菜单
Defines how an @samchon/lint-plugin-evidence benchmark campaign is set up, launched under frozen inputs, run, supervised, recovered, and reported, from issue creation through pull-request completion. Use whenever operating, supervising, or reporting a benchmark run.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/samchon/lint-plugin-evidence --skill benchmark命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Defines the review of @evidence and @evidenceExclude for fake citations, for cited requirements the code contradicts, and for exclusions created solely to evade compiler errors, of configuration edited beyond the one permitted activation, and of the compiler and runtime gates each scope must pass. Read only for a review objective; backend.md, frontend.md, and overall.md carry the per-scope configuration and gates.
Defines the Evidence Graph tag grammar, truthfulness rules, claim activation, frozen configuration, behavioral proof, citations, exclusions, and the stub marker. Read before Evidence implementation or handling a graph diagnostic; backend.md and frontend.md carry the per-phase claims, placement, examples, and staged unlock.
Defines backend layer ownership, implementation order, compiler checking, generation boundaries, and the backend gate. Read before backend work, then read every sibling topic.
基于 SOC 职业分类
正在显示 SKILL.md
| name | benchmark |
| description | Defines how an @samchon/lint-plugin-evidence benchmark campaign is set up, launched under frozen inputs, run, supervised, recovered, and reported, from issue creation through pull-request completion. Use whenever operating, supervising, or reporting a benchmark run. |
A campaign measures one coding engine building the same application twice: once with @samchon/lint-plugin-evidence and its guidance, once with neither. One subject and arm is a cell, one execution of a cell is a run, retained under benchmark/output/<subject>/codex/<arm>/runs/<run-id>/.
Two perspectives, and they are never interchangeable.
A rule written for the operator never binds a cell, and a cell's permitted edit is never yours to make.
Under pnpm --filter @samchon/evidence-benchmark:
start — launch, resume, or derive a run. running.md, recovery.mddashboard, audit-suspensions — the live pull-request record. dashboard.mdreport — the tracked benchmark/aggregate artifacts. aggregate.mdsupervise — apply a hand-written Plain review verdict. plain-review.mdwarn — deliver an operator warning to a running cell. warning.md