backlog-manager
需求池管理。用户随时抛出想法/痛点，AI 负责追问、整理、合并、归档到需求池文件。用户准备开新版本时，协助从池中筛选。痛点驱动，不做提前排期。
Best use case
backlog-manager is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. 需求池管理。用户随时抛出想法/痛点，AI 负责追问、整理、合并、归档到需求池文件。用户准备开新版本时，协助从池中筛选。痛点驱动，不做提前排期。
需求池管理。用户随时抛出想法/痛点，AI 负责追问、整理、合并、归档到需求池文件。用户准备开新版本时，协助从池中筛选。痛点驱动，不做提前排期。
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "backlog-manager" skill to help with this workflow task. Context: 需求池管理。用户随时抛出想法/痛点，AI 负责追问、整理、合并、归档到需求池文件。用户准备开新版本时，协助从池中筛选。痛点驱动，不做提前排期。
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/backlog-manager/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How backlog-manager Compares
| Feature / Agent | backlog-manager | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
需求池管理。用户随时抛出想法/痛点，AI 负责追问、整理、合并、归档到需求池文件。用户准备开新版本时，协助从池中筛选。痛点驱动，不做提前排期。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
用户随时会抛出产品想法、使用痛点、功能需求。AI 负责将这些零散输入整理成结构化的需求池， 并在用户准备启动新版本时协助筛选。需求池是一个持续维护的文件，不是一次性产出。 ## 核心原则 - **痛点驱动** — 只收集真实痛点和明确想法，不做假设性规划 - **AI 整理，用户决策** — AI 负责追问、归类、合并；用户负责确认和拍板 - **先归档，再说做不做** — 新想法先进池子，不急着排优先级或启动开发 - **池子要活** — 定期清理过时条目，升档想清楚的条目，不让池子变成垃圾堆 - **不越界** — 需求池管理到"可以做了"为止，后续的设计/PRD/开发由其他流程接管 ## 需求池文件 **位置**：`docs/需求池.md` 如果文件已存在，在现有内容上更新。如果不存在，按以下模板创建。 ### 文件模板 ``` # 需求池 > 随手记，随时加，隔段时间过一遍。 > > 状态说明： > - **可以做了** — 痛点清晰，知道要做成什么样，随时能进设计/PRD > - **需要想想** — 方向有了，细节没展开，需要调研或讨论 > - **先放着** — 记着就行，现在不花精力想 > - **已完成** — 做完了，标版本号归档 --- ## 总览 | # | 需求 | 状态 | 依赖 | 备注 | |---|------|------|------|------| | 1 | xxx | 可以做了 | 无 | xxx | --- ## 可以做了 ### 需求名称 - 痛点：xxx - 方案：xxx - 备注：xxx --- ## 需要想想 ### 需求名称 - 方向：xxx - 依赖：xxx - 待展开：xxx --- ## 先放着 ### 需求名称 - 想法：xxx - 备注：xxx --- ## 已完成 ### 需求名称（V0.xx） - 完成时间：yyyy-mm-dd - 简述：xxx ``` ### 条目模板说明 每个条目根据所在分区使用不同字段： | 分区 | 必填字段 | 可选字段 | |------|---------|---------| | 可以做了 | 痛点、方案 | 备注 | | 需要想想 | 方向 | 依赖、待展开 | | 先放着 | 想法 | 依赖、备注 | | 已完成 | 完成时间、简述 | — | 总览表每个条目必须有：编号、需求名称、状态、依赖、备注。 ## 工作流程 ### 第 1 步：收集 — 用户抛出新想法 用户说了一个想法或痛点后，主动追问： - **痛点是什么** — 现在遇到了什么问题？什么场景下不爽？ - **频率多高** — 多久碰到一次？ - **现在怎么绕** — 不做这个功能的话，手动怎么解决？ 整理成一句话描述，向用户确认："我理解的是 xxx，对吗？" **禁止**： - 用户说了一句话就直接写进需求池，必须先追问确认 - 追问超过 3 轮还没收敛，先按当前理解归档，标注"待进一步讨论" ### 第 2 步：归类 — 判断状态和合并 1. **读取现有需求池**（如果存在） 2. **检查是否可合并** — 新想法是否和已有条目属于同一个方向？ - 可合并 → 告诉用户"这个和 #X 相关，我建议合并成 xxx"，等用户确认 - 不可合并 → 作为新条目 3. **判断状态** — 根据追问结果归档： - 用户能说清痛点和大致方案 → **可以做了** - 用户有方向但细节模糊 → **需要想想** - 用户自己也说"先记着" → **先放着** 4. **向用户确认归类结果**，用户同意后再写入文件 **禁止**： - AI 自行判断状态不跟用户确认 - 强行合并用户认为不同的需求 ### 第 3 步：写入 — 更新需求池文件 确认后更新 `docs/需求池.md`： 1. 在对应分区添加条目详情 2. 更新总览表（加新行或修改已有行） 3. 如果发生合并，更新被合并条目的内容和总览表 **格式要求**： - 总览表和详情区必须同步更新，不能只改一处 - 编号递增，不复用已删除的编号 - 已完成的条目保留在总览表中，状态标"已完成" ### 第 4 步：整理 — 定期过一遍池子 当用户说"整理一下需求池"或"看看需求池"时： 1. 读取完整需求池文件 2. 逐条过，对每条给出建议： - **过时了** → 建议删除，说明理由 - **想清楚了** → 建议升档（先放着 → 需要想想，或需要想想 → 可以做了），说明依据 - **还是模糊** → 追问 1-2 个关键问题，帮用户想清楚 - **没变化** → 跳过，不废话 3. 用户逐条确认后，批量更新文件 **禁止**： - 没有用户确认就批量修改状态 - 每条都问一遍"要不要改"（没变化的直接跳过） ### 第 5 步：筛选 — 挑下一个版本做什么 当用户说"下一个版本做什么"或"挑一个来做"时： 1. 读取需求池，列出所有"可以做了"的条目 2. 如果"可以做了"为空，从"需要想想"里挑最接近的，帮用户聊清楚 3. 对候选条目，用三个标准分析： | 标准 | 问题 | |------|------| | 频率 | 你多久被这个问题卡一次？ | | 可绕过性 | 不做的话手动能搞定吗？多麻烦？ | | ROI | 做完之后日常能省多少事？ | 4. 给出分析结果，**不替用户做决定**，让用户选 5. 用户选定后，在需求池中标记该条目为"进行中"（或由用户直接进入 design-exploration / PRD 流程） **禁止**： - 替用户决定做哪个 - 给所有条目强行排优先级序号（只在用户要挑的时候才做对比分析） - 用户选完就开始做设计或写 PRD（需求池流程到"选定"为止，后续流程用户自己触发） ### 第 6 步：归档 — 版本完成 当用户说"xxx 做完了"或"标记完成"时： 1. 将条目从当前分区移到"已完成" 2. 补充版本号和完成时间 3. 更新总览表状态 4. 如果该条目被其他条目依赖，检查依赖条目是否可以升档，提醒用户 ## 沟通规范 ### 必须问用户的 | 时机 | 问什么 | |------|--------| | 第 1 步 | 痛点、频率、现在怎么绕 | | 第 2 步 | 合并是否合理、状态归类是否正确 | | 第 4 步 | 每条变更建议是否同意 | | 第 5 步 | 从候选里选哪个 | ### 不需要问用户的 | 事项 | 直接做 | |------|--------| | 文件格式 | 按模板写，不用问 | | 编号分配 | 自动递增 | | 总览表同步 | 改了详情就同步总览表 | | 没变化的条目 | 整理时直接跳过 | ### AI 绝不应该做的 - 替用户决定做哪个需求 - 用户扔了一个想法就开始做设计或写 PRD（先归档，用户说启动才启动） - 自己编造需求内容（必须基于用户原话整理） - 没有用户确认就修改需求池文件 - 给所有条目强行排优先级（只在筛选时做对比分析） - 把需求池当待办清单催用户（池子是被动的，用户主动来才响应）
Related Skills
risk-manager
Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-losses. Use PROACTIVELY for risk assessment, trade tracking, or portfolio protection.
context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI orchestration.
azure-resource-manager-sql-dotnet
Azure Resource Manager SDK for Azure SQL in .NET. Use for MANAGEMENT PLANE operations: creating/managing SQL servers, databases, elastic pools, firewall rules, and failover groups via Azure Resource Manager. NOT for data plane operations (executing queries) - use Microsoft.Data.SqlClient for that. Triggers: "SQL server", "create SQL database", "manage SQL resources", "ARM SQL", "SqlServerResource", "provision Azure SQL", "elastic pool", "firewall rule".
