组织
Scientific Computing and Intelligence Group
Department of Mathematics, National University of Singapore
- Skills
- 27
- 仓库
- 1
- 职业覆盖
- 3
- 场景覆盖
- 3
- Stars
- ★ 66
Scientific Computing and Intelligence Group 的 Skills 27
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
theorem-search
Use TheoremSearch to find, verify, and cite mathematical theorem statements, named results, proof routes, and literature dependencies.
supervise-run
Use when monitoring a running Eve experiment and recovering from problems while it runs
run-math-proof-quickstart
Use when running a Math Proof quickstart from a user-provided problem: create a local task copy, launch a real EvE attempt, supervise it, and report proof/evaluation results.
run-circle-packing-smoke
Use when a fast end-to-end smoke run is needed for the Eve loop development, will run on circle packing task.
resume-run
Use when continuing an interrupted or paused Eve run from where it stopped (same run, same id), optionally after editing the experiment
matlas-search
Use Matlas semantic search over published mathematical literature to find canonical statements, hypotheses, and citation metadata for standard or named results.
inspect-population
Use when reading what an Eve run evolved — its best solvers/optimizers, their code, and how the population improved
import-run
Use when starting a new Eve run seeded from one or more prior runs, e.g. keep the good solvers but try a fresh optimizer
implement-subagent
Use when implementing a subagent.
implement-evaluation-steps
Use when defining or updating Eve evaluation steps.
implement-check-subagent
Use when implementing a sanity check subagent for the phase 2 optimization in Eve loop.
delete-eve-run
Safely delete one or more local EvE run directories, including runs whose read-only files or directories make rm fail. Use when the user explicitly asks to remove run roots under .runs/eve/, or when rm reports Permission denied or Read-only file system while pruning an EvE run.
debug-agent-session
Use when an Eve agent is behaving wrong (stuck, gaming the score, bad reasoning) and you need to read its own rollout to find out why
configure-eve-driver
Use when choosing, editing, or overriding EvE driver settings for Codex, OpenCode, or interactive/debug runs.
writing-subagents
Use when creating new subagents, editing existing subagents, or verifying subagents work before deployment
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
theorem-search
Use TheoremSearch to find, verify, and cite mathematical theorem statements, named results, proof routes, and literature dependencies.