Code Builder
Translates plans into working code structures with architecture decisions, folder layout, and implementation strategy
- License 许可
- MIT
- 最近更新
- 2026-06-22
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- Code Builder
- tags
- [ "coding", "implementation", "scaffolding" ]
- author
- ForgeWeave Core
- version
- 1.0.0
- skill_id
- code-builder
- description
- Translates plans into working code structures with architecture decisions, folder layout, and implementation strategy
- tui_compatibility
- [ "opencode", "claude", "gemini", "qwen" ]
02 资源文件 2
- 参考文档references/project-conventions.md658 B
- 脚本scripts/scaffold_module.py2.0 KB
03 SKILL.md 正文
Code Builder
Purpose
Take a structured plan and produce working, well-organized code. Makes architecture decisions (framework choice, folder structure, module boundaries), generates the code, and verifies it compiles or passes basic checks.
When to Use
- A
plannerskill has produced an execution plan - The user asks to "implement" or "build" a feature from requirements
- Scaffolding a new module, component, or service
- Translating architecture decisions into concrete code
When Not to Use
- The code change is a simple rename or refactor — use
refactor-engine - Only tests are needed — use
test-generator - The task is debugging an existing issue — use
debugger
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
plan |
object | Yes | The execution plan from the planner skill |
existing_code |
string | No | Description of existing codebase structure |
standards |
array | No | Coding standards to follow (e.g., TypeScript strict, PEP 8) |
Expected Outputs
| Output | Description |
|---|---|
| New or modified files | Working code implementing the plan |
| Folder structure | Organized module layout |
| Architecture notes | Key decisions made during implementation |
Exact Workflow Steps
- Review the plan and understand the architecture
- Create folder structure matching project conventions
- Implement each module following existing patterns
- Add type annotations and documentation as code is written
- Verify the code compiles or passes syntax checks
- Run existing tests to confirm no regressions
Required Checks
- [ ] Code compiles without errors
- [ ] Existing tests still pass
- [ ] Code follows project conventions (naming, imports, formatting)
- [ ] New exports are properly typed
Failure Modes
| Failure Condition | Response |
|---|---|
| Code doesn't compile | Fix type errors and re-verify |
| Existing tests fail | Identify root cause and fix before continuing |
| Architecture decision contradicts plan | Flag to planner for resolution |
References
| Reference | Path |
|---|---|
| Planner skill | ../planner/SKILL.md |
| Test Generator skill | ../test-generator/SKILL.md |
04 同仓库更多 Skills
Workflow Orchestrator
Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)
Web Research
Browser-driven or scraping-based skill for real-time internet extraction using Playwright and HTTP-based fetching
Validation Engine
Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
Tool Selector
Determines which tools, APIs, MCP actions, or system capabilities are required for a given task
Test Generator
Creates test plans and test cases (unit, integration, edge cases) based on existing or planned code
Skill Generator
Meta-skill that creates new SKILL.md files from research outputs and patterns discovered in execution