AI Delivery Spec

Clarify, create, review or change product, service and office workflow requirements, PRDs and interactive prototypes. Use for vague goals, process improvements, spreadsheet/form rules, small UI edits and changes to existing systems, even without the word requirement. 中文：产品、服务及办公流程的需求判断、深挖澄清、PRD、原型、变更与验收；一句话想法、表单/表格规则和微小改动也适用。明确的纯翻译、排版、抄录或既定步骤执行由对应工具直接处理。

35 stars 6 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add franklinxkk/ai-delivery-spec --skill ai-delivery-spec

Manual install

git clone --depth 1 https://github.com/franklinxkk/ai-delivery-spec.git /tmp/ai-delivery-spec
mkdir -p ~/.claude/skills
cp -r /tmp/ai-delivery-spec/. ~/.claude/skills/ai-delivery-spec

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AI Delivery Spec 5.5.6 — 需求判断与交付

让人和 AI 一起把产品做对，为研发与测试提供明确的业务依据。

## 从当前目标进入

继承已确认决定，不因模板重复批准。`/ads` 从任务进入，`/dig` 澄清，`/prd` 写规格，`/proto` 做原型；宿主命令支持见 [README](README.md#shortcuts)。

小改读取相关基线，完成差异及正反验收；无关键未知不提问、不建生命周期文件。

先解决业务分歧。按[团队约定](references/team-customization.md)沿用模板、设计和交互原件；不让用户挑模板或维护机器文件。

| 当前需要 | 按需读取 |
|---|---|
| 判断问题、比较方案、澄清 | [discover.md](references/discover.md) |
| 轻量规格、正式 PRD 与模块交接 | [specify.md](references/specify.md) |
| 存量盘点、生成或修改可操作原型 | [prototype.md](references/prototype.md) |
| 用户需要双态评审 | [review-workspace.md](references/review-workspace.md) |
| 准入、处置、责任与基线 | [lifecycle.md](references/lifecycle.md) |
| 变更、交接反馈或验收 | [change-acceptance.md](references/change-acceptance.md) |
| 多文件、大上下文或跨会话 | [context.md](references/context.md) |
| 机器路由、模板或检查命令 | [stages.md](references/stages.md) |

领域入口不清时用 `python scripts/query_domain.py --list` 看中文摘要与别名；按[领域检索指引](references/stages.md#领域检索)取相关正文并核验权威、版本与适用对象。语言不决定法域，未命中不代表规则不存在；项目决定不写成通用领域规则。

## 保持业务含义与决定权

- 分清事实、授权决定、观察、建议和未知。硬条件核对当前来源；示例只借写法，不移植权限、状态或协议。原型行为不自动成为规则。
- 最新有效决定覆盖同主题旧内容。文档待同步、旧评审待复验不使该决定重新变成待批准。真正超出授权或存在冲突时只处理相应范围。
- 建议暂缓、不做、缩范围写回现有产物；未获处置权不得改变需求状态。记录理由、依据和复议条件；已获授权不重复询问。
- 未定规则保持未定。退路可以限制执行，不能借“保守默认”选定补考、口径、权限或晚到数据政策。未知只阻断依赖它的交付。

## 最小充分规格

按用户任务组织进入、输入、提交、结果及再次读取。先提取已定条件、待决分支和必须保持的结果；排版可自行设计，权限、状态、时间和成功凭据不能从示例或组件默认值补出。

业务条件和正反预期从原始决定产生，写在所属模块；工作推导不新增用户必填表。先完成一个任务的规格、可操作路径及拒绝/恢复验证，再扩展相邻任务；不先铺全产品空页面。复杂交接读[成品示例](examples/configuration-to-consumption.md)。技术空间保留，说明规则不等于新增配置。

Read the full skill on GitHub

Details

Skill name: ai-delivery-spec
Repository: franklinxkk/ai-delivery-spec
License: MIT
Repo updated: 31 October 2026

FAQ

What does the AI Delivery Spec skill do?

How do I install the AI Delivery Spec skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add franklinxkk/ai-delivery-spec --skill ai-delivery-spec. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is AI Delivery Spec popular?

It lives in franklinxkk/ai-delivery-spec, which has 35 GitHub stars and 6 forks.

Related skills

Kaoyan Navigator

mcxiaoxiao/kaoyan-navigator-skill

调研中国硕士研究生考试（考研）目标院校与专业的历年招生数据，评估择校爆冷/爆热、缩招、推免挤压、复试线虚低、专业课变更和复试风险，并给出冲稳保建议。适用于用户询问考研择校、院校难度、报录比、复试线、招生计划、统考名额、推免比例、拟录取分数、某校会不会爆、目标分数或需要导入自有 CSV/JSON 数据时。应先搜索公开网络和官方来源，确实找不到关键数据后再向用户索取补充材料；支持 Codex、Claude Code 和其他能读取 Skill Markdown 的 agent。

AI, LLMs & Agents

LLM Council

shuntacurosu/llm_council_skill

Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis

AI, LLMs & Agents

Agentic Command Center

Forgemind-git/agentic-command-center

An advisory blueprint for planning your own AI command center — one chat or voice interface that runs your whole business by routing to internal systems you own. Guidance and architecture only; it explains the four phases (own your systems, connect your tools, expose them over MCP, unify under one command layer) but never writes code or builds anything. Use when someone wants to understand how to approach internal dashboards, integrations, MCP, and a unified agentic command layer.

AI, LLMs & Agents14

R00 Travisvn Awesome Claude Skills Datascience

WireTarantulaKnife/r09-travisvn-awesome-claude-skills-datascience

🤖 Data Science & AI/ML skill suite derived from travisvn/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.

AI, LLMs & Agents

Booking Best Price

aiwithremy/claude-skills-booking-best-price

Use when the user pastes a holiday-rental or hotel listing link (Airbnb, Stayz, Vrbo, Expedia, Booking.com, HomeToGo, or similar) and wants to identify the actual property, find it listed on other sites, compare prices to book it cheaper, or track down the property manager / owner contact to book direct. Requires the Firecrawl MCP server. This skill verifies Firecrawl is installed and walks the user through setup first if it is not.

AI, LLMs & Agents

Intercom

Trac-Systems/intercom

Skill for autonomous agents. Secure & private P2P messaging (sidechannels), sparse state/data + contracts, and optional value transfer. For a true agentic internet.

AI, LLMs & Agents290

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.