菜单
Use when the user wants Karpathy-style autonomous experiment loops, overnight research runs, or iterative keep-or-discard testing.
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/Sheshiyer/skill-clusters --skill autoresearch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。
Arcplume runs Grok through the Grok Build CLI's own OAuth-authenticated session (grok login) for image generation, with strict preflight validation, secret-safe handling, and headless CLI-driven execution -- no separate XAI_API_KEY billing. Video falls back to the billed xAI API. USE WHEN a user wants to generate an image via a locally logged-in Grok Build CLI session, e.g. 'generate an image with grok', 'use grok build', or 'use my logged-in grok session'.
Shared reference for the Selemene cluster: the two report surfaces (deterministic Rust reports vs. narrative witness-pipeline readings), the @selemene/bridge CLI contract, the output manifest format, and non-prescriptive witnessing tone. USE WHEN deciding which Selemene surface to invoke or when routing between birth/compatibility/transit reports and solo/dyadic readings.
Route Selemene Engine tasks to the right surface: deterministic reports (birth/compatibility/transit) via selemene-core and the @selemene/bridge CLI, or narrative witness readings via selemene-report. USE WHEN the user wants anything under the Selemene/Noesis umbrella but has not named the exact surface.
正在显示 SKILL.md
基于 SOC 职业分类
| name | autoresearch |
| description | Use when the user wants Karpathy-style autonomous experiment loops, overnight research runs, or iterative keep-or-discard testing. |
| cluster | quality-eval |
| version | 1.0.0 |
| origin | folded from agent skills library (quality-eval overlap) |
Use this skill when the user wants an agent to run repeated experiments with a strict keep-or-discard loop instead of a one-shot answer.
Use this when the user wants the original Karpathy workflow.
autoresearch repo (set AUTORESEARCH_DIR or ask the user for the path).<autoresearch-repo>/README.md<autoresearch-repo>/program.mdtrain.pyprepare.pyresults.tsv untrackedautoresearch/<tag>Use this mode only if the machine and repo are actually ready for it. The upstream repo assumes a real training environment and is not a generic business-research framework by default.
Use this when the user wants the same experiment pattern applied to:
Read references/thoughtseed-business-loop.md before running this mode.
Always leave behind:
Resolve these per environment rather than hardcoding:
autoresearch repo (e.g. $AUTORESEARCH_DIR).