Agent skill

Workflow Code Generation

by davidYichengWei in davidYichengWei/agentic-engineering-framework

代码文件修改的统一入口。当用户请求任何代码变更(新功能、优化、Bug 修复、重构)时必须首先调用此 skill。仅适用于代码文件(如 .cc/.cpp/.h/.go/.py 等),修改 .md 等非代码文件时不需要调用。它会评估复杂度、检查 spec.md、生成 tasks.md、并逐个任务执行。

MITAuto-check passedDevelopment

Install Workflow Code Generation

skills CLI
$ npx skills add davidYichengWei/agentic-engineering-framework --skill workflow-code-generation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install davidYichengWei/agentic-engineering-framework workflow-code-generation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/davidYichengWei/agentic-engineering-framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/workflow-code-generation .claude/skills/workflow-code-generation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
workflow-code-generation
GitHub stars
158
Token cost
~733 tokens
SKILL.md length
218 words
Files
2
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

代码文件修改的统一入口。当用户请求任何代码变更(新功能、优化、Bug 修复、重构)时必须首先调用此 skill。仅适用于代码文件(如 .cc/.cpp/.h/.go/.py 等),修改 .md 等非代码文件时不需要调用。它会评估复杂度、检查 spec.md、生成 tasks.md、并逐个任务执行。

  • Works in 3 steps: 实现 → Code Review 与修复循环(🚨 强制) → 汇报 → 停止等待
  • Development work in your project
  • SKILL.md covers 工作流程, 用户跳过 spec 时 and 恢复中断的任务
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Workflow Code Generation is an agent skill from davidYichengWei/agentic-engineering-framework. 代码文件修改的统一入口。当用户请求任何代码变更(新功能、优化、Bug 修复、重构)时必须首先调用此 skill。仅适用于代码文件(如 .cc/.cpp/.h/.go/.py 等),修改 .md 等非代码文件时不需要调用。它会评估复杂度、检查 spec.md、生成 tasks.md、并逐个任务执行。

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `reference/task_planning_guide.md`).

It sits in Development. It works with C++. The repository describes itself as: 开箱即用、可按项目定制的 AI Coding Agent Skills 框架:提供通用 Workflow、可扩展的项目私有知识、自我学习闭环和问题排查能力,适配任意技术栈和工程场景。兼容主流 Coding Agent。 The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/workflow-code-generation”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. 实现
  2. Code Review 与修复循环(🚨 强制)
  3. 汇报 → 停止等待

What it can do on your machine

Read from SKILL.md and the folder at commit 1f7ac0f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Workflow Code Generation loads about 733 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 218 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~733

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davidYichengWei/agentic-engineering-framework at commit 1f7ac0f, republished under its MIT licence (© davidYichengWei). 218 words, ~733 tokens.

Download SKILL.mdSave it as .claude/skills/workflow-code-generation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
workflow-code-generation
description
代码文件修改的统一入口。当用户请求任何代码变更(新功能、优化、Bug 修复、重构)时必须首先调用此 skill。仅适用于代码文件(如 .cc/.cpp/.h/.go/.py 等),修改 .md 等非代码文件时不需要调用。它会评估复杂度、检查 spec.md、生成 tasks.md、并逐个任务执行。

代码生成

所有代码修改的统一入口。先加载规范,再写代码。

工作流程

步骤 1:评估复杂度与路径路由

⚠️ 防御性检查:如果 AI 无法明确回答"要改什么模块/文件"、"要实现什么行为"、"怎样算完成"这三个问题中的任何一个,则立即停止,调用 workflow-requirements-clarification。本 skill 不负责需求澄清。

默认走标准流程(步骤 2 → 3 → 4 → 5)。Fast-Path 仅当改动为单文件、局部改动(能在路由阶段确定完整文件列表,且只涉及 1 个文件的局部修改)时才可进入。

无法确定 → 标准流程。

Fast-Path 执行
  1. 加载编码规范(同步骤 4)
  2. 实现改动
  3. 执行过程中发现实际需要改多个文件 → 立即退出,回到步骤 2 进入标准流程
  4. 询问用户是否需要 code review
    • 需要 → 加载 workflow-code-review skill(指定 skip_reviewers: [magical-prompt-reviewer])→ 修复循环
    • 不需要 → 输出改动说明
  5. 结束,不进入后续步骤
标准流程入口

查找 docs/design-docs/<module>/<feature>/spec.md:

  • 存在且完整 → 仔细通读全文(不要只读关注的章节),确认理解
  • 不存在/不完整 → 调用 workflow-requirements-clarification(禁止自行澄清)

强制:spec.md 与 tasks.md 同时存在时,编码前必须完整读取两者。

步骤 2:选定当前任务

从 tasks.md 中找第一个未完成任务,记录其编号和上下文。

步骤 3:检查/创建 tasks.md

🚨 创建 tasks.md 后必须停下来等用户确认。 展示任务列表,然后停止并等待用户回复。禁止自动进入步骤 4。

步骤 4:加载编码规范(🚨 强制前置)

