openJiuwen-ai/sciencediscovery / skills/idea-tree-team
idea-tree-team
VerifiedPrepare supplied inputs for autonomous Idea Tree research and explain its saved results.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.6 KB |
| references/evaluation-principles.md | markdown | 1.7 KB |
| references/workflow.md | markdown | 1.1 KB |
references/workflow.md
View on GitHub# Autonomous research workflow
The Lead first prepares literature and supplied evidence, honoring explicit retrieval skips,
then calls create_idea_research. The Python engine owns the loop: refine directions to the
configured execution depth → select pending leaves → design each leaf → independently
assess activity, stability and sustainability → aggregate → propagate → next batch.
Each successful stage is saved. Pausing prevents new stages; continuing reuses saved outputs.
A service interruption never automatically wakes research. The user can continue from the
Idea Tree panel. Round, candidate, depth, node and optional token limits are selected before
starting. Only leaves at the configured depth can be evaluated. Internal directions receive summaries,
not independent scores. Later batches add improved sibling leaves under those directions.
The Lead prepares inputs and explains outputs; it starts the engine once and does not dispatch individual leaves or maintain
an execution plan for it. Specialist Skills remain available for ordinary tasks outside this engine.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |