Skip to main content
Repositorio de GitHub

autonomous-world-model

autonomous-world-model contiene 9 skills recopiladas de ScavieFae, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.

skills recopiladas
9
Stars
0
actualizado
2026-04-13
Forks
0
Cobertura ocupacional
3 categorías ocupacionales · 100% clasificado
explorador de repositorios

Skills en este repositorio

experiment-complete
Desarrolladores de software

Close out an experiment — update run card with results, update frontmatter, rebuild docs index, close PR, log to research log, propose program.md updates. Use when an experiment has finished training and eval.

2026-04-13
experiment-launch
Científicos de datos

Pre-flight checklist for launching a training experiment on Modal — verifies run card, config, data contract, local smoke test, budget, observability, and stop conditions before burning GPU time. Use when kicking off any new experiment, Mamba2 or JEPA. Counterpart to /experiment-complete.

2026-04-11
consult-architecture
Científicos de datos

Get Mamba2 and training architecture guidance for experiment design. Use when a proposed experiment touches model structure, training regime, or loss design and you need to understand how the architecture constrains or enables the approach.

2026-03-21
consult-canon
Físicos

Search the world model research literature for prior art, alternative approaches, or techniques from adjacent fields. Use when evaluating whether a proposed technique has precedent, when seeking inspiration from different paradigms, or when a paper is referenced and you need context on it.

2026-03-21
consult-empirical
Científicos de datos

Review project experiment history to answer questions about what's been tried, what worked, hit rates, and empirical patterns. Use when proposing a new experiment direction and you need to check whether it's been explored, or when evaluating results against prior findings.

2026-03-21
conductor
Desarrolladores de software

Run one conductor heartbeat — check experiment state, evaluate completed runs, dispatch new research cycles. Supports parallel experiments. Use with `/loop 60m /conductor` for autonomous operation.

2026-03-21
research-cycle
Desarrolladores de software

Run one autoresearch cycle — hypothesize, Director review, execute on Modal, evaluate. Use to manually trigger a research cycle or to test the loop.

2026-03-14
pull
Desarrolladores de software

Post-pull orientation — absorb what changed, scan HANDOFF and RUNNING for new context, check run cards and program.md, report to user. Use when starting a session, after a git pull, or when the user says "pull", "catch me up", "what changed", or "orient".

2026-03-14
push
Desarrolladores de software

Pre-push workflow — communicate with ScavieFae, capture notes in RESEARCH-LOG.md, check hygiene, then commit and push. Use when the user says "push", "ship it", "send it", or asks to commit and push changes.

2026-03-14