feature-dev

A development workflow for implementing complex software features in an existing codebase. Its instructions are in Chinese and emphasize tracing real code paths, reusing existing components, and making the smallest complete change.

In plain words
What is it for?
Exploring a repository, identifying affected modules, choosing an implementation approach, making the change, and running focused checks such as tests, linting, type checks, or a build.
Why use it?
It helps prevent changes based on guesses about how the code works. It also guides decisions about architecture, compatibility, errors, and testing when a feature spans several parts of a project.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ohh-889/skyroc/feature-dev
Any agent
npx skills add Ohh-889/skyroc --skill feature-dev
Clone the repo
git clone --depth 1 https://github.com/Ohh-889/skyroc

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,097 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00076 $0.01097
Opus 5 $0.00038 $0.00549
Sonnet 5 $0.00015 $0.00219
Haiku 4.5 $0.00008 $0.00110

Measured 2d ago against content hash d4deef8233ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-dev 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 2d 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.

.agents/skills/feature-dev/SKILL.md · 79 lines

What it actually says

复杂功能开发

在充分理解现有代码的基础上完成复杂功能。遵循仓库根目录及相关子目录中的 AGENTS.md,将其作为编码规范的唯一事实来源。

工作原则

  • 先追踪真实调用链、数据流、模块边界和相邻实现,再确定方案。
  • 优先复用现有组件、Hooks、服务、类型和基础设施。
  • 默认选择满足需求的最小完整改动,避免无关重构和预设式抽象。
  • 只有缺失信息会明显改变业务结果、兼容性、数据安全或实现边界时才询问用户;轻微歧义根据现有代码合理判断并继续。
  • 只在方案存在实质性差异时比较多个架构,不为形式完整而制造备选方案。
  • 未经用户授权,不扩大任务范围或执行破坏性、不可逆操作。

1. 判断复杂度

先判断任务是否确实需要本工作流。

  • 若任务范围清晰、局限于少量文件且不涉及重要架构决策,直接按常规开发流程完成,不强制执行后续阶段。
  • 若涉及多个模块或系统、公共接口、数据迁移、复杂状态流或高风险兼容性,继续执行以下流程。
  • 仅当任务包含三个以上相互依赖的阶段且计划能帮助跟踪进度时,使用当前环境提供的计划工具。

2. 探索代码库

  1. 阅读相关 AGENTS.md、包配置、架构说明和相邻实现。
  2. 追踪入口、调用链、状态变化、数据契约、错误处理和测试方式。
  3. 搜索可复用的类似功能与扩展点。
  4. 当存在多个可独立调查的问题且并行探索能明显提高效率时,按需启动探索代理;不要固定代理数量。要求代理返回结论、证据和关键文件列表,随后亲自阅读决定实现所必需的文件。
  5. 向用户说明会影响实现选择的关键发现;不要输出冗长的文件阅读流水账。

3. 补齐关键信息

根据代码证据识别真正阻塞实现的问题,例如业务边界、错误语义、权限、兼容性、迁移策略和不可逆操作。

  • 能从源码、配置、类型、测试或现有行为中确定的信息,直接查明,不反问用户。
  • 存在安全且符合项目惯例的默认方案时,说明必要假设并继续。
  • 只有不同答案会造成明显不同的业务结果或风险时,集中提出少量具体问题并等待回答。

4. 确定方案

定义目标结构、职责边界、交互方式和兼容策略。

  • 通常直接给出一个推荐方案及理由。
  • 只有多个方案存在实质性取舍时,简要比较最小改动、长期可维护性和实施风险。
  • 若推荐方案仍处于用户已授权的需求范围内,可直接实现。
  • 只有方案会扩大范围、改变公共行为、引入数据风险或需要不可逆操作时,才请求用户确认。

5. 实现与验证

  1. 按选定方案实施最小且完整的修改。
  2. 严格遵循现有架构、命名、类型和平台规范。
  3. 保持公共接口和既有行为稳定,除非需求明确要求改变。
  4. 运行受影响 workspace 的针对性测试、类型检查、lint 或构建;避免默认执行整个大型仓库的全部检查。
  5. 分析验证失败,区分本次改动、环境问题和已有问题,不把未执行或失败的检查描述为通过。

6. 质量审查

检查功能正确性、边界情况、重复逻辑、抽象边界、项目规范和回归风险。

  • 对高风险或跨模块改动,可按需并行委派彼此独立的审查方向;不要固定启动多个审查代理。
  • 直接修复任务范围内明确且安全的问题。
  • 无关问题只简短记录,不顺手扩大修改范围。
  • 需要新增授权或会改变业务行为的问题,向用户说明后再处理。

7. 交付

简洁说明:

  1. 修改了什么。
  2. 关键架构或根因是什么。
  3. 执行了哪些验证以及结果。
  4. 仍存在的风险或未验证项。

不要生成用户未要求的计划文档、迁移指南或冗长过程复盘。

Changes

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.

  1. 2d ago First seen · 79 lines · 76 tokens per session scan A d4deef8233ef

Subscribe to this mod's changes

feature-dev is a skill published in the GitHub repository Ohh-889/skyroc (787 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 1,097 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

antd

Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.

ant-design/ant-design-pro · 69 tokens

pro-upgrade

Use when the user wants to upgrade their Ant Design Pro project to the latest version. Triggers on: upgrade pro, pro upgrade, migrate pro, update pro, 升级, 迁移项目, "how to upgrade", "update to latest", "keep project up to date".

ant-design/ant-design-pro · 63 tokens

demo-create

基于项目中 .vscode/south.code-snippets 定义的 CRUD 模板,快速生成后台管理系统的标准 CRUD 页面代码。该技能根据用户提供的业务模块信息(如模块名称、API路径、字段配置等),自动生成完整的页面文件(Page)、数据模型文件(Model)和 API 接口文件(Api),支持分页列表页面(demoPage)、独立操作页面(demoOptionPage)两种页面模式。.

southliu/south-admin-react · 99 tokens

init-project

初始化整个项目,清除模板自带的示例内容(src/pages/demo、src/pages/content、src/components/Github、src/servers/content、menus/demo 及相关 i18n),并连带删除代码中的 import 与引用。执行时会先以 dry-run 预览将要删除的文件和将要修改的引用,经用户确认后再真正执行。.

southliu/south-admin-react · 83 tokens

v3-create-crud

创建增删改查(CRUD)页面,基于 Element Plus 组件库,包含表格、搜索、分页、新增/编辑弹窗、删除确认等功能。当用户提到以下任何场景时都应触发:创建管理页面、创建列表页、创建表格页。即使用户没有明确说 CRUD,只要意图是创建带表格和表单操作的后台页面就应该使用此 Skill。使用时需提供模块名称和字段信息。.

un-pany/v3-admin-vite · 108 tokens

v3-upsert-route

根据用户提供的路由信息,在 src/router/index.ts 中生成或更新路由配置。.

un-pany/v3-admin-vite · 88 tokens