code generator, create deployment scripts, export CMS content, or add health check commands. Covers CliCommandFactory.Interface, command definition, typed parameters, the Ui service for terminal output, and registration via <Cli.Command>.

Adding custom HTTP routes to the API using Api.Route and Route.Interface. Use this skill when the developer wants to expose a custom HTTP endpoint (GET, POST, PUT, etc.) on the API Gateway alongside the GraphQL handler, implement Route.Interface with full DI support, or register a custom HTTP handler in webiny.config.tsx.

Generate a market requirements document (MRD) from a product idea and save it as Markdown under the current project's markdown/ directory. Use when the user asks to write, draft, create, produce, or refine an MRD, market requirements document, product opportunity document, market demand analysis, product idea validation document, or asks for "写 MRD", "市场需求文档", "产品立项文档", "产品机会分析", especially when input is only an idea and the output should be structured, visual, and decision-oriented.

编写产品评测报告的 skill。流程：询问被评测产品名、资料/链接、评测功能点、目标使用场景、竞品 → 网络核实最新状态 → 站在决策者（买不买）和使用者（好不好用）双视角 → 输出图文并茂的 markdown 评测报告到当前项目的 markdown/ 目录。报告包含：TL;DR、双视角结论、维度评分、竞品对比、选型决策树、实操指南、依据与参考。适用于"评测 XX 产品"、"对比 X 和 Y"、"XX 工具选型"等需求。

面向投资者的近 3 天新闻抓取与影响分析技能。触发场景 - 用户要求「抓取最近新闻」「生成投研日报」「分析新闻对 XX 行业或公司的影响」「今天或最近有什么重要新闻」时启用。若用户提供行业名则只抓该行业, 否则并发抓取「中美关系、地缘局势、美联储、民生数据、高科技、生物医疗、云计算产业、AI 产业链」8 个默认主题, 按分类总结, 推演对行业和上市公司的影响, 图文并茂输出到当前项目 markdown 目录。

How xberg versions are synced and released — Cargo.toml is the single source of truth, `task version:sync` propagates it to alef-managed binding manifests AND the integrations under integrations/, which are versioned and published in lockstep with core (including -rc.N). Load before bumping a version, editing the version-sync task, or touching an integration's version/xberg dependency.

Set up, connect, validate, and repair Claude Desktop and MCP servers using Desktop Commander — inspecting and fixing mcp.json / claude_desktop_config.json, getting MCP servers to connect, and diagnosing local AI tooling. Use when a user wants to install, configure, connect, validate, or fix Claude Desktop, an MCP server, an MCP config file, or a local AI agent/gateway. Trigger on the symptoms that actually bring people in: "Claude can't see my tools", "my MCP server isn't showing up", "tools aren't loading in Claude", "add an MCP server", "my MCP isn't connecting", "fix my Claude Desktop config", "the agent won't respond", "wire up Ollama / LM Studio", "restart Claude Desktop". Also covers local agent gateways like OpenClaw and Hermes.

Use Desktop Commander for terminal and command-line work, especially anything that needs a shell whose state persists across turns: Python/Node REPLs, database shells, dev servers and other long-running processes, SSH into remote machines, and Windows PowerShell. Also handles everyday terminal tasks — navigating folders, choosing the right command for the user's shell (PowerShell, cmd, bash, zsh), running Docker/curl/cloud-CLI commands, inspecting processes and ports, and saving recurring workflows as scripts — even when the user doesn't say "Desktop Commander" or "terminal." Reach for it on pasted errors like "command not found", "permission denied", "EADDRINUSE", "address already in use", "npm ERR!", "ModuleNotFoundError", or "ENOENT", and on intents like "what's using port 3000", "kill that process", "ssh into my server", or "why won't my dev server start". Works on Windows, macOS, and Linux. Never run destructive commands without explicit confirmation.

Append a dated event to a matter's history file and refresh the log row — captures new developments, status changes, risk re-assessments, deadline shifts, and settlement authority changes. Use when the user wants to log an update on a matter, note a development, or record a status change against the portfolio.

Uninstall a community skill that was installed via the hub. Confirms before deleting files, refuses to touch first-party plugin skills, and logs every action. Use when the user wants to fully remove a community skill ("uninstall [skill]", "remove this skill") rather than just disable it.

Guided customization of your Legal Builder Hub profile — change one thing without re-running the whole cold-start interview. Adjust practice profile, installed starter pack, watched registries, update preferences, or QA strictness. Use when the user says "change my [thing]", "add a registry", "update my profile", "edit my config", or "customize".

Build or update a long-term bar prep (or exam prep) study plan — phases, subjects weighted by weakness, daily session schedule, adaptive to session history in study-plan.yaml. Use when the user says "build a study plan", "plan my bar prep", "schedule my studying", or "how should I study for [X]".

Draft an employment policy with state supplements where law differs across the jurisdictional footprint. Use when the user says "draft a [topic] policy", "we need a policy on", "update our [topic] policy", or names a policy gap.

Ask questions against an open investigation log — what witnesses said, where accounts conflict, what gaps exist, what the strongest evidence is on each issue. Use when the attorney needs to query the investigation record without re-reading every entry.

Guided customization of your employment practice profile — change one thing without re-running the whole cold-start interview. Adjust jurisdictional footprint, risk posture, escalation contacts, hiring review rules, termination review rules, handbook positions, investigation preferences, or matter workspace paths. Use when the user says "change my [thing]", "add a jurisdiction", "update my profile", "edit my config", or "customize".

Review and approve (or reject) pending playbook update proposals from the playbook-monitor agent and apply approved changes to the practice profile. Use when the playbook-monitor agent has surfaced proposals, when the user says "review playbook proposals", "what playbook updates are pending", or wants to step through deviation-driven playbook changes.

Guided customization of your AI governance practice profile — change one thing without re-running the whole cold-start interview. Adjust risk posture, escalation contacts, use-case registry entries, vendor AI positions, AI policy commitments, impact-assessment house style, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my config", "tune my playbook", or "customize".

Triage open pull requests for CI status, review comments, and merge readiness. Use in PR babysitter loops. Respects project review norms and required checks.

Pick the right fine-tuning framework for a MiniCPM5-1B base checkpoint and route to a framework-specific cookbook skill. Use when the user wants to SFT / LoRA / DPO / continue-pretrain MiniCPM5 and has not yet committed to a specific framework, or when they say "fine-tune MiniCPM5", "train MiniCPM5", "MiniCPM5 微调", "LoRA MiniCPM5", "继续训练 MiniCPM5".