skill_creator

skill_creator is a skill for Claude Code, Codex from silent-rs/silent-Tiangong. It costs 0 tokens per session (942 once invoked), scanned A, original, Apache-2.0.

An interactive workflow for creating, importing, and adapting Tiangong skills, which are instruction packages for an AI agent.

In plain words
What is it for?
Use it to make a skill from scratch, import one from GitHub, define how it is called, list its parameters and output, and set its required access.
Why use it?
It explains the required files, metadata, permissions, and installation layout so a skill can be created or brought in from an external source consistently.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to make a skill from scratch, import one from GitHub, define how it is called, list its parameters and output, and set its required access.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/silent-rs/silent-tiangong/skill_creator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add silent-rs/silent-Tiangong --skill skill_creator
Clone the repo
git clone --depth 1 https://github.com/silent-rs/silent-Tiangong

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill_creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/silent-rs/silent-tiangong/skill_creator/github.svg)](https://agentmods.dev/skills/silent-rs/silent-tiangong/skill_creator)
Your own site
<a href="https://agentmods.dev/skills/silent-rs/silent-tiangong/skill_creator"><img src="https://agentmods.dev/badge/skills/silent-rs/silent-tiangong/skill_creator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill_creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/silent-rs/silent-tiangong/skill_creator"><img src="https://agentmods.dev/badge/skills/silent-rs/silent-tiangong/skill_creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 20
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00942
Opus 5 $0.00000 $0.00471
Sonnet 5 $0.00000 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 11d ago against content hash 6f853c624bdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill_creator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL https://api.github.com/repos/{owner}/{repo}/contents/{path}
skills/skill_creator/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill 创建器

创建、导入和适配天工 Skill 的交互式工作流。支持从零创建新 Skill,也支持从 GitHub 等外部来源导入并适配为天工格式。

触发词

创建skill、新建技能、导入skill、创建一个skill、skill_creator

Skill 存储目录

所有 Skill 安装到 ~/.tiangong/skills/<skill-id>/(平铺布局,目录名必须等于 skill.toml 的 id)。

工作流

一、需求分析

  1. 确认用户想创建什么功能的 Skill
  2. 如果用户提供了外部 URL(如 GitHub 仓库),用 run_command 获取信息:
    curl -sL https://api.github.com/repos/{owner}/{repo}/contents/{path}
    
  3. 分析外部 Skill 的功能、依赖和调用方式

二、创建 Skill 文件

~/.tiangong/skills/<skill-id>/ 下用 write_file 等文件工具创建以下文件。

必需文件

1. skill.toml - 元数据声明

id = "my-skill"                    # 唯一 ID(kebab-case,必须与目录名一致)
name = "技能显示名称"               # 中文名称
version = "0.1.0"                   # 版本号
entry = "SKILL.md"                  # 入口文件
available = true                    # 是否启用

[source]
type = "local"
value = ""

[requires]
mcp = []
env = []

[permissions]
fs_read = []
fs_write = []
cmd_exec = []
net = []

2. SKILL.md - 技能使用说明(给 Agent 看的指令文档)

# 技能名称

简要功能描述。

## 调用方法

使用 `run_command` 执行:
\`\`\`bash
python3 {skill_dir}/main.py --arg1 value1
\`\`\`

## 全部参数

| 参数 | 必需 | 说明 |
|------|------|------|
| `--arg1` | 是 | 参数说明 |

## 输出

JSON 格式:`{"ok": true, "result": "..."}`

## 触发词

关键词1、关键词2

{skill_dir} 占位符在运行时会被替换为 skill 目录的绝对路径。

3. 执行脚本 - Python/Shell 脚本(按需)

  • Python 脚本使用 argparse 解析参数
  • 输出 JSON 格式结果到 stdout
  • 错误信息输出到 stderr

三、注册 MCP 服务器(如需)

如果 Skill 依赖 MCP 服务器,使用 register_mcp_server 工具:

  • name: 服务器名称
  • command: 启动命令完整路径(如 /usr/local/bin/uvx
  • args: 命令参数(如 ["mcp-server-name"]
  • env: 环境变量(如 {"API_KEY": "xxx"}
  • transport: 传输方式(stdiohttp

四、验证与提示

创建完成后告知用户:

  • Skill 名称和 ID
  • 触发词
  • 环境变量配置提示(如有)
  • 提示用户:刷新 Skill 列表或开启新对话后生效

外部 Skill 适配指引

将外部 Skill(如 OpenAI Skills、Claude Skills)转换为天工格式:

  1. 分析入口文件:找到 README 或配置文件,理解功能和依赖
  2. 提取执行逻辑:识别核心脚本和参数
  3. 创建 skill.toml:填写 id、name、requires
  4. 编写 SKILL.md:将调用方式转换为 run_command + 脚本参数格式
  5. 适配脚本:确保脚本可通过命令行参数调用,输出 JSON
  6. 处理依赖:Python 脚本头部用 /// script 声明 PEP 723 依赖,或在 SKILL.md 中说明使用 pipx run / uvx

Read the full file on GitHub · 115 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 115 lines · 0 tokens per session scan A 6f853c624bdf

Subscribe to this mod's changes

skill_creator is a skill published in the GitHub repository silent-rs/silent-Tiangong (26 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 942 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.