solo-knowledge
/knowledge
Answer questions using the solopreneur knowledge base. Loads the site index via llms.txt, finds relevant pages, fetches and synthesizes answers.
Source: rustman.org/llms.txt — full index of all published content.
How It Works
The knowledge base is a static site (rustman.org) with 60+ pages organized as:
- Posts — pillar articles (manifesto, STREAM framework, harness engineering, agent memory, context graphs, launch playbook)
- Wiki — compiled knowledge pages (concepts, summaries, catalogs)
- Projects — build-in-public case studies
- Skills — solo-factory executable skills documentation
- Stacks — technology stack templates
All content indexed in llms.txt — a machine-readable map with titles, URLs, and descriptions.
Steps
-
Load index — fetch
https://rustman.org/llms.txtvia WebFetch (or read fromreferences/llms-snapshot.txtif offline) -
Parse question from
$ARGUMENTS:- If empty: show available topics from the index
- If topic: find matching pages by keyword in titles/descriptions
-
Fetch relevant pages — for each match (max 3), fetch the full page:
WebFetch https://rustman.org/wiki/{slug}Or read locally if in solopreneur repo:
Read wiki/{slug}.md -
Synthesize answer — combine information from fetched pages:
- Answer the question directly
- Cite sources with links
- Note related pages for deeper reading
- If the answer contradicts or extends existing knowledge, note that
-
Suggest follow-up — based on wikilinks in the fetched pages, suggest related topics.
Usage Examples
/knowledge "how does harness engineering work?"
→ Fetches harness-engineering post + wiki summary, synthesizes key concepts
/knowledge "what's our approach to agent memory?"
→ Fetches agent-memory-architecture post + mempalace page, compares approaches
/knowledge "what stacks do we support?"
→ Lists all 9 stack templates with tech details
/knowledge "how to validate a startup idea?"
→ Fetches launch-playbook + SEED scoring + validation hub
Offline Mode
If WebFetch is unavailable, the skill falls back to:
- Local wiki files:
Grep "topic" wiki/+Read wiki/{match}.md - Snapshot in
references/llms-snapshot.txt
Key References
references/llms-snapshot.txt— cached copy of llms.txt (update with:curl -s https://rustman.org/llms.txt > references/llms-snapshot.txt)
Content Domains
| Domain | Key Pages | Depth |
|---|---|---|
| Philosophy | Manifesto, STREAM framework, antifragile design | Deep |
| Launch | Launch playbook, SEED scoring, kill/iterate/scale | Deep |
| Engineering | SGR, dev principles, CLI-first, privacy architecture | Deep |
| AI Agents | Harness engineering, agent memory, context graphs, RAG patterns | Very deep |
| Tools | Agent toolkit landscape, benchmarks, LLM providers | Catalog |
| Projects | 12 open source projects with case studies | Medium |
| Skills | 30 solo-factory skills with full documentation | Reference |
More from fortunto2/solo-factory
solo-research
Use when "research this idea", "find competitors", "check the market", "domain availability", "market size", "analyze opportunity", or need evidence before validation. Do NOT use for idea scoring (/validate) or SEO auditing (/seo-audit).
43solo-swarm
Use when "swarm research", "parallel research", "investigate fast", "3 agents", "team research", or want faster multi-angle alternative to /research. Do NOT use for solo research (/research) or idea scoring (/validate).
34solo-build
Use when "build it", "start building", "execute plan", "implement tasks", "ship it", track ID referenced, or plan tasks need execution. Do NOT use for planning (/plan) or scaffolding (/scaffold).
33solo-humanize
Use when "humanize this", "make it sound human", "strip AI patterns", "clean up the copy", or text reads like AI-generated output with em dashes and stock phrases.
33solo-audit
Use when "audit KB", "check frontmatter", "find broken links", "tag cleanup", "knowledge base quality", or docs need health check. Do NOT use for SEO audits (/seo-audit) or code reviews (/review).
31solo-scaffold
Use when "scaffold project", "create new project", "start new app", "bootstrap project", "set up from PRD", or need project from PRD + stack template. Do NOT use for planning features (/plan) or PRD generation (/validate).
30