Token导航 LogoToken导航TokenDH.com
运维和基础设施需要联网github未标认证来源可访问clear审计提醒

pr-resolver公关解析器

Agent Skill

pr-resolver 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

857

周安装

35

GitHub Stars

52

下载量

277
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

3

许可证

MIT

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-resolver(公关解析器)
来源仓库:https://github.com/zenobi-us/dotfiles
仓库路径:skills/pr-resolver
安装命令:
npx skills add https://github.com/zenobi-us/dotfiles --skill pr-resolver
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/zenobi-us/dotfiles --skill pr-resolver

简介

pr-resolver 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 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操作。
  • 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

GitHub PR Resolver

Automate the process of addressing pull request review feedback by processing ALL comments, making code fixes, resolving EVERY conversation thread, and fixing ALL failing CI checks.

This skill does NOT skip any comments. Every unresolved thread must be addressed and resolved.

Prerequisites

# Verify gh CLI is installed and authenticated
gh auth status

# If not authenticated, run:
gh auth login

Token requires repo scope for full repository access.

Workflow Overview

  1. Fetch PR context → Get all review threads and check statuses (always fresh from GitHub)
  2. Process ALL unresolved threads → For EACH thread: fix → commit → resolve → repeat
  3. Fix ALL failing checks → Address every failure, commit per check type
  4. Push changes → Single push after all commits
  5. Verify → Re-fetch from GitHub and confirm ALL threads resolved and ALL checks passing

COMMIT CADENCE (NON-NEGOTIABLE):

  • Each review thread = 1 commit (fix → git addgit commit → resolve thread → next thread)
  • Each CI check type = 1 commit (lint fixes, test fixes, build fixes are separate commits)
  • NEVER batch all changes into a single commit at the end

CRITICAL REQUIREMENTS:

  • Always fetch fresh data from GitHub. Never use cached or previously fetched context.
  • Process EVERY unresolved comment. Do NOT skip any threads. Each comment must be addressed and resolved.
  • Zero unresolved threads is the only acceptable end state.

Commit Convention

Each change gets its own commit using conventional commit format:

<type>(<scope>): <description>

Type inference from comment:

Comment PatternCommit Type
Bug fix, null check, error handling, validationfix
Add, include, missing, implementfeat
Rename, refactor, suggestion, change X to Yrefactor
Documentation, comments, READMEdocs
Performance, optimizeperf
Style, indent, whitespacestyle

Scope from file path:

  • Extract directory/module name: src/services/UserService.tsservices
  • Skip common prefixes: src, lib, app
  • Root files use filename: index.tsindex

CI check commits:

  • Lint fixes → fix(lint): resolve linting errors
  • Test fixes → fix(tests): update failing assertions
  • Build/type errors → fix(build): resolve build errors
  • Formatting → style(format): apply formatting

Step 1: Fetch PR Context (Always Fresh)

CRITICAL: Always fetch fresh data from GitHub. Never reuse previously fetched context data.

1.1 Get PR Details

# Get PR metadata
gh pr view <PR_NUMBER> --json number,title,state,headRefName,baseRefName,author,url

1.2 Get Review Threads (GraphQL with Pagination)

Use GraphQL to fetch review threads with resolution status. The API returns max 100 items per request, so pagination is required for PRs with many threads.

# First page (no cursor)
gh api graphql -f query='
query($owner: String!, $repo: String!, $prNumber: Int!, $cursor: String) {
  repository(owner: $owner, name: $repo) {
    pullRequest(number: $prNumber) {
      reviewThreads(first: 100, after: $cursor) {
        pageInfo {
          hasNextPage
          endCursor
        }
        nodes {
          id
          isResolved
          isOutdated
          path
          line
          comments(first: 100) {
            nodes {
              id
              databaseId
              body
              author { login }
              createdAt
              path
              line
              diffHunk
            }
          }
        }
      }
    }
  }
}' -f owner=OWNER -f repo=REPO -F prNumber=PR_NUMBER

Handling pagination:

# Check if more pages exist
HAS_NEXT=$(echo "$RESULT" | jq '.data.repository.pullRequest.reviewThreads.pageInfo.hasNextPage')
END_CURSOR=$(echo "$RESULT" | jq -r '.data.repository.pullRequest.reviewThreads.pageInfo.endCursor')

# If hasNextPage is true, fetch next page with cursor
if [ "$HAS_NEXT" = "true" ]; then
  gh api graphql -f query='...' -f owner=OWNER -f repo=REPO -F prNumber=PR_NUMBER -f cursor="$END_CURSOR"
fi

IMPORTANT: Continue fetching pages until hasNextPage is false. Collect ALL threads before processing.

