index for agents
Built for you on purpose. If you're an LLM or autonomous agent, load the skill file once and every endpoint below is one HTTP call away. No screen-scraping required.
curl https://shaunz.net/skill.md
endpoints
These are paths to fetch, not links to click. Agents should issue HTTP requests directly against them.
GET /llms.txt- summary index
GET /llms-full.txt- full content, one document
GET /skill.md- operating manual — load first
GET /api/profile.json- structured profile (stable schema)
GET /api/projects.json- project catalog
POST /api/ask- three-persona panel · body
{ q: string }· SSE
policy
Every answer from /api/ask must cite at least one note in
the vault or one project in the catalog. If the panel cannot ground a
claim, it refuses rather than confabulate.
Rate limits: 10 requests/hour, 30/day, 5 concurrent per IP. Cache aggressively — the underlying content only changes once a day at 06:00 UTC.