treylom

vault 통합 검색 — GraphRAG(있으면) → Obsidian CLI → (Obsidian MCP) → 텍스트 검색 4단계 자동 폴백. quick(즉답)/deep(분석) 자동 라우팅

Unified storage interface for Obsidian, Notion, and local file systems

6-phase workflow for content extraction, analysis, and export to Obsidian/Notion

Content extraction routing for KM - local documents (HWP/HWPX/PDF/DOCX/XLSX), web, and vault sources. Use when input is a local file or when km-workflow reaches Phase 2 with a non-URL input.

Unified browser interface for Antigravity native, Playwright, and Hyperbrowser providers

Output format specifications for Obsidian, Notion, and Markdown exports

Automated setup wizard for Knowledge Manager - configures MCP servers and creates config files

Extract content from Threads, Instagram with reply collection and depth control

Use when needing Google Gems 프롬프트 생성기. Gems 페르소나용 시스템 프롬프트 자동 생성.

Use when composing prompts targeting GPT-5.6 Sol (GPT 디폴트) or legacy GPT-5.5/5.4/5.2 — lean outcome-first 7블록 규칙 + LEGACY 섹션(구 XML 스택)을 담은 GPT 프롬프트 전략 레퍼런스의 라우팅 인덱스. 본문 = references/full.md.

Use when generating research/factcheck/image/video/slide prompts that need base templates (IFCN·StructuredResearch 등) — 단일 통합 AI 프롬프트 엔지니어링 레퍼런스의 라우팅 인덱스. 본문 전체는 references/full.md(대형 파일 — grep으로 위치 확인 후 부분 Read).

Use when the user asks to create, refine, or optimize a prompt ('프롬프트 만들어/생성해/다듬어') — AI 프롬프트 생성기. 사용자의 아이디어를 모델별(Claude/GPT/Gemini/이미지) 최적화 프롬프트로 변환. Codex 포트 — Claude Code의 /prompt 명령과 동일 절차.

Use when composing factcheck or research prompts — IFCN 원칙 기반 검증 워크플로우와 일반 리서치 템플릿을 담은 레퍼런스의 라우팅 인덱스. 본문 = references/full.md.

Use when the user explicitly targets Claude Opus 4.7 or earlier (구세대 first-class 지원) — legacy Claude 프롬프트 전략 레퍼런스의 라우팅 인덱스. 최신 모델(Opus 5·Fable 5·4.8·Sonnet 5)은 claude-fable-5-prompt-strategies.md가 정본. 본문 = references/full.md.

Use when a prompt needs an expert role assignment — 실존 전문가 지명과 전문 용어로 AI의 잠재 공간을 활성화하는 전문가 도메인 프라이밍 방법론 레퍼런스(/prompt 전문가 프롬프팅 대원칙의 근거 자료)의 라우팅 인덱스. 본문 = references/full.md.

Use when composing or optimizing prompts targeting Google Gemini models (Gemini 3 Pro/Flash, 3.1) — Google 공식 문서 + 실전 팁 기반 Gemini 프롬프트 전략 레퍼런스의 라우팅 인덱스. 본문 = references/full.md.

Use when someone asks what this harness offers, what is already installed, what a particular skill or gate does, or where to start — "what can this do", "harness help", "뭐가 설치돼 있어?", "어떻게 시작해?". Reports the live install state measured from the machine, not a…

Use when someone wants the whole harness stood up in one pass — "set up the harness", "install everything", "한 번에 설치해줘" — including the companion plugins it works best with (conversation memory, structured brainstorming, knowledge capture). Installs in…

Use when someone asks to install this bundle's verification hooks into a project — "install the project hooks", "set up the gates here", "프로젝트 관련 훅 설치해줘". Picks the hooks that fit the harness and the project, wires them into settings, and then proves each one…

Use when auditing an AI-agent harness (CLAUDE.md / AGENTS.md / SKILL.md / rules files) for drift — dead links, stale model names, tool mismatches, and cross-document conflicts — then repairing only independently verified findings. Deadline-bounded,…

Use at the start of any non-trivial task (build / fix / analyze / deliver) to run it under the tofable working discipline — honest decomposition, prompt refinement via /prompt when installed (basic-prompting fallback when not), evidence-first execution, and…

Use when needing Agent Teams 역할별 스폰 프롬프트 템플릿 + 도구 할당 + /prompt CE 통합. /tofu-at가 팀원 스폰 시 참조.

Use when a research question needs sourced, cross-checked findings — fact-checks, market/company/tech/policy research, comparisons, or open exploration. Routes the question to a research type, spawns per-frame investigators, grades sources, and…