// Use when the user invokes /update-tutorial, or when a verification-related Q&A exchange has just completed in the session and should be persisted into docs/tutorial/ as narrative-style content. Classifies by topic, finds the right file, inserts above the SECTION_MARKER, and updates the README index.
Use when planning, submitting, or debugging LLM-DNA fingerprint extraction jobs on SageMaker spot training. Trigger on keywords like "LLM-DNA jobs", "calc-dna", "submit_dna.py", "SageMaker spot", "Solar / K-EXAONE / A.X-K1 / EXAONE 추출", "Phase 5/6 재시도", "model fingerprint extraction", or follow-up verification rounds. Codifies 9 cost/operational lessons from Phase 4–6 of korea-ai-foundation-model-verification (2026-04-30, $64 / 77 jobs, 52.8% waste rate) so future rounds avoid the same learning curve.
Use when working on LLM model lineage, provenance, phylogenetic analysis, from-scratch verification, the project's verification targets (Solar-Open-100B, K-EXAONE, A.X-K1, HyperCLOVAX), reference families (Llama 3, Qwen 2.5, GLM, Mixtral, DeepSeek), or anything under experiments/llm-dna/. Routes through the project wiki/ before external search.
Use when writing, reviewing, or refactoring code in this repo to reduce common LLM coding mistakes — overcomplication, drive-by edits to unrelated lines, hidden assumptions, vague success criteria. Four principles: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
Use when the user invokes /update-changelog, or when a session has produced concrete repository changes (file edits, verification results, methodology updates, structural changes) that should be recorded in CHANGELOG.md by date and category.
| name | update-tutorial |
| description | Use when the user invokes /update-tutorial, or when a verification-related Q&A exchange has just completed in the session and should be persisted into docs/tutorial/ as narrative-style content. Classifies by topic, finds the right file, inserts above the SECTION_MARKER, and updates the README index. |
Append the session's Q&A to docs/tutorial/ in narrative prose (not bullet/table dumps). The tutorial is a chronological learning log; future readers should be able to read it as a story, not a report.
/update-tutorialSkip for project-operational questions ("어떤 파일이 어디 있어?"), Claude usage questions, or yes/no confirmations.
docs/tutorial/README.md to find the next Q-number (highest existing + 1, shared across files).<!-- SECTION_MARKER -->, insert the new Q&A above the marker.docs/tutorial/README.md.| Topic keywords | Target file |
|---|---|
| from-scratch concept, verification overview, controversy background | 01-기초개념.md |
| Tokenizer, vocabulary, vocab_size, BPE, merge rules, special tokens | 02-tokenizer-분석.md |
| Weight, cosine similarity, architecture, MoE, layer, expert | 03-weight-architecture-분석.md |
| Specific model verification result, Solar/HyperCLOVAX/A.X-K1 cases | 04-사례연구.md |
| Methodology critique, academic research, improvement direction | 05-방법론-평가.md |
If none fit: create docs/tutorial/0N-새주제.md with a <!-- SECTION_MARKER --> line at the bottom, add the README section, and update this skill's table.
---
## Q{N}: {질문 요약}
**질문 시각**: {YYYY-MM-DD}
**답변**:
{narrative prose — see references/narrative-style.md}
---
Required: write answers as connected prose that walks the reader through the discovery. Bullets and tables are a supporting tool, not the primary form.
See references/narrative-style.md for full examples and authoring tips.
SECTION_MARKER instead of above — breaks future appendsdocs/tutorial/README.md index — orphan entry