ai-research-explore
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of current_research with auditable repo understanding, idea gating, fair comparison, and governed experiments written to explore_outputs/. Do not use…
- installs 8w
- 160,575
- 30-day movement
- starts with the next reading
- Related entries
- 1
- Connections
- 0
An agent skill that guides candidate-only deep learning research exploration on top of a durable `current_research` anchor, compatible with Rigor Explore. It enforces auditable repo understanding, idea gating, fair comparison, and governed experiments whose outputs are written to `explore_outputs/`.
Use it when you have already chosen the task family, dataset, benchmark, evaluation method, and SOTA references, and want disciplined, authorized exploration of research candidates rather than open-ended direction finding.
Use it to
- Confirm the current_research anchor and explicit explore-lane authorization
- Accept a research_campaign or legacy variant_spec as input
- Rank candidates by expected gain, cost, risk, and rollback ease
- Run governed experiments with fair comparison against SOTA references
- Write auditable exploration results to explore_outputs/
For Researchers running gated deep learning exploration campaigns with an AI agent
- Host repository
- lllllllama/RigorPilot-Skills
- Installs, lifetime
- 311k
- Installs, 8 weeks
- 161k
- Host stars
- 487
- Host language
- Python