SOC 직업 분류 기준
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/yanacuti1121/Yana-AI --skill supermemory명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
Sovereign-grade safety OS for AI coding agents. 62 hooks, 2,025 skills, L1 memory, circuit breakers, and cross-engine enforcement — blocks rm -rf, force push, pipe-to-shell, and 40+ attack vectors before they reach your repo.
Use when the user wants to generate or keep repository documentation up to date via OpenWiki (langchain-ai/openwiki) — an LLM-driven CLI that writes a wiki for a codebase (or a personal knowledge base from Notion/Gmail/Slack/X/web search) and keeps it fresh via a scheduled CI pull request. Examples: "set up OpenWiki for this repo", "keep the docs updated automatically", "generate an agent wiki".
Use when implementing the core AR pipeline (camera pose estimation, marker tracking, projection overlay) from first principles — not when just using ARKit/ARCore/Unity's AR framework as a black box. Triggers on: 'build augmented reality from scratch', 'marker-based AR tracking', 'camera pose estimation', 'implement fiducial marker detection', 'AR projection matrix math', 'markerless AR tracking'. Covers marker-based vs markerless tracking, pose estimation, and the projection math to overlay 3D content on a camera feed.
| name | supermemory |
| description | Persistent memory + RAG + User Profile cho AI agents. |
| triggers | ["supermemory","persistent memory","nhớ qua session","AI memory","long-term memory","user profile AI","RAG search","tìm kiếm ngữ nghĩa","agent memory"] |
Source: github.com/supermemoryai/supermemory ⭐24k
API: api.supermemory.ai
MCP: mcp.supermemory.ai/mcp
Benchmark: #1 LongMemEval · LoCoMo · ConvoMem
# Thêm MCP server vào Claude Code
npx -y install-mcp@latest https://mcp.supermemory.ai/mcp --client claude --oauth=yes
Hoặc thêm thủ công vào ~/.claude/settings.json:
{
"mcpServers": {
"supermemory": {
"url": "https://mcp.supermemory.ai/mcp",
"headers": {
"Authorization": "Bearer sm_YOUR_API_KEY"
}
}
}
}
Lấy API key: app.supermemory.ai
from supermemory import Supermemory
client = Supermemory(api_key=os.environ["SUPERMEMORY_API_KEY"])
# Lưu memory sau mỗi conversation
client.add(
content="Anh Tâm thích Rust hơn Java, đang dùng Cloud Shell",
container_tag="tam_profile",
metadata={"type": "preference", "date": "2026-06-03"}
)
# Tìm context liên quan
context = client.profile(
container_tag="tam_profile",
query="thói quen làm việc"
)
print(context.profile) # user profile tự generate
print(context.memories) # relevant memories
# Upload tài liệu
client.add(content=open("guide.md").read(), container_tag="yamtam_docs")
# Search hybrid (semantic + keyword)
results = client.search(query="cách cài headroom", container_tag="yamtam_docs")
for r in results.results:
print(r.content[:200])
# Profile tự build từ memories, cập nhật liên tục
profile = client.profile(container_tag="tam_profile")
# → stable facts + recent activity combined
| YAMTAM hiện tại | Supermemory thay thế |
|---|---|
core/scripts/add-fact.sh | client.add(content, container_tag) |
| L1 INDEX.md manual | client.profile() tự generate |
| grep search trong .md files | client.search() semantic |
| Session context bị mất | Persistent across sessions |
# Kết nối Google Drive → tự sync
client.connectors.create(type="google_drive", credentials=...)
# GitHub repo sync
client.connectors.create(type="github", repo="yana-ai")
Supported: Google Drive · Gmail · Notion · OneDrive · GitHub
pip install supermemory # Python
npm install supermemory # TypeScript/Node
memory/ manual markdown files