Token导航 LogoToken导航

Agent Skill · 研究检索

recursive-spec(递归规范)

recursive-spec 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。

recursive-spec 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,权限为需要联网;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 54,679。

总安装 499周安装 20GitHub Stars 60下载 162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:recursive-spec(递归规范)
来源仓库:https://github.com/try-works/recursive-mode
仓库路径:skills/recursive-spec
安装命令:
npx skills add https://github.com/try-works/recursive-mode --skill recursive-spec
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/try-works/recursive-mode --skill recursive-spec

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。

recursive-spec 用于查找、检索和筛选相关信息,支持基于关键词或场景定位内容。适合在 Codex、Claude、Cursor、Gemini CLI 中需要快速获取候选结果时使用。通过 GitHub 安装,结合来源仓库和 README 可进一步核验具体用法。

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。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/recursive-spec

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/try-works/recursive-mode --skill recursive-spe…;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

    它需要需要联网,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

recursive-spec 怎么安装?

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

recursive-spec 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。

recursive-spec 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

recursive-spec 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。

recursive-spec 用的人多吗?

公开数据是累计安装 499 次,近一周安装 20 次,下载 162 次,GitHub 60 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。

recursive-spec 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

  • 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

  • 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
recursive-spec

递归规范 · 本页

49960需要联网未明确通过

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

recursive-spec

Use this skill to co-author a repo-aware 00-requirements.md for a new recursive-mode run.

This skill is for requirements/spec authoring before implementation starts. It does not replace /.recursive/RECURSIVE.md, and it should not skip ahead to Phase 2 planning or Phase 3 implementation.

Primary Use Case

Use recursive-spec when the user wants help shaping work before a run exists, especially with prompts like:

  • create a plan
  • help me plan
  • create a spec
  • write requirements
  • spec this out
  • scope this

The important signal is plan/spec language for a new run, not implementation of an existing run.

Conversation Contract

When the trigger is detected:

  1. First ask whether the user wants help creating a spec for a recursive run.
  2. If the user replies positively, ask: What do you want to do?
  3. Then gather context, read the repo, and co-author the requirements.

Do not jump straight into writing 00-requirements.md before the user confirms they want spec help.

Draft Handling Before Approval

Until the user explicitly approves the spec:

  • keep the draft outside the repository worktree
  • prefer a temporary session artifact or scratch file
  • do not create /.recursive/run/<run-id>/
  • do not write 00-requirements.md

If the user rejects the draft, revise it or discard the temporary draft artifact. Do not leave behind a half-approved run folder.

Required Read Behavior

Before drafting requirements, read:

  1. /.recursive/STATE.md
  2. /.recursive/DECISIONS.md
  3. /.recursive/memory/MEMORY.md
  4. relevant memory shards only when they actually matter
  5. the most relevant code and tests for the requested area

The skill should be repo-aware, not a blind questionnaire. Use the control-plane docs to understand current truth and the codebase to understand actual surfaces, coupled modules, existing tests, and likely boundaries.

Authoring Flow

Use a guided interview. Ask one focused question at a time when the answer is not already grounded by repo docs or code.

Recommended sequence:

  1. Goal and user outcome
  2. Task type: feature, bugfix, refactor, migration, investigation
  3. Affected subsystem or files
  4. In-scope requirements (R#)
  5. Observable acceptance criteria for each requirement
  6. Edge cases, failure paths, and exclusions
  7. Constraints, fixed decisions, and boundaries
  8. Open unknowns that must be resolved before Phase 0 is locked

Prefer proposing draft wording and asking the user to confirm or correct it rather than asking the user to author the whole document from scratch.

Quality Rules

Borrow the strongest authoring ideas from contract-first workflows, but keep the output native to recursive-mode:

  • start with user intent and desired outcome
  • separate fixed decisions from open questions
  • define deterministic, observable acceptance criteria
  • include exception and failure-path thinking instead of only the happy path
  • make boundaries concrete enough to guide later AS-IS analysis and planning
  • keep out-of-scope items explicit

Do not introduce a separate .spec DSL or a second workflow format.

Output Contract

The finished output should become:

  • /.recursive/run/<run-id>/00-requirements.md

Use the repository's native Phase 0 requirements structure:

  • keep the scaffolded header from recursive-init, including Workflow version: recursive-mode-audit-v2
  • keep the required ## TODO section and replace placeholder checklist items rather than deleting the heading
  • ## Requirements
  • ## Out of Scope
  • ## Constraints

Within ## Requirements, each R# should include:

  • a short title
  • a clear description
  • observable acceptance criteria bullets

Run Creation Rule

Do not create the run folder immediately.

  1. Draft and refine the requirements with the user first.
  2. Keep the draft in a temporary non-repo artifact until approval.
  3. Confirm the user approves the spec and that it is complete enough to proceed.
  4. Create the run with scripts/recursive-init.py or scripts/recursive-init.ps1.
  5. Replace the scaffolded 00-requirements.md with the approved requirements content.

This keeps the run artifact grounded in user-approved requirements instead of half-formed notes.

Routing Awareness

If spec authoring uses delegated critique, delegated review, or any other external model help to shape the draft, re-read:

  • /.recursive/config/recursive-router.json
  • /.recursive/config/recursive-router-discovered.json

immediately before choosing that CLI/model, and route through recursive-router instead of inventing an ad hoc model choice.

Boundaries

  • Stay focused on 00-requirements.md authoring for a new run.
  • Do not silently convert this into Phase 2 planning.
  • Do not start implementation just because the requirements became clear.
  • Do not skip code reading when repository structure matters to scope or constraints.
  • Do not create a run until the user-approved spec is ready to write.
  • Do not write repository requirements artifacts from an unapproved draft.

References

  • /.recursive/RECURSIVE.md
  • /.recursive/STATE.md
  • /.recursive/DECISIONS.md
  • /.recursive/memory/MEMORY.md
  • ../../references/artifact-template.md
  • ./references/patterns.md

平台分布

Codex

32.24%
按下载量换算52

Claude

30.63%
按下载量换算50

Cursor

20.43%
按下载量换算33

Gemini CLI

9.84%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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