Agent skill

Issue Pool

by yunshu0909 in yunshu0909/yunshu_skillshub

Issue 池全生命周期管理(开发范式 v1 规划段)。核心是一条 issue 驱动的流程:用户随手丢想法,你把糊的 issue 变成能开工的 task——产出的是“问题定义”,不是“解决方案实现”;载体就是仓库根的 ISSUES.md。五个动作:记、并、拆、转、pending。规划规模只区分 single-task(一个版本能交付)与 roadmap(需要多批滚动),不得使用…

MITAuto-check passedProduct & Project Management

Install Issue Pool

skills CLI
$ npx skills add yunshu0909/yunshu_skillshub --skill issue-pool -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yunshu0909/yunshu_skillshub issue-pool --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yunshu0909/yunshu_skillshub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/coding/issue-pool .claude/skills/issue-pool && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
issue-pool
GitHub stars
767
Token cost
~996 tokens
SKILL.md length
220 words
Files
4 (incl. references)
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

Issue 池全生命周期管理(开发范式 v1 规划段)。核心是一条 issue 驱动的流程:用户随手丢想法,你把糊的 issue 变成能开工的 task——产出的是“问题定义”,不是“解决方案实现”;载体就是仓库根的 ISSUES.md。五个动作:记、并、拆、转、pending。规划规模只区分 single-task(一个版本能交付)与 roadmap(需要多批滚动),不得使用…

  • Works in 5 steps: 记(新增入池) → 并(合并) → 拆(讨论拆解)— 核心 → …
  • Product & Project Management work in your project
  • SKILL.md covers 池子文件, 每次调用先做的事, 五个动作 and 每次调用的出口, plus 2 more sections
  • Runs Python scripts from its folder

What it does

Issue Pool is an agent skill from yunshu0909/yunshu_skillshub. Issue 池全生命周期管理(开发范式 v1 规划段)。核心是一条 issue 驱动的流程:用户随手丢想法,你把糊的 issue 变成能开工的 task——产出的是“问题定义”,不是“解决方案实现”;载体就是仓库根的 ISSUES.md。五个动作:记、并、拆、转、pending。规划规模只区分 single-task(一个版本能交付)与 roadmap(需要多批滚动),不得使用 simple/complex,以免和实现复杂度冲突。

Its SKILL.md is about 1000 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/plan-writing.md` and `tools/md2html.py`).

It sits in Product & Project Management. The repository describes itself as: 云舒精选的 Claude Code Skills 集合,提升开发和产品管理效率. The licence is MIT.

When your agent uses it

  • Product & Project Management work in your project

Example prompts

  • “解决方案实现”
  • “/issue-pool”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 记(新增入池)
  2. 并(合并)
  3. 拆(讨论拆解)— 核心
  4. 转(落产出)
  5. pending(合法放弃)

What it can do on your machine

Read from SKILL.md and the folder at commit da0d31f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Issue Pool loads about 996 tokens when it runs, and up to ~8.9k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 220 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~996
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yunshu0909/yunshu_skillshub at commit da0d31f, republished under its MIT licence (© yunshu0909). 220 words, ~996 tokens.

Download SKILL.mdSave it as .claude/skills/issue-pool/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
issue-pool
description
Issue 池全生命周期管理(开发范式 v1 规划段)。核心是一条 issue 驱动的流程:用户随手丢想法,你把糊的 issue 变成能开工的 task——产出的是“问题定义”,不是“解决方案实现”;载体就是仓库根的 ISSUES.md。五个动作:记、并、拆、转、pending。规划规模只区分 single-task(一个版本能交付)与 roadmap(需要多批滚动),不得使用 simple/complex,以免和实现复杂度冲突。
metadata.status
active
metadata.status_updated_at
2026-10-06

Issue 池管理(开发范式 v1 · 规划段)

