Coding & Development

Use for any work inside packages/world — Agent World, the local GBA-style dispatch console where this repo's .claude/agents/ are NPCs you walk up to and give tasks. Covers its bridge (Express on 127.0.0.1:8787, spawning the claude CLI, tailing and redacting transcripts, measuring diffs), its Phaser client (ASCII tilemaps, generated and vendored art, the session panel), and the rules that keep it safe and local. Also use when asked whether something about the world can be deployed, shared, or pointed at a second repo — the answers are no, no, and not yet. Not for the pokewatch app itself: packages/world/bridge/server.js and the repo-root server.js are different files with different owners.

Strategic finance executive who governs capital allocation, treasury operations, financial planning, M&A finance, investor relations, and board reporting — translating financial complexity into clear decisions that drive business performance and stakeholder confidence.

Audits AI-agent runs and session snapshots for token usage, cache traffic, cost, duration, turns, tool calls, failures, retries, subagent attribution, duplicated reads, and artifact yield. Use when reporting or comparing a Codex CLI rollout, GitHub Copilot CLI, Gemini CLI, OpenCode, Claude Code, a runner export, or transcript logs. Do NOT use to monitor live CI, prove a check can fail, or sandbox a CLI.

Claude Code ↔ Codex 组队协作：同步接手对方的工作。 当用户说"cowork sync"、"同步"、"接手"、"sync"、"继续对方的工作"时触发。 读取项目目录下 .teams/projects/bridge/ 的最新交接文档和 shared-context， 展示对方的工作成果并准备继续协作。

Check AI subscription usage limits across Claude, ChatGPT and Grok in one unified report — percent used, how much is left, and when each window resets. Use when the user runs /ai-usage or /uu, or asks 額度, 用量, usage, limit, 還剩多少, 什麼時候 reset, 被限流了嗎, rate limit, quota, "am I out of Claude", "how much ChatGPT left".

Give a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a user-supplied approach set. Use for a solo POV, a mid-session second opinion, a named-peer cross-check, any request to consult other models or reconcile their opinions, an `oracle` panel, or a correction-cost-gated proactive cross-check offer. Not for findings review (use ce-doc-review), neutral explainers, or generating options (use ce-ideate or ce-brainstorm).

Compile one portable AI capability spec into artifacts for MCP, Claude, Gemini, DeepSeek, Meta/Llama and browser agents.

Use any time Claude Code works with the PokeTrace API in this project — editing server.js's pokeTraceFetch/resolvePokeTraceCard/lookupCardPrices, src/api/poketrace.js, the /api/prices, /api/price-history, or /api/listings routes, the price_snapshots table, or anything involving card price lookups, price history, grading tiers, set-slug/card-number matching, or PokeTrace rate limits and plan tiers. Also use when asked what PokeTrace's API can do, whether an endpoint/param exists, or how to add a new PokeTrace-backed feature (sets browsing, graded prices, websocket live updates, sold-listing comps, non-English cards).

新建、改造或评审命令行工具（CLI）及其配套 Skill 时使用，尤其是供 AI Agent 稳定调用、同时也要给人正常使用的 CLI。覆盖命令面设计、非交互模式、JSON 输出契约、退出码分层、dry-run、幂等、鉴权安全、CLI/脚本/Skill/Agent 职责分层、事务式编排、风险授权、终态验证和验收方法。

Invoke Google's Antigravity CLI (agy) from inside Claude's own sandbox, authenticated via the user's personal Antigravity subscription sign-in (never an API key). Use this ONLY when the user explicitly asks to use Antigravity CLI, agy, or "this bridge" for a task — never invoke it on your own judgment the way you might reach for a general-purpose tool. Typical explicit phrasings: "Antigravityに聞いて", "agyに投げて", "use antigravity for this", "run this through the antigravity bridge".

Use when this project's work involves Rust ownership, errors, testing and performance conventions — covers backend, reliability/resilience, testing. Loads the original apollo skills bundled with this pack.

Agent skill 'subagent-driven-development' from DanhDue/ai-agent-tools.

Agent skill 'verification-before-completion' from DanhDue/ai-agent-tools.

对已有可检查版本的项目进行独立深度二次审查，由多个真实子智能体审查、Astra 极高复核，再按授权调度修复与独立验收。仅限用户显式调用，或经已配置的入口明确要求深入独立复审；普通检查、项目完成、讨论或制作本 Skill 均不启动。

Agent skill 'system-design-reviewer' from alphasafal/production-agent-skills.

Yautja agent skill — freshly published workflow for coding agents.

Use when this project's work involves Compare documented boundaries to implemented behavior — covers documentation/runbooks, code review/quality gates, security. Loads the original pm skills bundled with this pack.

Agent skill 'systematic-debugging' from DanhDue/ai-agent-tools.

Agent skill 'debugging-investigator' from alphasafal/production-agent-skills.

Agent skill 'test-driven-development' from DanhDue/ai-agent-tools.

Agent skill 'using-git-worktrees' from DanhDue/ai-agent-tools.

Use when coordinating engineering work in this project: selecting which original upstream skill to follow for discovery, architecture, frontend, backend, data, infrastructure, testing, security, release or operations work, and resolving its original file paths and tools.

Agent skill 'repo-architect' from alphasafal/production-agent-skills.

Use when this project's work involves Original agent skill evaluation and MCP server engineering specialists — covers testing, api contracts. Loads the original anthropic skills bundled with this pack.