catalyst

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

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

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

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

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

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.

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

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

Summarize the current goal progress

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

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

Apply a custom modification to a theory

Expand a theory by applying suggested expansion reviews

Improve a theory based on adherence review findings

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.

Attempt to refine a given hypothesis

Streamline a theory down to its core essence.

Write a theory to explain a given phenomenon.

Summarize the current research status

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

Attempt to falsify a given hypothesis

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

Review an entire theory and suggest concrete areas for expansion

Score the length of a given theory.

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

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

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

Refine a theory by sequentially applying all its available reviews

Review all theorems/lemmas in a theory and suggest expansions

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

Rank different theories based on their explanatory power

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

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).

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

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

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

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

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

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

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