未加载规范就写代码 → 立即停止,先加载。

必须加载
规范说明
bp-coding-best-practices通用编码最佳实践
bp-performance-optimization性能优化(所有代码都是性能敏感的)
按需加载
规范何时加载
std-cpp.cc/.cpp/.h 文件
std-go.go 文件
bp-distributed-systems涉及网络通信、多节点协调、一致性、故障恢复
步骤 5:逐个任务实现

核心规则:一个 Task → review 通过 → 报告 → 等用户批准 → 下一个 Task

Phase 1: 实现

修改代码,更新 tasks.md 标记 In Progress。

Phase 2: Code Review 与修复循环(🚨 强制)

4a. 执行 Code Review

加载 workflow-code-review skill,按其工作流执行(指定 skip_reviewers: [magical-prompt-reviewer])。该 skill 会并行调用 reviewer subagent 执行审查——禁止主 agent 自己做 review 代替 subagent。

4b. 逐条反思犯错原因

对报告中每条 keep 的 finding,反思犯错原因:

原因分类含义
Spec 理解偏差spec 写清楚了但理解错误
规范未遵守编码规范有要求但未执行
执行遗漏漏掉边界/细节
设计考虑不足需更深层设计思考

4c. 自动修复 → Re-review 循环

修复 finding → 重新加载 workflow-code-review skill 执行 re-review → 重复 4b-4c,直到结论为 PASS。

中间轮次的报告和反思不需要展示给用户,内部处理即可。

4d. 输出 Review 总结

所有轮次结束(PASS)后,向用户输出一份总结,包含:

  • 经历了几轮 review
  • 每条发现的问题、修复方式和犯错原因
  • 最终 PASS 的 review 报告
Phase 3: 汇报 → 停止等待

输出报告,更新 tasks.md 标记 Completed,停止等待用户批准。

Task 完成报告模板
markdown
---
## ✅ Task N 完成

### 改动文件
- `path/to/file.cc`: [改动说明]

### 改动内容
[做了什么,为什么]

### Code Review 结果

**Review 轮次**: [第 K 轮通过]
[附 workflow-code-review 输出的报告]

---

询问用户下一步操作,提供以下选项:
- **继续/LGTM** → 下一个任务
- **修改** → 重新提交(用户附带修改要求)
- **回滚** → 撤销本次改动

用户跳过 spec 时

必须生成简化版 spec.md(标注 Status: Quick Draft)。禁止无 spec 修改中等+代码。

恢复中断的任务

读取 tasks.md → 找未完成任务 → 重新加载编码规范 → 继续执行。

© davidYichengWei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/workflow-code-generation of davidYichengWei/agentic-engineering-framework.

  • SKILL.md
  • reference/task_planning_guide.md

Open the folder on GitHubat commit 1f7ac0f

Compare with similar skills

Workflow Code Generation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Workflow Code Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Workflow Code Generation this skilldavidYichengWei/agentic-engineering-framework158—~733Automated safety check: PassMIT
Qt C++ Code Reviewx-tools-author/x-tools1.1k2 repos~4.3kAutomated safety check: PassBSD-3-Clause
YugabyteDB ASH Instrumentationyugabyte/yugabyte-db11k—~4.5kAutomated safety check: PassCustom licence
pybind11 Release Preparationpybind/pybind1118k—~1.7kAutomated safety check: PassCustom licence
Qt Cpp ReviewSerial-Studio/Serial-Studio7.2k—~4.3kAutomated safety check: PassCustom licence
Paddle Eager GraphPaddlePaddle/Paddle24k—~562Automated safety check: PassApache-2.0

Similar skills

  • Qt C++ Code Review

    x-tools-author/x-tools

    Read-only review of Qt6 C++ code that combines a deterministic lint script with six parallel analysis agents and reports only high-confidence issues.

    1.1k GitHub starsUsed in 2 repos~4.3k tokens
    DevelopmentAuto-check passed
  • YugabyteDB ASH Instrumentation

    yugabyte/yugabyte-db

    Procedure for adding or changing YugabyteDB Active Session History wait states in TServer and DocDB C++ code, including the macro to use for sync and async paths.

    11k GitHub stars~4.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Opens the pybind11 release-preparation pull request: picking the release base, bumping the version in common.h and integrating the changelog, following docs/release.rst.

    18k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Qt Cpp Review

    Serial-Studio/Serial-Studio

    Qt6/C++ deep code review for Serial Studio. An agent skill from Serial-Studio/Serial-Studio.

