rag-experiment

Run one controlled RAG experiment (chunking, embeddings, top-k, rerank, threshold, prompt or LLM) and save config, raw results, metrics and run IDs. Use when testing a hypothesis from docs/RESEARCH_PL

SKILL.md

GitHub

Read and follow the shared methodology in .agents/skills/rag-experiment/SKILL.md (repository root). It is the single source of truth; this file is only the Claude Code adapter.

Claude Code specifics: run commands from lab1/ with uv run; respect AGENTS.md limits (at most two concurrent subagents, writing agents in separate git worktrees).

Похожие навыки: agents

agent-memory-yamadashy-repomix

Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save t...

Автор: yamadashy
21,427

openai-whisper-api

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Автор: clawdbot
7,675

video-frames

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Автор: clawdbot
7,675