agentleFS
IamK77IamK77/Skill/skills/inquiry/crucible/SKILL.md

crucible

Skill2 starsChanged 32 days agoApache-2.0View on GitHub

Invent and reshape research mechanisms through analogy, inversion, and recombination. Use while the idea is unsettled; no mandatory tournament, novelty certificate, or convergence.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If a method assumes perfect information, abundant compute, or stationary data, imagine the opposite.

    line 32
  2. Distinctive:

    If an idea is chosen for a test, ledger specifies the comparison.

    line 46
  3. Distinctive:

    Read selectively when a thread needs another perspective or a concrete technique.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “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
<!-- Copyright 2026 IamK77 — Licensed under the Apache License, Version 2.0. See ./LICENSE and ./NOTICE · https://www.apache.org/licenses/LICENSE-2.0 -->

crucible

Invent and reshape research mechanisms through analogy, inversion, and recombination. Use while the idea is unsettled; no mandatory tournament, novelty certificate, or convergence.

Starting point

A mechanism is a story about how one change could produce another. Keep several incompatible stories alive long enough to learn what each lets you notice.

Bring a question, fragment, reference, or tension. Follow whichever association becomes useful; these invitations are not a sequence to complete. Speculation should remain distinguishable from an observed fact.

Thought experiments

Transfer a mechanism, not its costume

Borrow feedback, competition, memory, or conservation from another domain. Name the relation being transferred and where the analogy would break.

Invert the expensive assumption

If a method assumes perfect information, abundant compute, or stationary data, imagine the opposite. Does the objective change, or can the mechanism exploit the apparent weakness?

Recombine at the seam

Take the representation of one idea and the update rule of another. Sketch the simplest interesting case before adding machinery. A deliberately awkward hybrid can reveal a third option.

A possible turn

A search procedure repeatedly restarts after failure. A memory analogy suggests retaining forbidden regions; a market analogy suggests reallocating effort by opportunity cost; a developmental analogy suggests changing the representation over time. The aim is distinct causal stories, not renamed parameter settings.

Leave the space open

Offer a few genuinely different possibilities, a sketch, an analogy, or a sharper question when useful. Do not turn every prompt into a scored diagnostic, a completion gate, or a demand for an action plan. The human may choose a direction, combine them, or leave the question open.

If an idea is chosen for a test, ledger specifies the comparison; forge executes it. A speculative diagram or an unanswered mechanism question is also a legitimate stopping point.

Optional references

Read selectively when a thread needs another perspective or a concrete technique. The notes supply possibilities, examples, and limits; none is a prerequisite or a requirement to close the exploration.

  • Removing pieces to discover what an idea means
  • A mechanism sketch and its possible limits
  • Theory as a source of mechanisms and questions
  • Variants as different causal stories

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.