    7.2k GitHub stars~4.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Paddle Eager Graph

    PaddlePaddle/Paddle

    A skill your agent uses when navigating Paddle eager-mode (dynamic graph) source code, tracing forward/backward execution, debugging autograd issues, understanding PyLayer, or investigating…

    24k GitHub stars~562 tokensUpdated 8 days ago
    DevelopmentAuto-check passed
  • ONNX Runtime Source Build

    microsoft/onnxruntime

    Official

    Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.

    22k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed

More from davidYichengWei/agentic-engineering-framework

All 14 skills in this repo
  • Architecture Design Principles

    davidYichengWei/agentic-engineering-framework

    Gives architecture design principles for system design discussions and code review: module boundaries, dependency direction, data ownership and interface rules, plus a checklist.

    158 GitHub stars~545 tokensUpdated 6 mo ago
    Auto-check passed
  • General Coding Best Practices

    davidYichengWei/agentic-engineering-framework

    A checklist of language-neutral rules for writing and reviewing code: naming, function design, control flow, resource safety, comments and logging.

    158 GitHub stars~631 tokensUpdated 6 mo ago
    Auto-check passed
  • Component Design Principles

    davidYichengWei/agentic-engineering-framework

    Chinese-language checklists for component-level design: class and module structure, public interfaces, data models, concurrency and error handling.

    158 GitHub stars~1k tokensUpdated 6 mo ago
    Auto-check passed
  • Skill Authoring Guide (Chinese)

    davidYichengWei/agentic-engineering-framework

    Chinese-language guide to writing and improving SKILL.md files: frontmatter rules, concise writing, progressive disclosure, common patterns and a pre-release checklist.

    158 GitHub stars~788 tokensUpdated 6 mo ago
    Auto-check passed
  • Self-Refinement from Corrections

    davidYichengWei/agentic-engineering-framework

    Turns mistakes you correct into proposed updates to persistent Rules and Skills so the same error does not recur in later sessions, triggered automatically or with /reflect.

    158 GitHub stars~575 tokensUpdated 6 mo ago
    Auto-check passed
  • Root-Cause Troubleshooting

    davidYichengWei/agentic-engineering-framework

    Diagnoses compile errors, runtime exceptions, failing tests, pipeline failures and production alerts from code and logs, giving a root cause before any fix.

    158 GitHub stars~646 tokensUpdated 6 mo ago
    Auto-check passed

Works with

Categories

Questions about Workflow Code Generation

What does Workflow Code Generation do?

代码文件修改的统一入口。当用户请求任何代码变更(新功能、优化、Bug 修复、重构)时必须首先调用此 skill。仅适用于代码文件(如 .cc/.cpp/.h/.go/.py 等),修改 .md 等非代码文件时不需要调用。它会评估复杂度、检查 spec.md、生成 tasks.md、并逐个任务执行。. Workflow Code Generation is an agent skill from davidYichengWei/agentic-engineering-framework.

When should I use Workflow Code Generation?

Workflow Code Generation fits situations like: development work in your project.

How do I install Workflow Code Generation in Claude Code?

Run `npx skills add davidYichengWei/agentic-engineering-framework --skill workflow-code-generation -a claude-code`. Or copy the skill folder (skills/workflow-code-generation in davidYichengWei/agentic-engineering-framework) into .claude/skills/workflow-code-generation in your project. Claude Code loads it when a task matches its description.

How do I install Workflow Code Generation in Codex?

Run `npx skills add davidYichengWei/agentic-engineering-framework --skill workflow-code-generation -a codex`. Or copy the skill folder (skills/workflow-code-generation in davidYichengWei/agentic-engineering-framework) into .agents/skills/workflow-code-generation in your project. Codex loads it when a task matches its description.

Can I use Workflow Code Generation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davidYichengWei/agentic-engineering-framework --skill workflow-code-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/workflow-code-generation, .gemini/skills/workflow-code-generation, .github/skills/workflow-code-generation and .opencode/skills/workflow-code-generation in your project.

What does Workflow Code Generation need to run?

SKILL.md names no scripts, command-line tools or credentials: Workflow Code Generation is instructions for the agent only.

Does Workflow Code Generation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Workflow Code Generation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Workflow Code Generation use?

Workflow Code Generation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Workflow Code Generation use?

About 733 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Workflow Code Generation?

Skills that share tags, products or a category with Workflow Code Generation: Qt C++ Code Review (x-tools-author/x-tools, 1.1k stars), YugabyteDB ASH Instrumentation (yugabyte/yugabyte-db, 11k stars), pybind11 Release Preparation (pybind/pybind11, 18k stars) and Qt Cpp Review (Serial-Studio/Serial-Studio, 7.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Workflow Code Generation?

davidYichengWei (a GitHub user) maintains it in davidYichengWei/agentic-engineering-framework, which has 158 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on March 25, 2026.

Source: davidYichengWei/agentic-engineering-framework on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.