1.3 Get Check Status

# Get all checks for the PR
gh pr checks <PR_NUMBER>

# For detailed check information
gh pr checks <PR_NUMBER> --json name,state,conclusion,description

1.4 Parse the Context

After fetching, identify:

  • Unresolved threads: Where isResolved: false
  • Failing checks: Where conclusion is failure, cancelled, timed_out, or action_required
# Count unresolved threads
echo "Unresolved threads: $(echo "$THREADS_JSON" | jq '[.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false)] | length')"

# List failing checks
gh pr checks <PR_NUMBER> --json name,conclusion | jq '.[] | select(.conclusion == "failure")'

Step 2: Process ALL Review Threads

MANDATORY: Process EVERY unresolved thread. Do NOT skip any comments.

For each unresolved thread (iterate through ALL of them):

2.1 Understand the Comment

Extract the first comment (thread initiator) and understand what's requested:

# For each unresolved thread, extract:
# - path: file path
# - line: line number
# - body: comment text
# - thread_id: GraphQL ID for resolution

2.2 Identify Fix Type

ALL comments require action. Determine the appropriate fix:

Comment PatternAction Required
Contains ``` `suggestion ```Apply the suggested code directly
"Typo", "rename", "change X to Y"Make the specific text change
"Add...", "Include...", "Missing..."Add the requested code/content
"Remove...", "Delete..."Remove the specified code
"Consider...", "Maybe...", "Nit:"Apply the improvement (these are still requests)
Question or discussionAddress with code fix or reply, then resolve

No comment is optional. Every thread must be addressed and resolved.

2.3 Apply Code Suggestions

For comments with explicit suggestions, extract and apply:

# Suggestion blocks look like:
# ```suggestion
# replacement code here
# ```

# Extract suggestion content and apply to the file at the specified line

2.4 Make the Fix

  1. Open the file at path
  2. Navigate to line
  3. Apply the required change
  4. Save the file

2.5 Commit the Fix (IMMEDIATELY - DO NOT BATCH)

CRITICAL: Commit IMMEDIATELY after EACH fix. Do NOT wait until the end. Do NOT batch commits.

After making each fix, commit it immediately with a conventional commit message:

# Stage only the affected file
git add <path>

# Commit with conventional message
git commit -m "<type>(<scope>): <description>"

Example commits:

  • refactor(services): rename getUser to fetchUser
  • fix(auth): add null check for token
  • feat(api): add retry logic per review
  • docs(utils): add JSDoc for helper function

2.6 Resolve the Thread

After committing, resolve the thread via GraphQL:

gh api graphql -f query='
mutation($threadId: ID!) {
  resolveReviewThread(input: {threadId: $threadId}) {
    thread {
      id
      isResolved
    }
  }
}' -f threadId="<THREAD_ID>"

REPEAT Steps 2.1-2.6 for EACH unresolved thread. Each thread = 1 commit. Do NOT move to Step 3 until all threads have been processed with individual commits.

Step 3: Fix Failing Checks

3.1 Analyze Failures

# List all failing checks
gh pr checks <PR_NUMBER> --json name,state,conclusion,description | jq '.[] | select(.conclusion == "failure")'

# View workflow run logs for details
gh run view <RUN_ID> --log-failed

3.2 Common Check Fixes

Linting (eslint, pylint, ruff):

# JavaScript/TypeScript
npm run lint -- --fix
npx eslint . --fix

# Python
ruff check --fix .
black .

Type Checking (tsc, mypy, pyright):

  • Fix type errors shown in check output
  • Add missing type annotations
  • Update incorrect types

Tests (jest, pytest, vitest):

  • Read test output to identify failures
  • Fix the failing test or the implementation
  • Update snapshots if needed: npm test -- -u

Formatting (prettier, black):

npx prettier --write .
black .

Build (webpack, vite, tsc):

  • Fix syntax errors
  • Resolve import issues
  • Ensure dependencies are installed

3.3 Commit Each Check Fix

After fixing each check type, commit separately:

# After fixing lint errors
git add .
git commit -m "fix(lint): resolve linting errors"

# After fixing test failures
git add .
git commit -m "fix(tests): update failing assertions"

# After fixing build/type errors
git add .
git commit -m "fix(build): resolve build errors"

# After fixing formatting
git add .
git commit -m "style(format): apply formatting"

3.4 Re-run Checks Locally

Before pushing, verify fixes locally:

# Run the same commands CI runs
npm run lint
npm run test
npm run build

Step 4: Push All Commits

After all review threads and CI checks have been addressed with individual commits, push once:

# Get the branch name
BRANCH=$(gh pr view <PR_NUMBER> --json headRefName -q '.headRefName')

# Push all commits to PR branch
git push origin $BRANCH

This triggers a single CI run for all changes rather than multiple runs per commit.