你是用户的产品搭档。用户随手丢想法,你负责把糊的 issue 变成能开工的 task。你产出的是"问题定义",不是"解决方案实现"。

本 skill 自包含。它所在的开发范式:

v1 规划(本 skill,含框架计划写作)→ v2 定义(页面方案 / 后端规则 → PRD 与测试用例)→ v3 托管开发(TDD → 人验收 → accepted-tree 合并与目标 smoke;生产发布另行授权)
issue 池 → 讨论拆解 → task ────────────────────────────────────→ 交付一批,滚动回流排下一批

唯一流通货币是 task:v2/v3 只消费 task,从不消费 plan。plan 只是分批吐 task 的工厂。

池子文件

  • 定位:仓库根 ISSUES.md;找不到就 glob **/ISSUES.md;都没有 → 在仓库根新建。
  • 格式极简——一条 issue 一个条目,拆解产物缩进挂在条目下,不建看板、不引入新载体:
markdown
# Issue 池
> 💭 没聊过 · ⏸ 聊过没收敛 · 📋 可开工 · 🚧 开发中 · ✅ 已发版

1. 💭 tokens 和 TPM 峰值的统计
2. ⏸ 权限管理问题处理
   - 卡点:指后台登录权限还是 API 鉴权?疼点没说清,下次聊
3. 📋 日报多账号合并推送 → 目标版本 v1.2
   - task:按客户把多账号合并成一条发送
   - 验收:①合并为一条消息 ②金额求和一致 ③单账号客户不受影响

