Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Wade-DevCode/awesome-coding-skills-cn --skill requirement-deliverygit clone --depth 1 https://github.com/Wade-DevCode/awesome-coding-skills-cnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wade-devcode/awesome-coding-skills-cn/requirement-delivery)<a href="https://agentmods.dev/skills/wade-devcode/awesome-coding-skills-cn/requirement-delivery"><img src="https://agentmods.dev/badge/skills/wade-devcode/awesome-coding-skills-cn/requirement-delivery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wade-devcode/awesome-coding-skills-cn/requirement-delivery"><img src="https://agentmods.dev/badge/skills/wade-devcode/awesome-coding-skills-cn/requirement-delivery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.02443 |
| Opus 5.5 | $0.00014 | $0.00977 |
| Sonnet 5.5 | $0.00007 | $0.00489 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
requirement-delivery scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 后端接口写完,用 `curl` 或 Postman 打一个真实请求,不等前端联调才发现返回格式不对。 How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
接需求提效
何时用
- 接到一个新需求或任务,需要快速产出可运行、可演示的成果时。
- 需求描述模糊、验收标准不清晰,担心做完方向不对时。
- 任务较大,不知道从哪里切入、如何拆解时。
- 时间紧张,需要优先打通核心流程、把次要功能后置时。
核心规则
1. 先澄清再动手
规则: 接到需求后,先列出验收标准与边界条件;有模糊之处,先向对方确认,不猜着做。
为什么: AI 极容易把"我理解的需求"当成"真实需求"——用户说"做一个导出功能",AI 默默实现了 CSV 导出,结果对方要的是 Excel;用户说"优化一下性能",AI 大幅重构了数据结构,结果对方只是想加个分页。这类方向性错误往往要到交付时才暴露,前面所有工时全部作废。
怎么做:
- 收到需求后,先不写代码,而是写出 2-4 条验收标准,发给对方确认:
我理解这个需求的验收标准是: 1. 用户点击"导出"按钮后,下载一个 .xlsx 文件 2. 文件包含当前筛选结果中的所有行,字段顺序与表格列顺序一致 3. 导出超过 1 万行时有进度提示,不卡死页面 以上理解是否正确?有没有我遗漏的场景? - 列出不确定的边界条件,例如:空列表怎么处理?文件名格式是什么?权限校验在哪一层?
- 确认完成再开始写代码,不要"边做边猜、做完再问"。
2. 拆成可交付小块
规则: 把需求拆成独立可演示的小块;优先打通核心路径(MVP),次要功能后置。
为什么: AI 倾向于一口气把"完整方案"全部写完再交付——结果往往是:核心逻辑正确,但周边逻辑(错误处理、边界分支、UI 细节)有缺漏,整体跑不起来,联调阶段才发现问题。拆成小块后,每一块都能独立验证,早发现早修正,整体风险大幅降低。
怎么做:
- 拿到需求先画出任务树,识别哪条是核心路径:
需求:用户可以通过邮箱注册账号 核心路径(MVP,优先做): - [ ] POST /api/register 接口,写入 users 表 - [ ] 返回 JWT token,前端可以登录 次要功能(MVP 通过后再加): - [ ] 邮件验证流程 - [ ] 密码强度校验提示 - [ ] 注册成功欢迎邮件 - 每块完成后,能独立运行一个最小 demo 或通过一个测试,再进入下一块。
- 不在"核心路径还没跑通"时去完善次要功能。
3. 复用优先
规则: 动手前先找现成的库、模板、或项目内已有代码;不从零造轮子。
为什么: AI 在生成代码时有一种惯性——直接写一套新实现,哪怕项目里已经有一模一样的工具函数,或者一个知名库早就解决了这个问题。这不仅浪费时间,还会在代码库里留下重复逻辑,日后维护时产生不一致。
怎么做:
- 在写任何工具函数或模块前,先搜索项目内的已有代码:
# 检查项目内是否已有日期格式化工具 grep -r "formatDate\|format_date\|dateFormat" src/ --include="*.ts" -l - 依赖外部功能时,先查标准库和主流 npm/PyPI 包,再考虑自己写:
- 日期处理 →
date-fns/dayjs,不自己写padZero - HTTP 请求 →
axios/httpx,不自己封装XMLHttpRequest - 数据校验 →
zod/pydantic,不自己写if typeof x !== 'string'链
- 日期处理 →
- 复用项目内已有代码时,读懂它的接口约定再调用,不要复制粘贴后再魔改。
4. 边做边验证
规则: 每完成一块,立即用真实场景自测一遍;不把验证堆到最后。
为什么: AI 写完一大段代码后统一"跑一下看看",是最危险的工作方式。一旦出错,错误来源可能在任何一块代码里,定位成本极高。更常见的情况是:每一块单独看起来都合理,但组合在一起时有隐含的状态依赖或接口不匹配,早测早改成本是后测的十分之一。
怎么做:
- 每完成一个函数或接口,立即写一个最小调用验证:
# 写完 parse_config() 后,立刻跑一遍: cfg = parse_config("tests/fixtures/sample.toml") assert cfg.host == "localhost" assert cfg.port == 5432 print("parse_config OK") - 后端接口写完,用
curl或 Postman 打一个真实请求,不等前端联调才发现返回格式不对。 - 发现错误立即修,不要"先记着、做完再统一修"——堆积的 bug 会产生连锁效应。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 225 lines · 34 tokens per session scan A d62fe6173024
requirement-delivery is a skill published in the GitHub repository Wade-DevCode/awesome-coding-skills-cn (7 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 2,443 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
executing-plans
A procedure for carrying out a written software implementation plan in a separate session, including reviewing the plan, completing its tasks, and checking the results at defined review points.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.