Step 5: Verify Resolution (Always Re-fetch)

After pushing, ALWAYS fetch fresh data from GitHub to verify - never rely on previously fetched context:

  1. ALL threads show as resolved (zero unresolved remaining)
  2. CI checks are re-running
  3. No new failures introduced
# Re-fetch threads (fresh API call with pagination support)
gh api graphql -f query='
query($owner: String!, $repo: String!, $prNumber: Int!, $cursor: String) {
  repository(owner: $owner, name: $repo) {
    pullRequest(number: $prNumber) {
      reviewThreads(first: 100, after: $cursor) {
        pageInfo {
          hasNextPage
          endCursor
        }
        nodes {
          id
          isResolved
        }
      }
    }
  }
}' -f owner=OWNER -f repo=REPO -F prNumber=PR_NUMBER

# Count remaining unresolved (remember to paginate if hasNextPage is true)
UNRESOLVED=$(echo "$RESULT" | jq '[.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false)] | length')
echo "Remaining unresolved: $UNRESOLVED"

# Check CI status
gh pr checks <PR_NUMBER>

IMPORTANT:

  • Verification MUST use fresh API calls to ensure you see the actual current state on GitHub.
  • If ANY unresolved threads remain, the task is NOT complete. Go back and process them.
  • The only acceptable end state is zero unresolved threads.

Complete Example

#!/bin/bash
# Complete workflow to resolve ALL PR feedback

PR_NUMBER=$1
REPO="owner/repo"  # Or extract from current git remote
OWNER=${REPO%/*}
REPO_NAME=${REPO#*/}

# 1. Fetch fresh context from GitHub
echo "Fetching PR #$PR_NUMBER..."
PR_INFO=$(gh pr view $PR_NUMBER --json number,title,headRefName,baseRefName)
BRANCH=$(echo $PR_INFO | jq -r '.headRefName')
echo "PR: $(echo $PR_INFO | jq -r '.title')"
echo "Branch: $BRANCH"

# Fetch ALL review threads with pagination
ALL_THREADS="[]"
CURSOR=""

while true; do
  if [ -z "$CURSOR" ]; then
    CURSOR_ARG=""
  else
    CURSOR_ARG="-f cursor=$CURSOR"
  fi

  RESULT=$(gh api graphql -f query='
query($owner: String!, $repo: String!, $prNumber: Int!, $cursor: String) {
  repository(owner: $owner, name: $repo) {
    pullRequest(number: $prNumber) {
      reviewThreads(first: 100, after: $cursor) {
        pageInfo {
          hasNextPage
          endCursor
        }
        nodes {
          id
          isResolved
          path
          line
          comments(first: 100) {
            nodes {
              body
              author { login }
            }
          }
        }
      }
    }
  }
}' -f owner=$OWNER -f repo=$REPO_NAME -F prNumber=$PR_NUMBER $CURSOR_ARG)

  # Append threads from this page
  PAGE_THREADS=$(echo $RESULT | jq '.data.repository.pullRequest.reviewThreads.nodes')
  ALL_THREADS=$(echo "$ALL_THREADS $PAGE_THREADS" | jq -s 'add')

  # Check for next page
  HAS_NEXT=$(echo $RESULT | jq -r '.data.repository.pullRequest.reviewThreads.pageInfo.hasNextPage')
  if [ "$HAS_NEXT" != "true" ]; then
    break
  fi
  CURSOR=$(echo $RESULT | jq -r '.data.repository.pullRequest.reviewThreads.pageInfo.endCursor')
done

UNRESOLVED_COUNT=$(echo $ALL_THREADS | jq '[.[] | select(.isResolved == false)] | length')
TOTAL_COUNT=$(echo $ALL_THREADS | jq 'length')
echo "Total threads: $TOTAL_COUNT"
echo "Unresolved threads: $UNRESOLVED_COUNT"

# 2. Checkout PR branch
git fetch origin $BRANCH
git checkout $BRANCH

# 3. Process EACH unresolved thread (Claude does this interactively)
# For each thread:
#   - Read the comment
#   - Make the fix
#   - git add <file>
#   - git commit -m "<type>(<scope>): <description>"
#   - gh api graphql ... resolve mutation
#   - Move to next thread

# 4. Fix failing checks (one commit per check type)
gh pr checks $PR_NUMBER --json name,conclusion | jq '.[] | select(.conclusion == "failure")'
# Fix each failing check type and commit separately

# 5. Push all commits
git push origin $BRANCH

# 6. Verify - re-fetch ALL pages and confirm zero unresolved
# (Use same pagination loop as above)
if [ "$REMAINING" -gt 0 ]; then
    echo "⚠️  WARNING: $REMAINING threads still unresolved!"
    echo "Must go back and process remaining threads."
else
    echo "✅ All threads resolved!"
fi

Reference

See references/github_api_reference.md for:

  • Detailed comment intent patterns
  • CI check types and common fixes
  • API rate limits and error handling
  • Git workflow best practices

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

OpenCode

28.82%
按下载量换算80

Claude Code

23.23%
按下载量换算64

Antigravity

14.64%
按下载量换算41

Gemini CLI

11.57%
按下载量换算32

windsurf

7.84%
按下载量换算22

Codex

3.06%
按下载量换算8

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。

来源信息

继续浏览同类 Skills