agentleFS
Sign inStart free
r-irber-irbe/proof-skills/skills/epistemic-discovery-engine/SKILL.md

epistemic-discovery-engine

Skill3 starsChanged 25 days agoApache-2.0View on GitHub

USE FOR: epistemic discovery: picking a discovery mode (Census / Dependency / Literature / Cross-domain / Community). DO NOT USE FOR: a known research question (@lean-research). TRIGGERS: discovery, unknown unknown, UU hunt, epistemic discovery, census.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    Run the UU hunting protocol at the chosen depth (handbook Part 2).

    line 43
  2. Very specific:

    STOP if the suspected unknown turns out to be a known-unknown after probe — re-classify and delegate to @lean-research.

    line 50
  3. Distinctive:

    STOP if 3+ consecutive sessions in the same mode produce overlapping leads — switch mode per handbook Part 5.

    line 52
  4. Distinctive:

    STOP if project relevance score (handbook Part 6) falls below threshold — close the discovery and document the negative result.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Epistemic Discovery Engine — Active UU Hunting

The Discovery Engine is the operational arm of epistemic-mapping. Where epistemic-mapping defines quadrants, scores, and transitions, the Discovery

Routing

  • USE FOR / DO NOT USE FOR / TRIGGERS — see the description field in the YAML frontmatter above. Same dispatch contract is restated here for in-skill discovery.
  • USE FOR: epistemic discovery — picking a discovery mode (Census / Dependency / Literature / Cross-domain / Community), running an Unknown-Unknown (UU) hunting protocol at the right depth (Shallow / Standard / Deep / Exhaustive), emitting census + probe + trigger reports, anti-stagnation mechanisms, project relevance scoring.
  • DO NOT USE FOR: a known research question (use @lean-research); council convocation on a known artifact (use @lean-review-council or

Workflow

  1. Pick the discovery mode (handbook Part 1) that matches the suspected blind spot.
  2. Run the UU hunting protocol at the chosen depth (handbook Part 2).
  3. Emit the corresponding report (handbook Part 3 — Census / Probe / Trigger templates).
  4. Hand off promising leads to @research-council (deep) or @lean-research (single-question) per handbook Part 4.
  5. Apply anti-stagnation mechanisms (handbook Part 5) when consecutive discovery sessions produce overlapping leads.

Recovery & STOP

  • STOP if the suspected unknown turns out to be a known-unknown after probe — re-classify and delegate to @lean-research.
  • STOP if 3+ consecutive sessions in the same mode produce overlapping leads — switch mode per handbook Part 5.
  • STOP if project relevance score (handbook Part 6) falls below threshold — close the discovery and document the negative result.

Handoffs

  • Predecessors: agent:gateway, skill:research-council, skill:lean-research.
  • Successors: skill:research-council, skill:research-synthesis-engine, skill:lean-zettelkasten.

Detailed reference

Full encyclopedic reference, decision trees, and lookup tables live in references/epistemic-discovery-engine-handbook.md .

See also

  • ../../references/epistemic-discovery-engine-handbook.md -- Complete epistemic-discovery-engine Handbook
  • ../lean-gateway/SKILL.md -- Top-level skill router

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.

Check your setup, free