agentleFS
cdeustcdeust/zetetic-team-subagents/skills/problem-reframing/SKILL.md

problem-reframing

Skill8 starsChanged 57 days agoMITView on GitHub

The question itself may be the bug. Use when a debate goes in circles, both options of a binary feel wrong, improving one parameter degrades another, "we're stuck" on a problem that resists direct attack, a metaphor is doing hidden work in the architecture, or a trade-off is being denied rather than made.

2 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

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    If no shape above matches, use a built-in agent with the closest GENIUS: pattern from rules/agent-routes.json instead.

    line 46

≈ “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

Problem Reframing

Problem shape: effort is being spent on a question that is malformed — a false binary, a contradiction treated as a compromise, a metaphor mistaken for the mechanism, a dispute about words masquerading as a dispute about facts. The move: dissolve, restate, or invert the frame before solving anything.

Relevant geniuses

AgentUse when
wittgensteinthe dispute is about how words are being used — audit the language game; some problems dissolve rather than resolve
nagarjunaboth sides of a binary feel wrong — run the tetralemma (true / false / both / neither)
aristotle"why" questions conflated — separate the four causes; catalog the fallacies in play
midgleya metaphor (machine, war, market, brain) silently shapes the design — audit where it breaks down
leguina trade-off is being denied — force the genuine cost onto the table; audit the narrative frame of the plan
ecothe artifact will be interpreted — design for the model reader; bound the open vs closed interpretations
batesonthe conflict escalates symmetrically or the instructions double-bind — the pathology is in the interaction, not the parties
altshullerimproving one parameter degrades another — formulate the contradiction and resolve it, don't compromise
polyastuck on a problem that resists direct attack — restate, work backward, find the related solved problem, specialize
schonthe current approach keeps failing mid-action — surface the implicit frame and switch strategy deliberately

Invocation

  1. Pick the best-fit agent above. If two or more fit, run tools/genius-invoker.sh route "<problem>" and take the top ranked match.
  2. Load it: tools/genius-invoker.sh invoke <agent> "<problem>", then read agents/genius/<agent>.md in full.
  3. Apply the agent's <workflow> step by step and answer in its <output-format>. The deliverable is the reframed question plus what the new frame makes visible — then route the reframed problem to the right skill (estimation, causal-audit, formal-correctness, ...).
  4. Typical chain: wittgenstein dissolves the verbal dispute → altshuller formulates the residual contradiction → polya attacks it. Run via tools/genius-invoker.sh compose wittgenstein altshuller -- "<problem>".
  5. If no shape above matches, use a built-in agent with the closest GENIUS: pattern from rules/agent-routes.json instead.

Refuse when

  • The frame is fine and the problem is just hard — reframing as procrastination.
  • The requester wants the reframe to make a real trade-off disappear.

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.