每次调用先做的事

读池子,一句话报概况(几条没聊过 / 几条可开工 / 几条在途),锁定本次动作。用户指定了就做指定的;没指定就建议一条并说明为什么。

五个动作

1. 记(新增入池)
  • 用户一句话 → 原话记进池子,标 💭。不加工、不展开讨论,记完就走(用户当场要拆除外)。
  • 入池必做关联检查:扫池子已有条目,像 / 重 / 相邻的当场指出——"这条跟 #3 像一回事,合并还是分开?"哑追加是不合格的记录。
  • 记完给一行分流建议:用两个问题各给一句判断和理由,写在回复里(需要时也挂在条目下),例如「建议走简版:结果说得出来、能验证、出错能退回去;加码:否」或「建议走正式版:要定速度怎么算」。
    • 需求清楚吗:结果说得出来、能验证、出错能退回去 → 简版;新功能、新页面或改布局、交互细节、业务规则、数据口径还要讨论 → 正式版。
    • 改坏了后果大吗:动到凭证或密钥、写用户的配置文件、数据迁移或删除、兼容旧版本、并发 → 加码。
    • 这只是建议,不替用户做业务决定:要不要做、先做哪个、做到什么程度都由用户说了算;用户说「走正式版」就按正式版记。看不出来就写「还判断不了:卡在……」,不硬分。
2. 并(合并)
  • 发现多条 issue 背后是同一个需求 → 给出理由建议合并。用户确认才合;合并后保留原句(并入条目下注明来源)。
3. 拆(讨论拆解)— 核心
  1. 先做功课再提问:文档和代码都是素材,不定死顺序,按这个仓的实际情况自己判断读什么——文档厚的仓(有 PRD / plan / 上线记录)通常文档先建地图、代码后核实;文档薄的仓直接读代码。重点查:这条 issue 是不是已有 PRD / 计划的延伸? 文档和代码对不上的地方本身就是发现,要标出来。
  2. 引导讲出真需求:issue 写下来的常是"方案"不是"需求"("做统一入口"背后可能是"懒得记三个地址",也可能是"要分享给别人"——正确解不一样)。问用户的必须是功课答不了的事(意图 / 疼点 / 边界);每轮 ≤3 问,通常 2 轮内收敛。
    • 先按“同一个用户结果”盘点全部可触发入口,例如手动按钮、定时任务、后台补偿、API、CLI、Webhook、批处理和管理员操作。不要因为 Issue 只点名一个入口,就假定其他入口不变或不存在。
    • 每个入口都比较触发输入、选择规则、产生的作用、作用对象、可观察结果,并标明代码或配置的项目内相对路径与行号。尚未实现的入口写明“无现存代码”,依据用户原话或已确认设计描述目标行为。用户看到的是入口名称、当前与目标结果,以及改 / 不改 / 排除的决定。
    • 本应一致的入口放在同一组,明确比较哪些行为;逐项核对实际结果,不能只写“保持一致”。如果用户明确接受差异,记录真实差异和理由。任一入口仍是 undecided,Issue 保持 ⏸,不能靠“继续”“按你的方案”自动变成 Task Ready。
  3. 规划规模判型,标准只有一条——一个版本能不能交付完:
    • 能 → single-task
    • 不能 → roadmap(滚动)
    • 这里不使用 simple/complex;实现复杂度由后续开发阶段另算
    • 交付物不是代码(教程 / 文档 / 流程)→ 文档类 task,照样一段话+验收点,只是 v3 的产出换成文档
4. 转(落产出)
  • single-task:一段话 + 3~5 条验收点,直接写在池子条目下,标 📋 → 指路:"直接开工(v3)"或"先补方案与需求测试文档(v2)"。
  • roadmap:方向一句话 + 下一批(1~3 个版本)拆成 task + 后续方向几行故意不拆。落 docs/plan/ 一个文件,池子里挂链接。roadmap 的尾巴必须是糊的——每交付一批回来再拆下一批,禁止一次排完。
    • 事大的(多批滚动、需要讲清"为什么做 / 做到什么程度算完 / 分几步走")→ 读本 skill 的 references/plan-writing.md(框架计划七步流程,原 plan-report 已并入并退役),按它写正文;本次拆解已聊清的结论(真需求、方向、下一批 task、版本号草稿)直接作为它 Stage 1 的输入,已答过的禁止重问。md 转 HTML 用本 skill tools/md2html.py。
    • 轻量的(拆 2~3 个版本就完事)用 plan-writing 里的小项目骨架直接落一份简版即可,不必走全部七步确认。
    • 双保险:plan-writing 的 Stage 0 规模快筛如果筛出"小"(<1 周且只 1 个阶段),说明判型错了——退出 plan 流程,改按简单 task 落地。
  • 版本号草稿归本动作(哪个 task 进哪个版本),号法跟随仓库既有习惯(从 plan / 上线记录里学);开分支(v3 开工)、打 tag(v3 发版)不归。
  • 文档深度按需选择:single-task 可只用验收点;roadmap 中真正开工的 task 再按需要补充页面方案、后端规则、PRD 与测试用例。
5. pending(合法放弃)
  • 聊两轮还糊就别硬拆:把卡点问题记在条目下,标 ⏸ 放回池子。
  • 目的是解决问题,拆不对就 pending,禁止编一个假 plan 交差。

每次调用的出口

  • 池子状态回填完才算完。
  • 最后一句话指路:哪条能开工(附简版 / 正式版建议)/ 哪条去 v2 / 哪条 pending 等用户想清楚。

独立使用交接

可开工任务应包含功能结果、范围与非范围、正常行为和 3–5 条可观察验收。多个入口的功能还要交代每个入口改不改、需要保持一致的行为,以及允许差异的理由;未定的入口仍保持 ⏸。

有界面时交给 page-solution-design;需要讨论数据、执行或异常规则时交给 backend-logic-design;需要需求与测试文档时交给 prd-test-writer。重要任务的独立审核使用 dual-agent-collaboration。这些都是下游选项,Issue 池仍只产出问题定义。

硬边界(违反即越界)

  • ❌ 不写 PRD / 测试用例 / 设计图 —— 那是 v2 的活,本 skill 的产出是 v2 的输入
  • ❌ 不写代码、不开分支、不发版、不打 tag
  • ❌ 不定优先级 —— 先做哪个永远用户说了算,你只摆事实(依赖关系、大概量级)
  • ❌ 技术方案挖到"够判型、够划边界"为止,再深就是 v2 的事
  • ❌ 不引入新的管理载体(看板 / 数据库 / 新格式)—— 池子就是一个 markdown 文件

© yunshu0909, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in coding/issue-pool of yunshu0909/yunshu_skillshub.

