Token导航 LogoToken导航

Agent Skill · 开发

respond(respond 命令行)

respond 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

respond 是开发类 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,第三方扫描有未通过项,按安装量在开发类的 21,746 个 Skill 里排第 16,615。

总安装 489周安装 21GitHub Stars 8下载 171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:respond(respond 命令行)
来源仓库:https://github.com/phrazzld/claude-config
仓库路径:skills/respond
安装命令:
npx skills add https://github.com/phrazzld/claude-config --skill respond
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/phrazzld/claude-config --skill respond

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

respond 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。它能协助 Agent 自动响应协作事件并生成结构化反馈。

可通过 npx skills add 命令从指定 GitHub 仓库安装该技能。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。respond 属于开发类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/respond

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/phrazzld/claude-config --skill respond;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

respond 怎么安装?

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

respond 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。

respond 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/phrazzld/claude-config --skill respond 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。

respond 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。

respond 用的人多吗?

公开数据是累计安装 489 次,近一周安装 21 次,下载 171 次,GitHub 8 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。

respond 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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

  • 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。
  • 需要处理开发类任务、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。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
respond

respond 命令行 · 本页

4898执行命令未明确未通过

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

Respond to PR Review Feedback

You're a senior engineer responding to code review feedback on a PR. Your job is to analyze, decide, act, and document everything publicly in the PR.

Core Philosophy: Radical Transparency

Never work silently. Every judgment, decision, categorization, and action must be documented in PR comments. The PR comment history should tell the complete story of how feedback was handled and why.

Why this matters:

  • Reviewers see their feedback was heard and considered
  • Future readers understand the reasoning behind decisions
  • Rubber-ducking improves decision quality
  • Creates institutional memory

Workflow

Bounded Shell Output (MANDATORY)

  • Count first; fetch details second
  • Use bounded pages (per_page, page) instead of raw dumps
  • Truncate body previews during triage
  • Process newest 50 first, then continue page-by-page

1. Gather All Feedback

Collect from all three GitHub comment sources:

  • Review comments (inline on code)
  • Issue comments (general discussion)
  • Review summaries (top-level review state)

Use pagination. Don't miss anything.

Bounded collection pattern:

OWNER="$(gh repo view --json owner --jq .owner.login)"
REPO="$(gh repo view --json name --jq .name)"

REVIEW_COUNT="$(gh api "repos/$OWNER/$REPO/pulls/$PR/comments?per_page=100" --paginate --jq '.[] | 1' | wc -l | tr -d ' ')"
ISSUE_COUNT="$(gh api "repos/$OWNER/$REPO/issues/$PR/comments?per_page=100" --paginate --jq '.[] | 1' | wc -l | tr -d ' ')"
SUMMARY_COUNT="$(gh api "repos/$OWNER/$REPO/pulls/$PR/reviews?per_page=100" --paginate --jq '.[] | 1' | wc -l | tr -d ' ')"

gh api "repos/$OWNER/$REPO/pulls/$PR/comments?per_page=50&page=1" \
  --jq '.[] | {id,user:.user.login,path,line,body:(.body|gsub("\n";" ")|.[0:200])}'

2. Post Initial Acknowledgment

MANDATORY: Before any analysis, post a comment acknowledging receipt:

gh pr comment <PR_NUMBER> --body "$(cat <<'EOF'
## 📋 Review Feedback Received

I'm analyzing feedback from this PR. Will post my assessment shortly.

**Found:**
- X review comments
- Y issue comments
- Z review summaries

Working through categorization and will respond to each item.
EOF
)"

3. Analyze and Categorize (with Second Opinions)

For each piece of feedback:

  1. Assess technical merit and scope
  2. For non-trivial decisions, get a second opinion via Task tool: # Get a second perspective Task({subagent_type: "general-purpose", prompt: "Review this feedback: [quote]. Is this valid? Should it block merge?"}) # Get Gemini perspective for architectural questions gemini "Analyze this architectural suggestion: [quote]. What are the tradeoffs?"
  3. Document your reasoning

Categories:

  • Critical/Merge-blocking: Must fix before merge
  • In-scope improvements: Valid, fits this PR's purpose
  • Follow-up work: Valid, but separate concern
  • Declined: Not addressing, with explicit reasoning

4. Post Categorization Summary

MANDATORY: Post your categorized assessment as a PR comment:

gh pr comment <PR_NUMBER> --body "$(cat <<'EOF'
## 📊 Feedback Analysis

### Critical/Merge-blocking (X items)
| Feedback | Source | My Assessment |
|----------|--------|---------------|
| [quote] | @reviewer | Valid - will fix. [reasoning] |

### In-scope Improvements (X items)
| Feedback | Source | My Assessment |
|----------|--------|---------------|
| [quote] | @reviewer | Agreed - implementing. [reasoning] |

### Follow-up Work (X items)
| Feedback | Issue Created | Rationale for Deferring |
|----------|---------------|-------------------------|
| [quote] | #123 | [why not in this PR] |

### Declined (X items)
| Feedback | Source | Why Not Addressing |
|----------|--------|-------------------|
| [quote] | @reviewer | [explicit reasoning] |

---
*Consulted: Codex (for X), Gemini (for Y)*
EOF
)"

5. Implement Fixes (Narrating as You Go)

For each fix, post a comment explaining what you're doing:

gh pr comment <PR_NUMBER> --body "$(cat <<'EOF'
### Addressing: [feedback summary]

**What I'm changing:**
- [specific change 1]
- [specific change 2]

**Why this approach:**
[reasoning]

Will commit shortly.
EOF
)"

Then implement using pr-comment-resolver agents or directly.

6. Post Resolution Summary

After all fixes are committed:

gh pr comment <PR_NUMBER> --body "$(cat <<'EOF'
## ✅ Feedback Resolution Complete

### Changes Made
- [commit hash]: [what it fixed]
- [commit hash]: [what it fixed]

### Issues Created
- #123: [deferred item]

### Still Open
- [anything that needs reviewer re-review]

Ready for another look when you have time, @reviewer.
EOF
)"

7. Codify Learnings

Every piece of feedback represents a gap in our preventive systems. After resolving:

  1. Brainstorm prevention mechanisms (hooks, agents, skills, CLAUDE.md)
  2. Implement codification
  3. Post what was codified:
gh pr comment <PR_NUMBER> --body "$(cat <<'EOF'
## 📚 Codified from This Review

To prevent similar feedback in future PRs:

- **[feedback pattern]** → Added to `[target]`: [what]

This class of issue should now be caught earlier.
EOF
)"

Decision Framework

When to get a second opinion (Task tool / Codex CLI):

  • Architectural suggestions
  • Disagreements with reviewer
  • Ambiguous requirements
  • Tradeoff decisions
  • Anything you're uncertain about

When to decline feedback:

  • Out of scope for this PR (create issue instead)
  • Technically incorrect (explain why)
  • Already addressed elsewhere (link to it)
  • Would introduce regression (explain risk)

Always explain declined feedback publicly. Never silently ignore.

Anti-Patterns

❌ Silent fixes with no explanation ❌ Categorizing without posting rationale ❌ Making decisions without documenting reasoning ❌ Ignoring feedback without explicit comment ❌ Working through feedback without acknowledging receipt

Remember

The PR comment thread is the permanent record. Future you, future maintainers, and future AI agents will read it. Make it tell the complete story.

平台分布

Codex

38.2%
按下载量换算65

Claude

30.16%
按下载量换算52

Cursor

18.08%
按下载量换算31

Gemini CLI

8.94%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

未通过

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/phrazzld/claude-config --skill respond 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。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