Prepare supplied inputs for autonomous Idea Tree research and explain its saved results.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Idea Tree is executed by the Python research engine, independently of the Lead conversation.
Configure budgets and role prompts in System Settings → Idea Tree. Use /idea-tree <task>
or /idea-tree-team <task> in the composer to enter this preparation workflow.
An explicit natural-language request for idea-tree or idea-tree-team uses the same workflow.
Search and read relevant literature first, then summarize evidence with source references,
constraints and uncertainties. Skip retrieval only when the user explicitly requests it or
supplied evidence is sufficient. Respect requests to skip retrieval without asking again.
Call create_idea_research(objective, materials) after preparation; do not merely describe a plan.
After the tool succeeds, report the handoff and finish the turn. Python owns all tree iterations;
do not dispatch design or assessment Subagents, run shell to simulate a tree, or poll for completion.
Use get_idea_research when the user later asks about progress or results.
Objective and prepared materials are backend inputs, not a separate front-end form. Do not create a plan or invoke legacy
tree_* tools to execute this workflow.
Before starting, prepare the research objective, explicit constraints and any relevant supplied materials. External retrieval or analysis must be completed before submission; the engine does not search, execute code or dispatch tool-using Subagents. Respect requests to skip retrieval. Without supplied evidence, identify conclusions as hypotheses rather than sourced findings.
Direction nodes organize hypotheses and receive insight from their children; they are not independently designed or scored. Only pending leaves at the configured execution depth run. Later cycles add improved leaves under directions, preserving earlier leaf results.
The engine performs repeated batches of ideation, design, independent activity/stability/ sustainability assessments, aggregation and insight propagation. Existing role prompts can be replaced in Idea Tree settings. Progress, pause, continue and end controls live in the tree panel. Do not restart or continue research merely because a chat message or notification arrives.
Explain saved results in terms of candidate differences, assessment findings, improvements and uncertainties. Do not narrate internal protocol fields. Old trees remain read-only; new research uses the Python engine. A completed research is not experimental verification of its hypotheses.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Prepare, launch, monitor, and summarize the real RFdiffusion to ProteinMPNN to Protenix antibody pipeline on a local or remote ScienceDiscovery Runner with sandboxed Ascend NPUs.
The English summary is being prepared. Showing the original description.
Independent multi-dimensional assessor for material design candidates. Loads configurable scoring rubrics to evaluate candidates from different expert perspectives. Each dispatch produces structured scores, pros/cons, and verification data without sharing results with other assessors.
The English summary is being prepared. Showing the original description.
Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the merge queue, the nightly schedule and the release tag. Use when a job fails, when editing .github/workflows/, when asking which layer runs what, when reproducing a pipeline failure locally, or when a job needs the bubblewrap sandbox. Running the layers before proposing a change, and reading the result a proposal receives, belong to create-github-pr.
The English summary is being prepared. Showing the original description.
Verify cited paper identity and decide whether claims in an Artifact are supported by their linked Evidence using a governed source snapshot.
The English summary is being prepared. Showing the original description.
Use this skill when you need to write and execute Python/R code to process, transform, and analyze data, delivering reproducible computational results with complete code-level methodology documentation. Supports statistical analysis, data transformation, visualization, method justification, and structured result output.
The English summary is being prepared. Showing the original description.
Check whether numeric claims marked with Evidence aliases in an Artifact agree with the linked Evidence content and context.
The English summary is being prepared. Showing the original description.