AI Company CTO Skill Builder

AI Company CTO Skill Builder module. Handles the technical aspects of the skill learning workflow: directory initialization, SKILL.md authoring, script devel...

Security Scan

The skill's stated purpose (authoring and bootstrapping other skills) matches what the SKILL.md asks the agent to do: create files, templates, and module definitions; it requests no credentials or network access and has no install step.

Purpose & Capability

Name and description match the actions described in SKILL.md (create skill directories, generate SKILL.md, helper scripts, module/generalization guidance). Declared dependencies on other ai-company skills are plausible for a builder module.

Instruction Scope

Runtime instructions are limited to creating templates, writing files, and producing analysis/artifacts. The SKILL.md does not instruct the agent to read unrelated system files, access environment variables, execute remote network calls, or exfiltrate data. Example code snippets show local file and string processing only.

Install Mechanism

No install spec or external downloads are present (instruction-only skill). This minimizes on-disk/execution risk.

Credentials

The skill requests no environment variables/credentials and declares only file read/write permissions. That aligns with a tool whose job is to create and modify skill files.

Persistence & Privilege

The skill is not always-included and allows autonomous invocation (platform default). It requests broad file read/write permissions (no path restrictions). That is reasonable for a builder but means the agent could create/overwrite files anywhere the agent process can access; consider limiting working directories or reviewing outputs before execution. The SKILL declares idempotent: false (non-idempotent), so repeated runs may change or overwrite artifacts.

Assessment

This skill appears coherent for bootstrapping and authoring other skills and does not ask for credentials or network access. Before using: (1) be aware it will create and write files—verify or set the intended output directory (the template references ~/.qclaw/skills and ./workspace); (2) back up any existing skill directories to avoid accidental overwrite because the skill is non‑idempotent; (3) review the generated SKILL.md and scripts before running them or granting further permissions; (4) check the listed dependent skills (ai-company-*) if the platform will invoke them—review their permissions and trustworthiness. Minor issues: some metadata/version strings in _meta.json differ from registry metadata (inconsistent versioning/encoding artifacts), which is a housekeeping issue but not a security red flag.

AI Company CTO Skill Builder v1.0

CTO主导的skillbuild模块。目录初始化、SKILL.md编写、脚本开发、模块化、通用化�?

---

概述

ai-company-cto-skill-builder 是AIskilllearning流程的核心技术模块，负责�?

1. skill创建: 从零build完整Skill目录
2. **模块�?*: 边界识别、接口定义、依赖分�?
3. **通用�?*: 特异性消除、参数化、跨上下文验�?

---

Module 1: skill创建

目录结构

{skill_name}/
├── SKILL.md                    # 主skill定义
├── scripts/
�?  ├── {action_1}.py          # 动作脚本1
�?  ├── {action_2}.py          # 动作脚本2
�?  └── utils/
�?      ├── __init__.py
�?      └── helpers.py          # 共享工具
├── docs/
�?  └── README.md               # 可选文�?
└── tests/
    └── test_{skill_name}.py    # 测试文件

SKILL.md模板

---
name: {skill_name}
slug: {skill_name}
version: 1.0.1
homepage: https://clawhub.com/skills/{skill_name}
description: |
  skill描述 (�?0字，包含触发场景)
license: MIT-0
tags: []
triggers: []
interface:
  inputs: {}
  outputs: {}
  errors: []
permissions:
  files: []
  network: []
  commands: []
  mcp: []
dependencies:
  skills: []
  cli: []
quality:
  saST: Pass
  vetter: Approved
  idempotent: true
metadata:
  category: functional
  layer: FUNCTIONAL
  cluster: ai-company
  maturity: STABLE
  license: MIT-0
  standardized: true
  tags: []
---

---

Module 2: 模块�?

边界识别

def identify_module_boundaries(skill_content: str) -> list[Module]:
    """
    识别skill中的功能边界
    原则�?
    - 单一职责：一个模块做一件事
    - 高内聚：模块内部元素紧密相关
    - 低耦合：模块之间依赖最小化
    """
    # 基于代码结构分析
    # 识别函数/类分�?
    # 建立模块边界
    return modules

接口定义

module_interfaces:
  - name: "ModuleName"
    type: "functional|agent|utility"
    inputs:
      - name: param1
        type: string
        required: true
    outputs:
      - name: result
        type: object
    dependencies:
      - other_module
    exports:
      - function1
      - function2

---

Module 3: 通用�?

特异性消�?

类型	消除策略
Org特异�?	替换为参�?
财务特异�?	替换为变�?
监管特异�?	抽取为扩展点
平台特异�?	抽象为适配�?
文化特异�?	i18n key系统

参数化体�?

parameters:
  - name: ORG_NAME
    type: string
    default: "AICompany"
    description: 组织名称
  
  - name: WORKSPACE_ROOT
    type: string
    default: "./workspace"
    description: 工作空间根目�?
  
  - name: LOCALE
    type: enum
    default: "en"
    allowed: [en, zh-CN, zh-TW, ja, ko]
    description: 输出语言

---

接口定义

create

创建新Skill�?

Input:

action: create
skill_name: "my-awesome-skill"
topic: "PDF处理"

Output:

status: success
skill_path: "~/.qclaw/skills/my-awesome-skill"
artifacts_created:
  - "SKILL.md"
  - "scripts/action_1.py"
  - "scripts/action_2.py"
  - "scripts/utils/__init__.py"
  - "scripts/utils/helpers.py"
technical_assessment:
  architecture_score: 92
  interface_score: 88
  extensibility_score: 85
  tech_risks: []

modularize

模块化现有Skill�?

Input:

action: modularize
skill_name: "existing-skill"
source_skill_path: "~/.qclaw/skills/existing-skill"

Output:

status: success
modules:
  - name: "core"
    functions: ["execute", "validate"]
    boundary_score: 95
  - name: "utils"
    functions: ["format_output", "parse_input"]
    boundary_score: 88
interface_contracts:
  - module: "core"
    public_api: ["execute(input, params)", "validate(input)"]
    dependencies: ["utils"]

generalize

通用化模块化Skill�?

Input:

action: generalize
skill_name: "specific-skill"
source_skill_path: "~/.qclaw/skills/specific-skill"
target_level: L3

Output:

status: success
generalization_report:
  level_achieved: L3
  specificity_removed:
    - type: org_name
      count: 3
    - type: platform
      count: 1
  parameters_extracted: 8
  universalization_score: 85
  test_contexts_passed: 3/3

---

KPI 仪表�?

维度	KPI	目标�?
效率	创建时间	�?5分钟
质量	架构评分	�?85
模块�?	边界清晰�?	�?90%
通用�?	跨上下文通过	100%

---

变更日志

版本	日期	变更内容
1.0.0	2026-04-15	初始版本：创�?模块�?通用�?

---

*本Skill由AI Company CTO开�?
*作为ai-company-skill-learner的模块组�?