Token导航 LogoToken导航

Agent Skill · 研究检索

rpi(转速)

rpi 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

rpi 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 11,687。

总安装 11,007周安装 468GitHub Stars 318下载 3,856核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:rpi(转速)
来源仓库:https://github.com/boshu2/agentops
仓库路径:skills/rpi
安装命令:
npx skills add https://github.com/boshu2/agentops --skill rpi
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/boshu2/agentops --skill rpi

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

rpi 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词快速定位候选结果时使用。适用于研究检索类任务,可结合来源仓库和原始 README 核验具体用法。通过 npx skills add 命令从 GitHub 安装,需确认权限范围和维护状态。

使用前建议检查是否会触发联网、命令执行或文件读写等敏感操作。rpi 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/rpi

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/boshu2/agentops --skill rpi;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

rpi 怎么安装?

在终端执行 npx skills add https://github.com/boshu2/agentops --skill rpi。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

rpi 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

rpi 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/boshu2/agentops --skill rpi 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

rpi 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

rpi 用的人多吗?

公开数据是累计安装 11,007 次,近一周安装 468 次,下载 3,856 次,GitHub 318 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

rpi 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
rpi

转速 · 本页

11,007318执行命令未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

/rpi - Full Lifecycle Orchestrator

Quick ref: /discovery -> /crank -> /validation, then report.

Execute this workflow. Do not only describe it. RPI is autonomous unless --interactive is set. The user touchpoint is after validation, or after a real blocked state exhausts retries. Read references/autonomous-execution.md when you need the full autonomy contract.

Core Contract

RPI delegates via Skill(skill="discovery",...), Skill(skill="crank",...), and Skill(skill="validation",...) as separate tool invocations. Keep strict delegation on by default; do not compress phases, replace phase skills with direct agent spawns, or skip validation. Read ../shared/references/strict-delegation-contract.md for the full anti-compression contract.

RPI owns one lifecycle objective across all phases. Preserve the discovered epic_id when present; otherwise preserve the original goal and execution packet objective. A child bead or one ready slice is context, not a replacement objective. <promise>PARTIAL</promise> from /crank means retry Phase 2 on the same objective.

Route And Classify

  1. Create .agents/rpi/.
  2. Resolve --from:

- default, research, plan, pre-mortem, brainstorm -> discovery - implementation or crank -> implementation - validation, vibe, or post-mortem -> validation

  1. If the input is a bead and --from is absent, resolve it with bd show:

- epic -> implementation with that epic - child with parent -> implementation with the parent epic

  1. Classify complexity:

- fast: short/simple goal or --fast-path - standard: medium goal or one scope keyword - full: --deep, complex-operation keyword, 2+ scope keywords, or >120 chars

  1. Log RPI mode: rpi-phased (complexity: <level>).

Track state compactly:

rpi_state = {
  goal: "<goal string>",
  epic_id: null,
  phase: "<discovery|implementation|validation>",
  complexity: "<fast|standard|full>",
  test_first: <true by default; false only when --no-test-first>,
  cycle: 1,
  verdicts: {}
}

Complex-operation keywords include refactor, migrate, rewrite, redesign, rearchitect, overhaul, decouple, deprecate, split, extract module, and port. Scope keywords include all, entire, across, everywhere, every file, system-wide, global, and codebase.

Phase DAG

Enter at the routed phase and run every phase after it.

  1. Discovery: invoke /discovery <goal> [--interactive] --complexity=<level>. On DONE, read .agents/rpi/execution-packet.json or the run archive and preserve its objective spine. On BLOCKED, stop with the discovery verdict.
  2. Implementation: invoke /crank <epic-id> when the packet has epic_id; otherwise invoke /crank.agents/rpi/execution-packet.json. Pass --test-first or --no-test-first through. On DONE, record ao ratchet record implement 2>/dev/null || true and continue. On PARTIAL or BLOCKED, retry the same objective up to 3 total attempts.
  3. Validation: invoke /validation <epic-id> --complexity=<level> when an epic exists; otherwise invoke /validation --complexity=<level>. Add --strict-surfaces when --quality is set. On FAIL, extract findings, re-run /crank on the same objective, then re-run /validation, up to 3 total validation attempts. On DONE, record ao ratchet record vibe 2>/dev/null || true.
  4. Report: summarize phase verdicts and epic status using references/report-template.md. With --loop, restart from discovery on FAIL while cycle < max_cycles. With --spawn-next, read .agents/rpi/next-work.jsonl and suggest the next command without invoking it.

Phase Data Contract

The execution packet carries the repo execution profile through contract_surfaces, done_criteria, and queue claim/finalize metadata. Keep the latest alias at .agents/rpi/execution-packet.json and read references/phase-data-contracts.md for schemas and archive paths.

Complexity-Scaled Gates

Pre-mortem

  • complexity == "low" or "fast": inline review, no spawning (--quick)
  • complexity == "medium" or "standard": inline fast default (--quick)
  • complexity == "high" or "full": full council, 2-judge minimum; max 3 total attempts

Final Vibe

  • complexity == "low" or "fast": inline review, no spawning (--quick)
  • complexity == "medium" or "standard": inline fast default (--quick)
  • complexity == "high" or "full": full council, 2-judge minimum; max 3 total attempts

Post-mortem (STEP 2)

  • complexity == "low" or "fast": inline review, no spawning (--quick)
  • complexity == "medium" or "standard": inline fast default (--quick)
  • complexity == "high" or "full": full council, 2-judge minimum; max 3 total attempts

Flags

FlagDefaultPurpose
--from=<phase>discoveryStart at discovery, implementation, or validation
--discovery-artifact=<path>unsetWith implementation start, convert an existing artifact into the handoff packet
--interactiveoffHuman gates in discovery/validation
--autoonFully autonomous default
--loop --max-cycles=<n>off / 3Iterate when validation fails
--spawn-nextoffSurface follow-up work after reporting
--test-firstonPass strict-quality preference to /crank
--no-test-firstoffExplicitly opt out of strict-quality
--fast-path / --deepautoForce fast or full complexity
--qualityoffMake validation strict surfaces blocking
--dry-run / --no-budgetoffReport only, or disable phase time budgets

Examples

User says: /rpi "add user authentication" Run discovery, implementation, validation, then report.

User says: /rpi --from=implementation ag-23k Resolve the bead scope, run implementation and validation, then report.

User says: /rpi --deep "refactor payment module" Use full council gates across the lifecycle.

Read references/examples.md for resume, interactive, loop, and artifact-mode examples.

Troubleshooting

ProblemResponse
Discovery BLOCKEDStop and report discovery's manual-intervention reason
/crank returns PARTIALRetry /crank on the same objective; do not narrow to a child slice
Validation FAILRe-crank with findings, then re-validate, up to 3 total attempts
Packet shape unclearRead references/phase-data-contracts.md

Reference Documents

平台分布

Codex

35.84%
按下载量换算1,382

Claude

30.72%
按下载量换算1,185

Cursor

16.42%
按下载量换算633

Gemini CLI

9.85%
按下载量换算380

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/boshu2/agentops --skill rpi 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills