---
id: gh-build
name: "build"
url: https://skills.yangsir.net/skill/gh-build
author: juliusbrussee
domain: ai-code-generation-quality
tags: ["agent-workflow", "code-execution", "verification", "devops", "spec-implementation"]
install_count: 2700
rating: 4.40 (120 reviews)
github: https://github.com/juliusbrussee/cavekit/tree/main/skills/build
---

# build

> "build" 技能定义了 AI 智能体实现规范的单线程计划-执行流程。它负责读取规范、解析任务、制定详细的实施计划（包括引用不变式、接口、文件和测试），然后按计划修改代码、运行验证。如果验证失败，智能体将触发回溯机制，分析失败原因并决定是修复代码还是更新规范，确保每次提交都经过验证，并遵循严格的提交策略。

**Stats**: 2,700 installs · 4.4/5 (120 reviews)

## Before / After 对比

### 规范实现效率提升

**Before**:

开发者手动根据规范进行任务规划、编码、测试和调试，耗时且易出错，导致任务完成周期长，质量不稳定，平均需要 4 小时完成一个中等复杂度的任务。

**After**:

AI 智能体自动化执行规范实现流程，包括智能规划、代码修改、自动验证和错误回溯，显著缩短任务完成时间，提高代码质量和一致性，将任务完成时间缩短至 1 小时。

| Metric | Before | After | Change |
|---|---|---|---|
| 任务实现时间 | 240分钟 | 60分钟 | -75% |

## Readme

# build — implement spec

Single-thread native plan→execute. You are main Claude. No swarm.

## LOAD

1. Read `SPEC.md`. If missing → tell user to invoke the spec skill first. Stop.
2. Read `FORMAT.md` once if not loaded.
3. Parse invocation args:
   - `§T.n` → that task only
   - `--next` → lowest-numbered row with status `.` or `~`
   - `--all` or empty → every `.` row in §T order

## PLAN

Native plan mode. For chosen task(s):

1. Cite every §V invariant that applies. Plan must respect all.
2. Cite every §I interface touched. Plan must preserve shape.
3. List files to create / edit.
4. List tests to add or update (one per invariant touched).
5. Name verification command (test, build, lint).

Show plan. Wait for user OK unless auto mode.

## EXECUTE

Per task in order:

1. Flip §T.n status cell `.` → `~`. Just write to SPEC.md.
2. Edit code per plan.
3. Run verification command.
4. **Pass** → flip `~` → `x`. Next task.
5. **Fail** → invoke backprop skill. Do NOT retry blindly.

## FAIL → BACKPROP

On test/build failure:

1. Read failure output.
2. Ask: is failure (a) my code bug, (b) spec wrong, or (c) unspecified edge case?
3. If (a) → fix code, re-run. No spec change.
4. If (b) or (c) → invoke spec skill with `bug: <cause>` first, let it update §V and §B, then resume build against updated spec.

Rule: never silently fix root-cause without considering backprop. §B is the memory that stops recurrence.

## WRITE POLICY

- Only flip §T status. No other SPEC.md edits from build.
- Other spec edits → invoke spec skill.
- Commit after each §T completes. Message: `T<n>: <goal line>` + §V cites.

## VERIFICATION

Task `x` only if:
- Verification command exits 0.
- New test(s) added per plan.
- No §V invariant regressed (run full test suite at end).

## NON-GOALS

- No sub-agents. No parallel workers. Main thread only.
- No progress dashboards. `cat SPEC.md | grep §T` is the dashboard.
- No speculative work beyond chosen task scope.


---
*Source: https://skills.yangsir.net/skill/gh-build*
*Markdown mirror: https://skills.yangsir.net/api/skill/gh-build/markdown*