imbue-ai/catalyst

summarize-goal-progress

Summarize the current goal progress

원문 언어: 영어

summarize-research

Summarize the current research status

원문 언어: 영어

score-guidance-adherence

Score how well the given theory adheres to the provided guidance.

원문 언어: 영어

score-length

Score the length of a given theory.

원문 언어: 영어

score-soundness

Score the mathematical soundness of a given theory based on its existing falsification reports.

원문 언어: 영어

score-theory-local-subscores

Score the given theory according to certain per-theory subscore criteria.

원문 언어: 영어

propose-experiment

Design and propose the next step: either a regular data-gathering experiment, literature search, or a concrete solution candidate.

원문 언어: 영어

execute-proposal

Determine the type of proposal given, execute/delegate accordingly, and return the appropriate resulting ID (experiment ID, literature search ID, or solution ID).

원문 언어: 영어

score-theory-solutions

Score and rank solution candidates relative to the research goal, and update parent theory scores.

원문 언어: 영어

integrate-interpretations

Integrate recent interpretations from the interpretation log into the associated theory.

원문 언어: 영어

rank-experiments

Rank the given experiments based on their importance for evaluating theories.

원문 언어: 영어

interpret-result

Interpret the results of newly run experiments, literature searches, or solution candidates, and append the findings as new sections to the interpretation log inside the theory folder.

원문 언어: 영어

rank-proposals

Compare and rank multiple proposals (experiments, literature searches, and solution candidates), separating solution candidates from other proposals.

원문 언어: 영어

run-experiment

Set up and run a single experiment. Experiments can be arbitrary Python scripts. All experiment execution must go through this skill.

원문 언어: 영어

literature-review

Search arXiv for relevant papers, download papers, and produce a structured literature review

원문 언어: 영어

search-literature

Run a targeted literature search on specific findings or questions that emerged during theory development

원문 언어: 영어

edit-theory

Apply a custom modification to a theory

원문 언어: 영어

expand-theory

Expand a theory by applying suggested expansion reviews

원문 언어: 영어

improve-adherence

Improve a theory based on adherence review findings

원문 언어: 영어

polish-theory

Polish a theory to improve its clarity and make it easier to read. Does not add or remove any content, just rewords and restructures it.

원문 언어: 영어

refine-hypothesis

Attempt to refine a given hypothesis

원문 언어: 영어

streamline-theory

Streamline a theory down to its core essence.

원문 언어: 영어

write-theory

Write a theory to explain a given phenomenon.

원문 언어: 영어

support-idea

Run experiments and derive mathematical proofs to support a pre-existing theory idea supplied as a latex/pdf/markdown file or argument.

원문 언어: 영어

falsify-hypothesis

Attempt to falsify a given hypothesis

원문 언어: 영어

predict-experiments

Use the given theory to predict the results of a given set of experiments.

원문 언어: 영어

suggest-expansions

Review an entire theory and suggest concrete areas for expansion

원문 언어: 영어

score-theories

Score the quality of the given theories relative to each other and update all population scores.

원문 언어: 영어

smoke

Trivial skill used to validate the orchestrator + agent runner plumbing without paying for a real research task

원문 언어: 영어

review-adherence

Review a given theory for adherence to guidance, constraints, and explanatory coverage

원문 언어: 영어

refine-theory

Refine a theory by sequentially applying all its available reviews

원문 언어: 영어

review-theory

Review all theorems/lemmas in a theory and suggest expansions

원문 언어: 영어

explore

Team of explorers that investigate a scientific phenomenon from multiple angles simultaneously

원문 언어: 영어

rank-explanatory-power

Rank different theories based on their explanatory power

원문 언어: 영어

rank-predictions

Rank different predictions based on how well they predict the results of a given experiment. Returns a ranked list of the theory IDs associated with each prediction with their accuracy ranking (1...n).

원문 언어: 영어

swarm

Fan out a task to N independent agents with diverse approaches and collect all results

원문 언어: 영어

write-n-theories

Spawn N independent agents that each invoke the write-theory skill, producing N distinct root theories

원문 언어: 영어

import-theory

Import a pre-existing theory from a latex/pdf/markdown file and store in the context database.

원문 언어: 영어

write-different-theory

Write a theory taking a *different* approach from the provided ones.

원문 언어: 영어

streamline-theory-variations

Streamline a theory down to its core essence, selecting a few different options.

원문 언어: 영어