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.
npx skills add silent-rs/silent-Tiangong --skill skill_creatorgit clone --depth 1 https://github.com/silent-rs/silent-TiangongWrote 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.
[](https://agentmods.dev/skills/silent-rs/silent-tiangong/skill_creator)<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.
<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>- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once 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 |
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} 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
- 确认用户想创建什么功能的 Skill
- 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} - 分析外部 Skill 的功能、依赖和调用方式
二、创建 Skill 文件
在 ~/.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(stdio或http)
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:
- 分析入口文件:找到 README 或配置文件,理解功能和依赖
- 提取执行逻辑:识别核心脚本和参数
- 创建 skill.toml:填写 id、name、requires
- 编写 SKILL.md:将调用方式转换为
run_command+ 脚本参数格式 - 适配脚本:确保脚本可通过命令行参数调用,输出 JSON
- 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
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.
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.
- 11d ago First seen · 115 lines · 0 tokens per session scan A 6f853c624bdf
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.
Other skills, from other repositories
codexplusplus
A desktop companion for Codex that connects through Chromium's developer interface and a local helper service. It can switch providers, convert between two chat API formats, manage sessions, export Markdown, track token usage history, and change parts of the interface.
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
ax-rust-signature
Use when writing Rust code with axllm for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.
dws
A command-line guide for DingTalk, a workplace platform with chat, documents, calendars, approvals, tasks, and other business tools.
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
government-writing
A skill for writing formal Chinese government documents, including notices and opinions, in the required official format.