Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计通过

batch-issues批次问题

Agent Skill

用于围绕 GitHub 仓库、Issue、Pull Request、分支、提交和代码协作流程提供辅助能力。它适合让 Agent 查询项目状态、整理变更、辅助创建或检查协作事项,并把仓库中的信息转成可执行的下一步。使用时需要区分只读查询和写入操作;涉及创建 PR、修改 Issue、推送分支或访问私有仓库时,应确认 token 权限、目标仓库范围和用户授权。

总安装

282

周安装

12

GitHub Stars

公开资料未说明

下载量

99
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:batch-issues(批次问题)
来源仓库:https://github.com/vitadynamics/vita-cc-market
仓库路径:skills/batch-issues
安装命令:
npx skills add https://github.com/vitadynamics/vita-cc-market --skill batch-issues
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/vitadynamics/vita-cc-market --skill batch-issues

简介

batch-issues 用于将计划文件拆解为小型 GitHub Issue,便于任务分解与跟踪。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中管理开发工作流与协作事项。
  • 自动估算工时(1–4 小时/任务),映射到单一实现点并生成标准 Issue。
  • 安装命令:npx skills add https://github.com/vitadynamics/vita-cc-market --skill batch-issues。
  • 需确保 gh CLI 已认证,且对目标仓库有写入 Issue 的权限。

SKILL.md

Batch Issues Skill

Purpose: Read one or more plan files and decompose them into a set of small, actionable GitHub issues. Each issue maps to a single concrete implementation task estimated at 1-4 hours of work.

Arguments

${ARGUMENTS} — optional path(s) to plan file(s). If omitted, the skill lists available plans and lets the user choose.


Workflow

0. Pre-flight check

  1. Verify gh is available and authenticated: gh auth status If not authenticated, print: gh CLI is not authenticated. Run gh auth login and try again. Then stop.
  2. Identify the current GitHub repo context: gh repo view --json name,owner,defaultBranchRef

1. Select plan file(s)

  • If ${ARGUMENTS} contains file paths, use those directly.
  • Otherwise, list all files under docs/plans/: ls docs/plans/ Use AskUserQuestion to present the list and let the user pick one or more files (multiple selection enabled).
  • If docs/plans/ is empty or absent, ask the user to paste or describe the plan content directly.

2. Analyse each plan — parallel agents

For each selected plan file, spawn a Task (general) agent with the following prompt:

You are an issue decomposition analyst. Read the plan at <path> and produce a JSON array of actionable GitHub issues.

Rules:
- One issue per concrete implementation task (roughly 1-4 hours of work).
- Tasks that are larger than 4h MUST be split further.
- Group tasks into logical work packages: backend, frontend, infra, test, docs, chore.
- Preserve traceability — reference the originating plan section in each issue body.

For each issue output:
{
  "title": "<conventional-commit-style title, e.g. feat: add OAuth callback endpoint>",
  "work_package": "<backend|frontend|infra|test|docs|chore>",
  "effort": "<S|M|L>",   // S = <2h, M = 2-4h, L = >4h (flag, should be split)
  "body": "<markdown body — see body template below>",
  "labels": ["<type>", "effort:<S|M|L>"],
  "milestone": "<inferred from plan filename or section, or null>"
}

Body template:
## Overview
<1-2 sentence description of the task>

## Acceptance Criteria
- [ ] <specific, testable criterion>
- [ ] ...

## Context
<relevant background, references to plan sections, file paths, or related issues>

Collect all agent outputs and merge into a single flat issue list.

3. Present issue list for review

Display the full list in a readable table:

#  | Work Package | Effort | Title
---|--------------|--------|-------
1  | backend      | M      | feat: add OAuth callback endpoint
2  | backend      | S      | chore: add env var for OAuth client secret
...

Flag any effort: L items with a warning:

⚠ Issue #N has effort L — consider splitting it before creating.

Use AskUserQuestion to ask:

"Here are the N issues I've derived from the plan(s). How would you like to proceed?"

Options:

  • Create all issues — proceed immediately
  • Edit before creating — show full issue details; let user adjust titles, bodies, or remove items
  • Cancel — exit without creating anything

4. Create labels & milestone (if needed)

Before creating issues:

  1. Fetch existing labels: gh label list --json name --jq '.[].name'
  2. For each required label not yet present, create it: gh label create "<label>" --color "<auto-pick color>" --description "<description>" Use these default colors: Label Color enhancement #a2eeef bug #d73a4a chore #e4e669 test #0075ca docs #cfd3d7 effort:S #c2e0c6 effort:M #fef2c0 effort:L #f9d0c4
  3. If a milestone was inferred, check whether it exists: gh milestone list --json title --jq '.[].title' If not, create it: gh milestone create --title "<milestone>" --description "Auto-created by batch-issues skill"

5. Create GitHub issues

For each issue in the approved list:

gh issue create \
  --title "<title>" \
  --body "<body>" \
  --label "<label1>" --label "<label2>" \
  [--milestone "<milestone>"]

Print progress as each issue is created:

✓ Created #42 — feat: add OAuth callback endpoint
✓ Created #43 — chore: add env var for OAuth client secret
...

6. Summary & post-creation options

Print a summary table linking each created issue:

Created N issues:
#42  [M] feat: add OAuth callback endpoint          → https://github.com/...
#43  [S] chore: add env var for OAuth client secret → https://github.com/...

Use AskUserQuestion to present options:

"All N issues created. What next?"

Options:

  1. Open issues in browser — run gh issue list --web
  2. Start /core:work — begin implementing the first issue
  3. Done — exit

Error Handling

SituationAction
gh not installedPrint install instructions: brew install gh
Not authenticatedPrint gh auth login and stop
No remote GitHub repoPrint gh repo create suggestion and stop
Plan file not foundAsk user to verify path or paste content directly
Issue creation failsPrint the error, skip that issue, continue with the rest, list failures at end

Key Principles

  • One task per issue — resist bundling; small issues are easier to assign, review, and ship
  • Effort L is a smell — always flag and encourage splitting before creation
  • Traceability — every issue body must reference the source plan section
  • Review before create — never create issues without user confirmation
  • Idempotent-friendly — if the same plan is run twice, remind the user to check for duplicates (gh issue list --search "<title>") before confirming creation

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

38.05%
按下载量换算38

Claude

26.82%
按下载量换算27

Cursor

20.46%
按下载量换算20

Gemini CLI

8.73%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。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