Multi-agent Memory + Identity
Multi-agent Memory + Identity — 同步/污染/信箱身分 When to use - CLAUDE.md / rules diverge across Cursor, Claude, Codex, etc. - Shared memory risks cross-cont...
Multi-agent Memory + Identity — 同步/污染/信箱身分 When to use - CLAUDE.md / rules diverge across Cursor, Claude, Codex, etc. - Shared memory risks cross-cont...
Agent SoT + Verification Gates — 勿信 done When to use - Agents say “done” while tests were weakened, staging breaks, or “only change Y” was ignored. - ...
Long-run Rule Persistence — 長任務規則怎麼不飄 When to use - CLAUDE.md / project rules are followed early, then ignored around turn 5+ on open-ended work. - Wi...
ADHD External Structure — body doubling/時間盲外化 Non-medical: This skill is about product/workflow design for task start and time externalization. It doe...
LLM Usage Burn Guard — 額度秒燒/失敗仍扣費 When to use - Credits vanish in minutes across Codex / Claude / ChatGPT / other agents. - Failed or empty responses ...
Agent Memory Portability — 換 agent 要帶什麼 When to use - Long debug / multi-hour coding; you will switch Claude ↔ Cursor ↔ Codex mid-task. - Bigger conte...
手機端 Coding Agent Companion — 需求/架構卡 When to use - Operator is away; coding agent runs on a trusted laptop/box. - You want ChatGPT/Claude-app-like remo...
Multi-model Coding Agent Harness — 選型與設計卡 When to use - You want Claude Code / Codex / Cursor-class UX but must swap models without rewriting the work...