Menü
Applies Munger / Jacobi inversion on a problem statement. Trigger= /dillylang-invert PROBLEM
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Trigger: /compress-file FILEPATH or "compress <file>"
Maps problem structure to other domains, importing mechanism not metaphor. Trigger= /dillylang-analogize PROBLEM
Promotes exploratory prose into canonical docs through a conservative 5-stage gate — extract, route, judge, rank, synthesize. Model C recipe with operator-confirmed routing. Trigger= /dillylang-canonize PROSE
Decomposes a problem into axioms, derivations, and assumptions. Trigger= /dillylang-decompose PROBLEM
Judges an artifact against an explicit criterion. Trigger= /dillylang-evaluate CRITERION ARTIFACT
Execute Dillylang recipes with visible step-by-step traces and intermediate artifacts. Use when the user wants to run, apply, or execute any named Dillylang recipe on a problem — including informal phrasing like using a recipe name as a verb.
| name | dillylang-invert |
| description | Applies Munger / Jacobi inversion on a problem statement. Trigger= /dillylang-invert PROBLEM |
invert[[THIS is_grounded_by: urn:unique_reference:dillylang::spec-primer]]
Apply Munger / Jacobi inversion on the given problem statement.
Stop asking "how succeed" and ask "what guarantees failure."
Calibration example:
Rejected: "FM-1. Market changes — Likelihood: high, Severity: costly." (No mechanism. How do market changes cause damage? Through what chain?)
Accepted: "FM-1. Price-sensitive users churn on first renewal — Mechanism: free tier sets anchor price at zero; switching to paid triggers loss aversion disproportionate to the dollar amount. Likelihood: high. Severity: costly. Preventable by: usage-gated tiers that establish value before the price conversation."
The problem statement from a Munger inversion point-of-view, e.g. "What would cause [desired state] to fail?"
Desired-state inversions: what would I aim for if I wanted to fail? Not causal chains (that's FM) — these are the goals of the adversary.
Causal chains: how does the damage happen, mechanistically?
Each entry must include:
Fragile-but-surviving conditions: things that almost fail but currently hold. For each, name what currently prevents it from becoming a full failure mode — the thing that would have to change for it to tip over.
n is sequential starting from 1 in each section.
After generating your output, review each failure mode: state what causal chain it reveals that the problem framing obscured. Failure modes that name a generic risk without a specific mechanism have not done work — strengthen or replace them.