karpathy-wiki-ingest
karpathy-wiki ingest (for spawned ingester only)
You are a detached claude -p ingester invoked by
wiki-spawn-ingester.sh. Your job: process one already-claimed
capture into wiki pages and commit. The main agent does NOT read this
skill — it's loaded by your spawn prompt.
Deep orientation
Before any wiki write, run this 9-step orientation protocol. The goal: your view of the wiki is shaped by the actual page content, not by titles alone.
Steps 1-3: read the wiki's current state
- Read
<wiki>/schema.md— current categories, taxonomy, thresholds. - Read
<wiki>/index.md(or<wiki>/<category>/_index.mdper category) — what pages exist with one-line summaries. - Read the last ~10 entries of
<wiki>/log.md— recent activity.
More from toolboxmd/karpathy-wiki
karpathy-wiki
|
8karpathy-project-wiki
Build and maintain a persistent Karpathy Project Wiki — an auto-updating knowledge base for your codebase based on Andrej Karpathy's LLM Wiki pattern. TRIGGER when: user modifies project files (code, configs, docs), adds new modules, refactors architecture, merges PRs, asks about project architecture ('how does auth work', 'what's the data flow', 'where is X implemented', 'explain this module', 'what patterns does this project use'), or requests a documentation health check ('is the wiki up to date', 'check the docs', 'find undocumented code'). Also triggers when git shows changes since last wiki update. DO NOT TRIGGER when: user wants a general research wiki on external topics (use karpathy-wiki instead), asks to read a single specific file, or asks general programming questions unrelated to this project.
3karpathy-wiki-read
|
2karpathy-wiki-capture
|
2using-karpathy-wiki
|
2