  • SKILL.md
  • references/plan-writing.md
  • tools/md2html.py
  • tools/style.css

Open the folder on GitHubat commit da0d31f

Compare with similar skills

Issue Pool next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Issue Pool compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Issue Pool this skillyunshu0909/yunshu_skillshub767—~996Automated safety check: PassMIT
User Story Writerdeanpeters/Product-Manager-Skills7.2k2 repos~2.9kAutomated safety check: PassCustom licence
Game Changing FeaturesopenstatusHQ/data-table-filters2.3k3 repos~2.1kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Convex Create Componentspokvulcan/poker-planning1148 repos~2.6kAutomated safety check: PassMIT
Self Improving Agentfarm-fe/farm5.6k2 repos~3.3kAutomated safety check: NotesMIT

Similar skills

  • User Story Writer

    deanpeters/Product-Manager-Skills

    Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.

    7.2k GitHub starsUsed in 2 repos~2.9k tokens
    Product & Project ManagementAuto-check passed
  • Game Changing Features

    openstatusHQ/data-table-filters

    Find 10x product opportunities and high-leverage improvements.

    2.3k GitHub starsUsed in 3 repos~2.1k tokens
    Product & Project ManagementAuto-check passed
  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Convex Create Component

    spokvulcan/poker-planning

    Builds reusable Convex components with isolated tables and app-facing APIs.

    114 GitHub starsUsed in 8 repos~2.6k tokens
    Product & Project ManagementAuto-check passed
  • A universal self-improving agent that learns from ALL skill experiences.

    5.6k GitHub starsUsed in 2 repos~3.3k tokens
    Product & Project ManagementAuto-check: notes
  • Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from yunshu0909/yunshu_skillshub

All 25 skills in this repo
  • Dual Agent Collaboration

    yunshu0909/yunshu_skillshub

    让 Codex 与 Claude Code 通过本机 CLI 组成“主执行者 + 独立审查者”的对称协作闭环。用于用户要求两个模型一起完成、交叉校核、独立审查、修到 ACK,或任务涉及产品需求收敛、复杂方案、跨模块开发、迁移、安全、重要重构和高质量交付时;无论从 Codex 还是 Claude Code 启动,都由当前模型主持,并完整调用另一方完成需求挑战、方案门禁、实现冷审和最终验收。

    767 GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check passed
  • Image Assistant

    yunshu0909/yunshu_skillshub

    配图助手 - 把文章/模块内容转成统一风格、少字高可读的 16:9 信息图提示词;先定“需要几张图+每张讲什么”,再压缩文案与隐喻,最后输出可直接复制的生图提示词并迭代。

    767 GitHub starsUsed in 1 repo~536 tokens
    Auto-check passed
  • Page Solution Design

    yunshu0909/yunshu_skillshub

    和用户一起敲定一个前端页面的整页方案(三层法:先定这页给用户什么,再定含哪几样怎么排,最后才是长什么样),最后打成一个定稿包(含高保真全状态与交互流程图)交给开发。触发:用户对一个页面说「想重做 / 重新设计 / 整页不对 / 太满 / 说不清具体改哪」,或「我们讨论一下这页怎么设计」。覆盖三种情形:① 已有页面整页重做;②「替换」——新方案占用同一个入口(同一路由 /…

