agentleFS
fortunto2fortunto2/solo-factory/skills/knowledge/SKILL.md

solo-knowledge

Skill18 starsChanged 4 months agoMITView on GitHub

Use when needing methodology reference, asking about principles, harness engineering, SGR, launch playbook, agent memory, decision frameworks, or any topic covered in the solopreneur knowledge base. Use when user says "what do we know about X", "how does our methodology handle X", "what does the playbook say", "remind me of the principle".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All content indexed in llms.txt — a machine-readable map with titles, URLs, and descriptions.

    line 29
  2. Distinctive:

    If empty: show available topics from the index

    line 36
  3. Distinctive:

    If topic: find matching pages by keyword in titles/descriptions

    line 37
  4. Distinctive:

    If the answer contradicts or extends existing knowledge, note that

    line 52
  5. Distinctive:

    If WebFetch is unavailable, the skill falls back to:

    line 74

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/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

  1. Load index — fetch https://rustman.org/llms.txt via WebFetch (or read from references/llms-snapshot.txt if offline)
  2. Parse question from $ARGUMENTS:
    • If empty: show available topics from the index
    • If topic: find matching pages by keyword in titles/descriptions
  3. 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
  4. 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
  5. 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:

  1. Local wiki files: Grep "topic" wiki/ + Read wiki/{match}.md
  2. 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

DomainKey PagesDepth
PhilosophyManifesto, STREAM framework, antifragile designDeep
LaunchLaunch playbook, SEED scoring, kill/iterate/scaleDeep
EngineeringSGR, dev principles, CLI-first, privacy architectureDeep
AI AgentsHarness engineering, agent memory, context graphs, RAG patternsVery deep
ToolsAgent toolkit landscape, benchmarks, LLM providersCatalog
Projects12 open source projects with case studiesMedium
Skills30 solo-factory skills with full documentationReference

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.