Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →AutoScientists coordination-mechanism testbed — dead-end registry, noise-band confirmation, effect-size ranking, stagnation-driven reorganization, honest null reporting.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 163% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -49% | 0% |
Project-scoped skill for the in-repo exemplar at projects/templates/template_autoscientists/. Load this when working inside the project.
template_autoscientists exemplar — running scripts, editing source,or regenerating outputs.
no-mocks testing) still hold after changes.
bash# From the repository root uv run pytest projects/templates/template_autoscientists/tests --cov=projects/templates/template_autoscientists/src --cov-fail-under=90 uv run python scripts/pipeline/stage_02_analysis.py --project templates/template_autoscientists uv run python scripts/pipeline/stage_03_render.py --project templates/template_autoscientists uv run python scripts/pipeline/stage_04_validate.py --project templates/template_autoscientists uv run python scripts/pipeline/stage_05_copy.py --project templates/template_autoscientists
src/ or sharedinfrastructure/, not in scripts/.
computation.
output/ — regenerate fromsource and config.
as working directory unless the child AGENTS.md states otherwise.
AGENTS.mdREADME.mdTODO.mdprojects/AGENTS.mdOther measured skills in the registry, with their headline benchmark lift.