技能实施

工程开发 社区

技能解读

当前原文的自动摘译,尚未人工审校。

触发条件

该技能在以下情况下激活: 任务类型为“z3”/实施命令目标 Z3 任务 计划存在并且任务已准备好实施

第一阶段:输入验证

验证任务编号是否存在且语言为“z3”。

第 2 阶段:预检状态更新

在调用子代理之前将状态更新为“实施”。

第 3 阶段:准备委托上下文

包括task_context、plan_path、metadata_file_path。

第 4 阶段:调用子代理

使用具有 subagent_type 的代理工具:“z3-implementation-agent”。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
工程开发
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@benbrastmckie · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
需简单配置
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
  • 命令执行
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Z3 Implementation Skill

Thin wrapper that delegates Z3 implementation to `z3-implementation-agent` subagent.

## Trigger Conditions

This skill activates when:
- Task type is "z3"
- /implement command targets a Z3 task
- Plan exists and task is ready for implementation

## Execution Flow

### Stage 1: Input Validation
Validate task_number exists and language is "z3".

### Stage 2: Preflight Status Update
Update status to "implementing" BEFORE invoking subagent.

### Stage 3: Prepare Delegation Context
Include task_context, plan_path, metadata_file_path.

### Stage 4: Invoke Subagent
Use Agent tool with subagent_type: "z3-implementation-agent".

### Stage 4b: Self-Execution Fallback

**CRITICAL**: If you performed the work above WITHOUT using the Agent tool (i.e., you read files,
wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a
`.return-meta.json` file now before proceeding to postflight. Use the schema from
`return-metadata-file.md` with status value "implemented".

If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata.

## Postflight (ALWAYS EXECUTE)

The following stages MUST execute after work is complete, whether the work was done by a
subagent or inline (Stage 4b). Do NOT skip these stages for any reason.

### Stage 5: Parse Subagent Return
Read the metadata file from `specs/{N}_{SLUG}/.return-meta.json`.

### Stage 6: Update Task Status (Postflight)
Update state.json and TODO.md based on result.

### Stage 7: Link Artifacts
Add artifact to state.json with summary. Update TODO.md per `@.claude/context/patterns/artifact-linking-todo.md` with `field_name=**Summary**`, `next_field=**Description**`.

### Stage 8: Git Commit
Commit changes with session ID.

### Stage 9: Return Brief Summary

## MUST NOT (Postflight Boundary)

After the agent returns, this skill MUST NOT:

1. **Edit Z3 files** - All constraint work is done by agent
2. **Run z3 solver** - Verification is done by agent
3. **Analyze or grep source** - Analysis is agent work
4. **Write summary/reports** - Artifact creation is agent work

> **PROHIBITION**: If the subagent returned partial or failed status, the lead skill MUST NOT attempt to continue, complete, or "fill in" the subagent's work. Report the partial/failed status and let the user re-run `/implement` to resume.

The postflight phase is LIMITED TO:
- Reading agent metadata file
- Updating state.json via jq
- Updating TODO.md status marker via Edit
- Linking artifacts in state.json
- Git commit
- Cleanup of temp/marker files

Reference: @.claude/context/standards/postflight-tool-restrictions.md

---

## Return Format

Brief text summary (NOT JSON).

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。