218 skills
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchm…
ASSISTANT RULES
Project: Fine-Tuning Pre-trained ResNet50 for Custom Image Classification
Use this skill when the user wants questions where the docs look relevant but still do not contain the answer. Trigger it for requests like 'make the model say it can't tell', 'give me questions with not enough information', 'test whether it refuses instead of guessing', or 'include related documen…
Consult a multi LLM council for deliberation, debate, voting, critique, or verification. Uses GPT 5.4, Gemini 2.5, and Claude as peers.
LLM Skill (Integrated, RAG‑First)
- History เก็บฝั่ง client (Next.js session) ส่งมาใน request - ChromaDB + SQLite persistent บน disk — ต้อง mount volume ถ้าใช้ Docker - Ingest ทำครั้งเดียวโดยเจ้าของ ไม่มี upload UI
This skill lets the agent inspect local project documentation, parameters, run summaries, and generated output artifacts through bounded, read-only tools. It is intentionally lightweight and does not require LlamaIndex for basic operation.