Token导航 LogoToken导航

Agent Skill · 研究检索

ln-913-community-debater(ln 913 社区辩手)

ln-913-community-debater 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。

ln-913-community-debater 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,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 32,795。

总安装 2,470周安装 105GitHub Stars 441下载 865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:ln-913-community-debater(ln 913 社区辩手)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-913-community-debater
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-913-community-debater
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/levnikolaevich/claude-code-skills --skill ln-913-community-debater

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。

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。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 命令从指定 GitHub 仓库安装,需确认权限范围和安装路径。建议在安装前确认维护状态、是否会触发联网或文件读写操作。ln-913-community-debater 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/ln-913-community-debater

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/levnikolaevich/claude-code-skills --skill ln-9…;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

ln-913-community-debater 怎么安装?

在终端执行 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-913-communi…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ln-913-community-debater 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。

ln-913-community-debater 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。

ln-913-community-debater 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。

ln-913-community-debater 用的人多吗?

公开数据是累计安装 2,470 次,近一周安装 105 次,下载 865 次,GitHub 441 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。

ln-913-community-debater 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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
ln-913-community-debater

ln 913 社区辩手 · 本页

2,470441需要联网未明确有提醒

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

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If shared/ is missing, fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.

ln-913-community-debater

Type: L3 Worker (standalone) Category: 9XX Community Engagement Launches structured debate discussions in GitHub Discussions for decisions that benefit from community input.


Phase 0: GitHub Discovery

MANDATORY READ: Load shared/references/community_github_discovery.md

Execute the discovery protocol. Extract:

  • {owner}/{repo} for URLs and codebase context
  • repo.id for GraphQL mutation
  • categories["Ideas"] for RFC/Proposal discussions
  • categories["Polls"] for Prioritization polls
  • Verify required categories exist

Load strategy: check docs/community_engagement_strategy.md in target project, fallback to shared/references/community_strategy_template.md. Extract Section 3 (Debate Triggers) and Section 1 (Decision Matrix).

MANDATORY READ: Load shared/references/community_discussion_formatting.md MANDATORY READ: Load shared/references/humanizer_checklist.md


Phase 1: Define the Topic

If $ARGUMENTS provided, use as the topic seed. Otherwise, ask the user what they want to debate.

Gather context:

  1. Read strategy Section 3 -- verify this qualifies as a debate
  2. Grep the codebase for files related to the topic
  3. Read relevant SKILL.md files, docs, or shared references
  4. Identify existing patterns that the proposal might change

Phase 2: Classify Debate Type

TypePrefixCategoryWhen to use
Maintainer RFC -- design mostly done, seeking validation[RFC]IdeasEnd of design process, soft announcement
Community RFC -- early stage, genuinely open to alternatives[RFC]IdeasBeginning of design, kickstart discussion
Proposal -- new feature or restructuring[Proposal]IdeasConcrete idea with use case
Workflow Change -- pipeline, task flow, or conventions[RFC]IdeasAffects multiple areas or user workflows
Prioritization -- what to build next, feature ranking[Poll]PollsMultiple options, need community vote

If type is Prioritization, switch to Polls flow (Phase 4).


Phase 3: Compose RFC Discussion

Use the RFC Structure Pattern from discussion_formatting.md (loaded in Phase 0).

Skill-specific additions beyond the shared pattern:

  • Add ## Unresolved Details section after Open Questions — implementation details not yet decided, to be resolved during development
  • Add ## Decision Criteria section — how the decision will be made (metrics, feedback threshold)
  • Minimum 2 alternatives in the Alternatives table

Phase 4: Compose Poll (for Prioritization type)

GitHub Discussions Polls are created via UI only. Instead, compose a reaction-based voting discussion:

## {Topic}

{1-2 sentence context}

**Vote by reacting to the options below** (each option is posted as a separate comment -- use :+1: to vote).

### Context
{Why this decision matters now}

After creating the discussion, post each option as a separate comment for reaction-based voting.


Phase 5: Fact-Check

Before presenting to user, verify every verifiable claim in the draft:

  1. File paths & links -- verify each linked file exists: ls {path}. Remove or fix broken links.
  2. Code references -- verify mentioned functions/patterns exist: grep -r "{name}".
  3. Alternatives accuracy -- re-read source files to confirm the Alternatives table accurately describes tradeoffs. No hallucinated pros/cons.
  4. Names -- verify skill names, directory names, config keys match actual repo state.
  5. Humanizer audit -- run the audit protocol from humanizer_checklist.md. If 3+ AI patterns found, rewrite flagged sections.

Gate: If any check fails, fix the draft before proceeding.


Phase 6: Review and Publish

Present the composed title + body to the user. Wait for explicit approval before publishing.

After approval, publish via GraphQL using discovery context:

gh api graphql -f query='
  mutation($title: String!, $body: String!, $repoId: ID!, $catId: ID!) {
    createDiscussion(input: {
      repositoryId: $repoId,
      categoryId: $catId,
      title: $title,
      body: $body
    }) {
      discussion { url id }
    }
  }
' -f title="TITLE_HERE" -f body="BODY_HERE" -f repoId="{repo.id}" -f catId="{categories.Ideas or categories.Polls}"

For Polls, after creating the discussion, post each option as a comment:

gh api graphql -f query='
  mutation($discussionId: ID!, $body: String!) {
    addDiscussionComment(input: {
      discussionId: $discussionId,
      body: $body
    }) {
      comment { url }
    }
  }
' -f discussionId="DISCUSSION_NODE_ID" -f body="**Option N:** {description}"

Report the discussion URL to the user.


Rules

  • Always present the full composed text for user approval before publishing
  • Never publish without explicit user confirmation
  • Title: descriptive, under 80 chars, prefixed with [RFC], [Proposal], or [Poll]
  • Body: factual, not persuasive -- present options neutrally
  • Include links to relevant code/docs in the repository
  • Set a decision timeline when applicable
  • Minimum 2 alternatives in the Alternatives table
  • Tone: "We're considering X. Here are the tradeoffs. What's your take?"

Definition of Done

  • Topic defined with codebase context gathered
  • Debate type classified (RFC/Proposal/Workflow/Prioritization)
  • RFC or poll composed with minimum 2 alternatives
  • Fact-checked (links, code references, alternatives accuracy, names)
  • Humanizer audit passed (< 3 AI patterns)
  • User approved final draft
  • Published via GraphQL mutation, URL reported

Version: 1.0.0 Last Updated: 2026-03-13

平台分布

Codex

37.71%
按下载量换算326

Claude

30.38%
按下载量换算263

Cursor

18.4%
按下载量换算159

Gemini CLI

10.71%
按下载量换算93

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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