Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Guide new SemanticOps MCP users through a plain-language setup concierge for licensing, modes, masking, guardrails, preferences, model safety, tests, reporting, diagnostics, RLS testing, and Enterprise posture. Use when a user types onboarding, asks to set up SemanticOps MCP, wants help choosing Free vs Pro, or wants MCP tailored to their workflow.
Read-only diagnostic for effort-band model routing. Prints the effective band → model map (shipped defaults or the per-environment ladder), the ladder file (or a ready-to-edit starter when none exists), the captured session model, and the most recent routing-bump events from the resolver log. Touches no files; no side effects.
OpenPrd 入口路由 skill：先判断当前任务该读哪个 skill、哪个命令面和哪个门禁。
Generalized structural compliance check for any Claude Code plugin. Audits architectural decisions only — agent type appropriateness (markdown vs script), frontmatter compliance, eval coverage, and body line-count budgets. Use when adding or modifying any agent or skill in a plugin, after scaffolding a new plugin, before a migration PR lands, or for a periodic health check. Accepts any plugin directory path; not hardcoded to one plugin's internal structure.
Mine real Claude Code session transcripts to suggest plugin improvements that cut token spend, reduce re-work, and improve accuracy. Use when the user asks to "review my sessions", "where am I wasting tokens", "why does this keep re-doing work", or "/session-review".
Upgrade an installed Next Move Theory setup to the latest published canon + skills by re-running the official one-command installer, which clones the public GitHub repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main) and refreshes the canon, the nmt-* skills (both Claude and Codex), the injected rules block in CLAUDE.md / AGENTS.md, and the README in place. Idempotent and safe: it never touches your own files and never deletes unrelated skills. Use when the user says "update NMT", "upgrade the skills", "get the latest canon", runs $nmt-upgrade, or when another skill reports that a newer version is available. Defaults to English.
记录和查阅 AI 错题本。当发生错误或需要预警时使用，建立自我进化的反馈闭环，避免重复错误。
Show all available skills, agents, and how to use them — organized by task.
Build an AI-agent application end-to-end — from an empty repo or an existing codebase. Use when the user wants to "build an agent", "scaffold an agent app", "add an agent API", "build an agent UI/chat", "pick an agent framework", or set up tool calling, tracing, or an AI gateway. Interviews the user when requirements are unclear; detects the stack when a project already exists. Knows LangGraph, DeepAgents, Vercel AI SDK, Cloudflare Agents SDK, TanStack AI, Google ADK, and the Claude Agent SDK. Always verifies against live official docs (Context7 / llms.txt / WebFetch) before writing code.
Train and evaluate a navigation policy in the habitat-gs simulator. Covers the full generate-episodes → train → evaluate flow for PointNav / ImageNav / ObjectNav (Habitat-Lab + DDPPO reinforcement learning) and for Vision-and-Language Navigation (StreamVLN, Uni-NaVid). Use when the user wants to train, fine-tune, resume, or evaluate a nav policy / agent on GS scenes — NOT for interactively piloting a live sim (use the habitat-gs-control skill for that).