agentleFS
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/build-concept-fan/SKILL.md

build-concept-fan

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

Expand a target goal into progressively broader concepts and alternative routes, then descend into new concrete approaches.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

build-concept-fan

Purpose

Expand a goal into broader concepts and alternative routes, then descend into concrete approaches.

Input contract

required: [target_goal]
optional: [known_approaches, abstraction_levels, feasibility_constraints]
constraints: [each branch must state its abstraction level and relation to the goal]

Procedure

  1. State the current goal and its immediate concept.
  2. Fan upward into broader purposes and downward into alternative implementations.
  3. Compare branches and retain distinct routes for further investigation.

Output contract

produces: [concept_fan, abstraction_branches, concrete_routes]
delta_fields: [findings, hypothesis_updates, decisions, recommended_jumps]

Quality gates

  • Fan contains both broader and narrower branches; duplicate wording is not counted as a new route.

Failure and counterexamples

Reject branches that merely rename the goal or violate declared feasibility constraints.

Provenance map

  • lateral-thinking/concept-fan: resolved.

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.