Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问许可证需确认审计提醒

pr-feedback-classifier公关反馈分类器

Agent Skill

pr-feedback-classifier 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。

总安装

1,648

周安装

68

GitHub Stars

81

下载量

539
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:pr-feedback-classifier(公关反馈分类器)
来源仓库:https://github.com/dagster-io/erk
仓库路径:skills/pr-feedback-classifier
安装命令:
npx skills add https://github.com/dagster-io/erk --skill pr-feedback-classifier
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/dagster-io/erk --skill pr-feedback-classifier

简介

pr-feedback-classifier 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 中围绕仓库状态、代码变更或协作事项进行整理。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 确认具体用法。
  • 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。

SKILL.md

PR Feedback Classifier

Classify PR review feedback by filling in semantic fields from mechanical CLI output.

Steps

  1. Run mechanical classification: erk exec classify-pr-feedback [--pr <number>] [--include-resolved] Pass --pr <number> if specified in $ARGUMENTS. Pass --include-resolved if specified in $ARGUMENTS. This returns JSON with mechanically pre-classified items:

- review_submissions: PR-level reviews (classification: "actionable" | "informational" | "needs_llm") - review_threads: Inline review threads (pre_existing_candidate flag set for bot + restructured) - discussion_comments: Discussion comments (classification: "informational" | "needs_llm") - restructured_files: Renamed/moved files detected by git diff - mechanical_informational_count: Items already filtered as informational by CLI

  1. Fill in semantic fields for items that need LLM judgment: For each item:

- review_submissions with classification "needs_llm": Determine if actionable or informational - All actionable items (review_submissions, review_threads, discussion_comments): Write action_summary (brief description of requested change) - All actionable items: Assign complexity (local/single_file/cross_cutting/complex) - Threads with pre_existing_candidate=true: Confirm if truly pre-existing (generic code quality issue, not specific to restructuring). If confirmed, set complexity to "pre_existing"

  1. Construct final JSON output with batches grouped by complexity.

Complexity Levels

  • local: Single line change at specified location
  • single_file: Multiple changes in one file
  • cross_cutting: Changes across multiple files
  • complex: Architectural changes
  • pre_existing: Bot comment on moved/restructured code (auto-resolve candidate)

Batch Ordering

  1. Pre-Existing (Auto-Resolve) (auto_proceed: true)
  2. Local Fixes (auto_proceed: true)
  3. Single-File (auto_proceed: true)
  4. Cross-Cutting (auto_proceed: false)
  5. Complex (auto_proceed: false)
  6. Informational (auto_proceed: false)

Output Format

Output ONLY the following JSON (no prose, no markdown, no code fences):

{
  "success": true,
  "pr_number": 5944,
  "pr_title": "Feature: Add new API endpoint",
  "pr_url": "https://github.com/owner/repo/pull/5944",
  "actionable_threads": [
    {
      "thread_id": "PRR_kwDOPxC3hc5q73Nd",
      "type": "review_submission",
      "path": null,
      "line": null,
      "is_outdated": false,
      "classification": "actionable",
      "pre_existing": false,
      "action_summary": "Reviewer requested changes: fix the authentication flow",
      "complexity": "cross_cutting",
      "original_comment": "The authentication flow is broken for edge cases..."
    },
    {
      "thread_id": "PRRT_kwDOPxC3hc5q73Ne",
      "type": "review",
      "path": "src/api.py",
      "line": 42,
      "is_outdated": false,
      "classification": "actionable",
      "pre_existing": false,
      "action_summary": "Add integration tests for new endpoint",
      "complexity": "local",
      "original_comment": "This needs integration tests"
    },
    {
      "thread_id": "PRRT_kwDOPxC3hc5q73Nf",
      "type": "review",
      "path": "src/api.py",
      "line": 55,
      "is_outdated": false,
      "classification": "actionable",
      "pre_existing": true,
      "action_summary": "Bot suggestion: add unit tests for error handling paths",
      "complexity": "pre_existing",
      "original_comment": "Consider adding unit tests for the error handling paths in this endpoint"
    }
  ],
  "discussion_actions": [
    {
      "comment_id": 12345678,
      "action_summary": "Update API documentation",
      "complexity": "cross_cutting",
      "original_comment": "Please update the docs to reflect..."
    }
  ],
  "informational_count": 12,
  "batches": [
    {
      "name": "Pre-Existing (Auto-Resolve)",
      "complexity": "pre_existing",
      "auto_proceed": true,
      "item_indices": [1]
    },
    {
      "name": "Local Fixes",
      "complexity": "local",
      "auto_proceed": true,
      "item_indices": [0]
    },
    {
      "name": "Single-File",
      "complexity": "single_file",
      "auto_proceed": true,
      "item_indices": []
    },
    {
      "name": "Cross-Cutting",
      "complexity": "cross_cutting",
      "auto_proceed": false,
      "item_indices": []
    }
  ],
  "error": null
}

Field notes:

  • thread_id: The ID needed for erk exec resolve-review-thread
  • comment_id: The ID needed for erk exec reply-to-discussion-comment
  • type: "review" for inline thread comments, "review_submission" for PR-level review submissions, "discussion" for discussion actions
  • classification: "actionable" or "informational" — determines how the user handles the thread
  • pre_existing: true if the issue existed before this PR (bot comment on moved/restructured code). Pre-existing threads use complexity: "pre_existing" and are placed in the first batch for auto-resolution
  • item_indices: References into actionable_threads (type=review or review_submission) or discussion_actions (type=discussion)
  • original_comment: First 200 characters of the comment text
  • informational_count: Count of informational items — includes items filtered by CLI plus any you classify as informational

Error Case

If no PR exists for the branch or API fails:

{
  "success": false,
  "pr_number": null,
  "pr_title": null,
  "pr_url": null,
  "actionable_threads": [],
  "discussion_actions": [],
  "informational_count": 0,
  "batches": [],
  "error": "No PR found for branch feature-xyz"
}

No Comments Case

If PR exists but has no unresolved comments:

{
  "success": true,
  "pr_number": 5944,
  "pr_title": "Feature: Add new API endpoint",
  "pr_url": "https://github.com/owner/repo/pull/5944",
  "actionable_threads": [],
  "discussion_actions": [],
  "informational_count": 0,
  "batches": [],
  "error": null
}

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.66%
按下载量换算187

Claude

28.99%
按下载量换算156

Cursor

17.97%
按下载量换算97

Gemini CLI

8.75%
按下载量换算47

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills