execution-grounded-bon
暂无简介
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
03 SKILL.md 正文
Execution-Grounded Best-of-N + Behavioral-Diff Reranker
When N agents produce N candidate patches for the same task, the naive rerank is to ask a model "which is best?" — and that is proven near-worthless: an LLM judge over candidate code lands around chance on adversarial selection (JudgeBench), and it is exactly the same-context self-grading the whole Theme-A verification program exists to route around (Goodhart + the intrinsic self-correction ceiling, Huang ICLR'24). The done-signal must be external and agent-inauthorable.
Execution is that signal. Instead of an opinion, run every candidate on inputs chosen to make them disagree, watch what they actually do, and let their behavior cluster them. Candidates that crash or hang eliminate themselves. Candidates that independently converge on the same behavior — especially across two different vendors — are the ones to trust: two independent samples agreeing is the classic oracle-free consensus signal (CodeT), and cross-vendor agreement makes the two samples' blind spots independent (a Codex bug and a Codex bug are unlikely to be the same bug).
Grounded in: S* (2502.14382, distinguishing-input synthesis for candidate selection), B4 (2409.08692, Bayesian best-selection over execution results), PatchDiff (2503.15223, behavioral patch differencing), CodeT (2207.10397, dual-execution agreement without a ground-truth oracle). MASTER A4 / COUNCIL C3 both mandate: gate on executable evidence, never model opinion.
When to run
What makes this distinct (do not conflate)
The bus this rides (do not rebuild)
Protocol
The reranker: rerank.mjs
precomputed: manifest already carries candidates[].observations[]
execute: run each candidate's cmd once per probe to build the behavior matrix
machine-readable (pure JSON on stdout; terminal marker goes to stderr)
prove the logic on this machine (13 embedded assertions)
Manifest schema
Pipeline (all stages pure & execution-derived — no model opinion)
Verdict (excerpt)
SHADOW mode (per COUNCIL C5 — always ship observe-only)
04 同仓库更多 Skills
clarify-requirements
Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.
openmm-md
Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein / protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.
visual-review
Take screenshots of web pages and UI using Playwright for visual review and iteration
status
Diagnostic status report — shows metaswarm installation state, project setup, and potential issues
start
Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work
setup
Interactive project setup — detects your project, configures metaswarm, writes project-local files