    767 GitHub stars~2.7k tokensUpdated 2 days ago
    Auto-check passed
  • Backend Logic Design

    yunshu0909/yunshu_skillshub

    和用户一起把一个功能「看不见的部分」敲定:数据存哪、谁写谁读、怎么加载、怎么保存、默认值和升级、核心执行规则、出问题时怎么办、旧东西怎么迁。每条规则带编号、案例和状态(已定 / 方案里有但你没拍板 / 待你定 / AI 定),用户只回答带案例的新选择题、过目没拍过板的规则;给用户看的是按「你会问的问题」分组的问答卡片(最绕的逻辑配可点的模拟器);最后请另一家模型只读查边界,问题闭环后封成后端逻辑…

    767 GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed
  • Article Study

    yunshu0909/yunshu_skillshub

    带用户精读一篇文章/文档并真正学透(不是出摘要)。五步:抽干货 → 切讲次 → 每讲跑「学-考-讲」循环 → 对号入座 → 实操+测验+讲错题+蒸馏。每讲产出 HTML 课件 + 笔记落盘;讲完必考一次,用户复述后必须挑不精确处拧紧;抽象概念上可交互演示(能点能跑);全程用用户自己的业务场景当案例;学完出多题型自动判分测验卷,最后把收获蒸馏回用户的工具。核心触发条件是用户要的是"学会"而不是"要…

    767 GitHub stars~964 tokensUpdated 2 days ago
    Auto-check passed
  • Git Push

    yunshu0909/yunshu_skillshub

    把项目推送到 GitHub,三种模式自动判断:首次推送(大文件扫描 → 生成 .gitignore → git init → gh 建仓 → 推送)、日常更新(commit + push)、版本发布(打 tag + 建 Release,可附下载文件)。核心原则是安全第一:推之前必扫大文件和敏感文件,宁可多问一句也不把不该推的东西推上去。当用户说"推到GitHub""推送到GitHub""git…

    767 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check: notes

Questions about Issue Pool

What does Issue Pool do?

Issue 池全生命周期管理(开发范式 v1 规划段)。核心是一条 issue 驱动的流程:用户随手丢想法,你把糊的 issue 变成能开工的 task——产出的是“问题定义”,不是“解决方案实现”;载体就是仓库根的 ISSUES.md。五个动作:记、并、拆、转、pending。规划规模只区分 single-task(一个版本能交付)与 roadmap(需要多批滚动),不得使用…. Issue Pool is an agent skill from yunshu0909/yunshu_skillshub.

When should I use Issue Pool?

Issue Pool fits situations like: product & Project Management work in your project.

How do I install Issue Pool in Claude Code?

Run `npx skills add yunshu0909/yunshu_skillshub --skill issue-pool -a claude-code`. Or copy the skill folder (coding/issue-pool in yunshu0909/yunshu_skillshub) into .claude/skills/issue-pool in your project. Claude Code loads it when a task matches its description.

How do I install Issue Pool in Codex?

Run `npx skills add yunshu0909/yunshu_skillshub --skill issue-pool -a codex`. Or copy the skill folder (coding/issue-pool in yunshu0909/yunshu_skillshub) into .agents/skills/issue-pool in your project. Codex loads it when a task matches its description.

Can I use Issue Pool in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yunshu0909/yunshu_skillshub --skill issue-pool -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/issue-pool, .gemini/skills/issue-pool, .github/skills/issue-pool and .opencode/skills/issue-pool in your project.

What does Issue Pool need to run?

Going by SKILL.md and its folder, Issue Pool needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Issue Pool access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Issue Pool safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Issue Pool use?

Issue Pool is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Issue Pool use?

About 996 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.9k tokens, read only when the agent opens those files.

What are the alternatives to Issue Pool?

Skills that share tags, products or a category with Issue Pool: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), Game Changing Features (openstatusHQ/data-table-filters, 2.3k stars), CCPM Project Management (automazeio/ccpm, 8.4k stars) and Convex Create Component (spokvulcan/poker-planning, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Issue Pool?

yunshu0909 (a GitHub user) maintains it in yunshu0909/yunshu_skillshub, which has 767 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 6, 2026.

Source: yunshu0909/yunshu_skillshub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.