azure-resource-manager-redis-dotnet
Azure Resource Manager SDK for Redis in .NET. Use for MANAGEMENT PLANE operations: creating/managing Azure Cache for Redis instances, firewall rules, access keys, patch schedules, linked servers (geo-replication), and private endpoints via Azure Resource Manager. NOT for data plane operations (get/set keys, pub/sub) - use StackExchange.Redis for that. Triggers: "Redis cache", "create Redis", "manage Redis", "ARM Redis", "RedisResource", "provision Redis", "Azure Cache for Redis".
azure-resource-manager-postgresql-dotnet
Azure PostgreSQL Flexible Server SDK for .NET. Database management for PostgreSQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "PostgreSQL", "PostgreSqlFlexibleServer", "PostgreSQL Flexible Server", "Azure Database for PostgreSQL", "PostgreSQL database management", "PostgreSQL firewall", "PostgreSQL backup", "Postgres".
azure-resource-manager-playwright-dotnet
Azure Resource Manager SDK for Microsoft Playwright Testing in .NET. Use for MANAGEMENT PLANE operations: creating/managing Playwright Testing workspaces, checking name availability, and managing workspace quotas via Azure Resource Manager. NOT for running Playwright tests - use Azure.Developer.MicrosoftPlaywrightTesting.NUnit for that. Triggers: "Playwright workspace", "create Playwright Testing workspace", "manage Playwright resources", "ARM Playwright", "PlaywrightWorkspaceResource", "provision Playwright Testing".
azure-resource-manager-cosmosdb-dotnet
Azure Resource Manager SDK for Cosmos DB in .NET. Use for MANAGEMENT PLANE operations: creating/managing Cosmos DB accounts, databases, containers, throughput settings, and RBAC via Azure Resource Manager. NOT for data plane operations (CRUD on documents) - use Microsoft.Azure.Cosmos for that. Triggers: "Cosmos DB account", "create Cosmos account", "manage Cosmos resources", "ARM Cosmos", "CosmosDBAccountResource", "provision Cosmos DB".
agent-manager-skill
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
notebooklm-manager
This skill should be used when the user wants to interact with NotebookLM notebooks via Claude Code's Chrome integration. Trigger phrases: "Query my NotebookLM", "Ask my notebook about X", "query [id] about X", "list my notebooks", "add notebook URL", "show notebook details", "search notebooks for X", "Check my docs", "what does my [topic] notebook say about", "remove notebook", "delete notebook", "disable notebook", "enable notebook". Also triggers when user: (1) mentions NotebookLM explicitly, (2) shares NotebookLM URL (https://notebooklm.google.com/notebook/...). Do NOT use for: general web searches, local file reading, or non-NotebookLM documentation queries. Requires: claude --chrome with claude-in-chrome MCP.
home-assistant-manager
Expert-level Home Assistant configuration management with efficient deployment workflows (git and rapid scp iteration), remote CLI access via SSH and hass-cli, automation verification protocols, log analysis, reload vs restart optimization, and comprehensive Lovelace dashboard management for tablet-optimized UIs. Includes template patterns, card types, debugging strategies, and real-world examples.
ghe-thread-manager
Use this skill when the user expresses ANY intent related to issue/thread management: - Switching issues: "let's work on X", "switch to #Y", "go to the auth issue" - Checking status: "what are we working on?", "current issue?", "status?" - Background work: "what's in background?", "any features ready?", "check progress" - Starting development: "implement X", "add feature", "fix bug Y", "build a..." - Joining reviews: "let me see the review", "check that feature", "join #X" - Pausing/resuming: "pause this", "come back later", "resume #X" - Stopping transcription: "stop tracking", "don't record this", "private mode" - Resuming last session: "what were we working on?", "resume last issue", "continue where we left off" - Any natural expression of wanting to change focus or check work status This skill interprets natural language - users should NOT memorize commands. For the full GHE workflow protocol, see skill: github-elements-tracking
worktree-manager-skill
Comprehensive git worktree management. Use when the user wants to create, remove, list, or manage worktrees. Handles all worktree operations including creation, deletion, and status checking.