Four-layer AI detection evasion, not word swapping. Real math (burstiness CV, vocabulary density) — no guessing. Detector-specific: attacks GPTZero, Originality, Turnitin by their weakest links. Chinese NLP: tracks 四字成语密度, a blue ocean. 105+ AI markers with genre-aware replacements. Research-backed (27 reports, 25+ papers). Honest: 75-85% typical improvement, no fake 100% claims.
Claude Codeのサブエージェント設計を多数手がけ、よくある暴走パターン（全権限継承・責任の詰め込み・曖昧な発動条件）の修正ノウハウを体系化。このSkillはその実践知識を、再現可能な設計フローとして提供します。
此Skill整合了APP製作的角色權限控管、智慧財務自動結算、動態資源預約排程、系統級通知功能、分工遊戲化模組等等 本 Agent 專長於： 執行階層化權限管理（EX：房長/財務/成員）。 自動化記帳與私密催繳通知。 即時資源調度與過期自動清理。 提供溫馨、簡潔的 AI 生活助理服務。 無論是共居空間、工作室或宿舍，透過 CollabSpaceOS 皆可快速部署具備高安全性與生活溫度感的專屬 App。 匯入此技能包，讓您的 AI 瞬間進化為精通 React + Firebase 的資深架構師！本 Skill 內建『蒐集代幣的遊戲化任務』、『智慧財務記帳』與『PWA 系統推播』等高度模組化的領域知識。 您的專屬 AI 將為您精準產出高品質代碼，完美處理『跨時區同步』與『防資料流失』等高階邏輯。從架構整合、客製化微調到進階 Debug，為接案者與開發者省下破百小時的摸索期。獲取神級框架，極速部署您的專案！」
Forces AI agents to identify independent judgment axes before answering any complex question — decomposing the problem into minimum separable sub-problems, solving each one independently, then integrating into a single conclusion so complex analysis is auditable, correctable, and never a blur of mixed reasoning.
This Skill is built on practical expertise in long-running AI workflow control, constraint tracking, handoff reliability, completion evidence, and instruction-change recovery. It helps agents keep the user's first, middle, and latest requirements aligned across multi-step work so older assumptions do not override newer directions and completion is backed by observable evidence.
A premium cross-domain design systems engineering skill for AI agents, now with design context engineering: choose where design context lives, author DESIGN.md and design.md, structure design knowledge as OKF v0.2 bundles, drive anti-slop creative direction, and verify with an eval harness. Covers UI and UX, TUIs, accessibility, motion, dashboards, publishing, marketing collateral, game and film interfaces, HUDs, design-to-code, and 2D, 3D, CAD, CAM, AR, VR, XR, and print handoffs.
Structure project docs as modular memory + reasoning files so AI agents load only what they need — cutting token usage by 70–96% per query. Grounded in Anthropic, LangChain, and Crawl4AI's production llm.txt research. Implements write/select/compress/isolate context engineering strategies.
This Skill is built on practical expertise in AI agent safety, prompt-injection defense, source-to-sink privacy review, tool and MCP metadata integrity, memory provenance checks, autonomous action scoping, and evidence-based verification. It helps agents separate instructions from evidence before tool calls, uploads, publishing, deletion, code execution, or network output.
This agent helps Python teams using the Anthropic or OpenAI SDK safely cut LLM spend without risking regressions. With zero code changes, it maps call sites and runs your test scenarios to rank token waste from missed prompt caching or heavy model tiers. It tests fixes in isolated git worktrees, enforcing a strict "do-no-harm" gate that reverts any patch failing to preserve behavior. It delivers a clear savings audit that converts into verified, behavior-preserving code patches upon opt-in.