Borrowing it
Nothing to install: this file belongs to RandyChen1985/nanzi-ai-agent-platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RandyChen1985/nanzi-ai-agent-platform/main/.agent/skills/dev-skills/SKILL.mdgit clone --depth 1 https://github.com/RandyChen1985/nanzi-ai-agent-platformWrote 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/randychen1985/nanzi-ai-agent-platform/dev-skills)<a href="https://agentmods.dev/skills/randychen1985/nanzi-ai-agent-platform/dev-skills"><img src="https://agentmods.dev/badge/skills/randychen1985/nanzi-ai-agent-platform/dev-skills/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/randychen1985/nanzi-ai-agent-platform/dev-skills"><img src="https://agentmods.dev/badge/skills/randychen1985/nanzi-ai-agent-platform/dev-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.01105 |
| Opus 5 | $0.00015 | $0.00553 |
| Sonnet 5 | $0.00006 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
dev-skills scanned grade A with 0 findings 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Skills
此技能定义了用户偏好的开发流程和规范。请在所有任务中严格遵守以下规则。
1. 沟通与文档 (Communication & Documentation)
- 核心原则:始终使用 中文 (Chinese) 与用户交流,无论是在对话中还是在生成的文档中。
- OpenSpec 与需求文档:
- 创建或更新 OpenSpec 需求文件(如
proposal.md,design.md等)时,必须使用 中文。 task.md和implementation_plan.md等工件也必须使用中文编写。
- 创建或更新 OpenSpec 需求文件(如
2. 计划与原理解释 (Planning & Rationale)
在进行任何功能开发或 Bug 修复 之前,必须先确定计划。
- 分级计划机制 (Tiered Planning):
- 微小改动 (Trivial):如拼写修复、样式微调。可以在对话中直接解释 Why/How,获得确认后执行。
- 常规任务 (Normal/Feature):涉及逻辑变动。必须创建
implementation_plan.md。 - 主动询问原则:在开始执行前,Agent 必须询问用户:“此任务是否需要创建正式的实现计划文件?”。
- 创建/更新 Implementation Plan (若确定需要):
- 使用
implementation_plan.md详细列出修改计划。 - 核心内容必须包含:
- 为什么这么做 (Why):解释修改的动机、根本原因 (Root Cause) 或设计思路。
- 准备怎么搞 (How):详细的修改步骤、涉及的文件以及预期的效果。
- 为什么这么修改 (Rationale):针对具体的代码变动,解释选择此实现方式的原因。
- 使用
- 确认先行:在开始写代码之前,必须先让用户阅读并确认计划。
3. 代码提交规范 (Git Workflow)
- 严禁自动推送:每次修改完成并提交代码时,除非用户下达了明确的 “Push” 或 “推送” 指令,否则 Agent 只允许在本地执行
git commit提交,绝对禁止自动执行git push同步到远程。 - 提交确认:本地进行
git commit前,也必须征得用户明确确认,严禁自动执行。
4. 开发环境与启停服务 (Development & Startup)
- 严禁编译前端与执行启动脚本:代码修改完成后,Agent 绝对不得自己去编译前端(如
npm run build等),也不得执行./dev.sh等编译/启停脚本。 - 由用户主导编译与重启:所有的前端编译构建、服务启停、重载与日志观察均由用户在控制台手动完成(方便排查问题)。修改完成后,仅需通知用户代码已就绪,等待用户自行处理。
5. 代码推送与 PR 流程 (Push & PR Workflow)
当用户要求“提交代码并发布”、“Push”或“创建 PR”时,遵循以下流程:
- 检查与切换分支 (Branching):
- 根据任务内容(Feature/Fix)生成新分支名(例如
feat/xxx),并使用git checkout -b <new_branch>切换。
- 根据任务内容(Feature/Fix)生成新分支名(例如
- 推送到远程 (Pushing):
- 执行
git push -u origin <new_branch>。
- 执行
- 创建 Pull Request (Automated PR):
- 自动生成 PR 标题和详细描述,并尝试使用
gh pr create创建。
- 自动生成 PR 标题和详细描述,并尝试使用
- 分支清理 (Cleanup):
- 在 PR 合并或发布流程结束后,Agent 必须主动询问或提醒用户清理已完成的功能分支。
6. 数据库与提示词变更规范 (Database & Prompt Changes)
- 数据库变更 (Database Changes):
- 执行边界 (Strict Boundary):凡涉及数据库 Schema 或数据变更,Agent 仅负责在
db-prod/目录下创建 SQL 脚本。严禁自动执行 SQL 语句或通过 Python 脚本直接修改数据库。 - 命名规范:使用
V开头 + 自增序号 + 描述(例如V29-add_new_table.sql,必须检查目录下的当前最大序号并 +1)。
- 执行边界 (Strict Boundary):凡涉及数据库 Schema 或数据变更,Agent 仅负责在
- 提示词变更 (Prompt Changes):
- 凡涉及系统提示词 (Prompts) 的新增或更新,必须在
architech/prompts/下操作并进行版本控制。 - Agent 仅负责创建/更新文件,不负责自动同步到系统内部。
- 凡涉及系统提示词 (Prompts) 的新增或更新,必须在
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.
- 4d ago Changed d2d35d5f4fd0
- 10d ago First seen · 64 lines · 29 tokens per session scan A 1413d80c1e05
dev-skills is a skill published in the GitHub repository RandyChen1985/nanzi-ai-agent-platform (167 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,105 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
node-connect
Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale…
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.