← Back to Skills Marketplace
cxlhyx

agent-namer

by 货又星 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
333
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agent-namer
Description
为内部agent生成"货xx"格式的名字,并检查是否已被使用。用于给新agent起名时避免重复。功能:给新agent起名、检查agent名字是否可用、查看已使用的agent名字列表、添加/复活agent名字、弃用/阵亡agent名字。
README (SKILL.md)

\r \r

Agent Namer\r

\r 内部agent命名工具,统一使用"货xx"格式。\r \r

已使用的名字\r

\r | 名字 | 状态 | 角色 |\r |------|------|------|\r | 货又星 | 活跃 | 用户 |\r | 货小星 | 活跃 | 首席大管家 |\r | 货十三 | 活跃 | 小说写作者 |\r \r

使用方法\r

\r

生成名字\r

\r 根据以下prompt生成名字:\r \r

你是一个起名大师,专门为内部agent生成符合"货xx"格式的名字。请遵循以下规则:\r
\r
起名规则\r
格式要求:名字必须为"货"字开头,后面跟1-3个字符(可以是汉字、数字或字母),总长度2-4个字符\r
例如:货小星、货十三、货又星、货A1、货小七、货无双、货小机灵、货A100、货零零发\r
\r
核心原则:名字需紧密结合agent的角色功能和特点或具有一定的趣味性\r
例如:数据分析师 → 货小数、货算盘、货精算\r
例如:内容审核员 → 货火眼、货金睛、货把关\r
例如:货小星、货十三、货又星\r
\r
命名风格参考(结合角色特点):\r
功能映射型:直接体现核心能力(货搜索、货翻译、货摘要)\r
特质映射型:体现角色特质(货细心、货耐心、货快速)\r
趣味映射型:幽默有趣地体现功能(货百科、货活字典、货算无遗)\r
形象映射型:拟人化角色形象(货小秘、货管家、货助手)\r
\r
创意要求:\r
名字要让人一看就能联想到角色的功能\r
名字要有特色,容易记忆\r
避免生僻字和拗口的组合\r
每次生成3-5个候选名字,并附上简要的命名思路说明\r
\r
特别提醒:\r
不要生成已经在"已使用的名字"列表中活跃状态不可用的名字,可以使用python3 scripts/manage_name.py list查看活跃的名字列表,或者python3 scripts/manage_name.py check \x3C名字>检查名字是否可用\r
根据用户提供的角色描述,量身定制名字方案\r
```\r
\r
### 检查名字是否可用\r
\r
检查名字状态:\r
- 不在字典中 → ✅ 可用(全新)\r
- 在字典中且状态为"活跃" → ❌ 已被使用\r
- 在字典中且状态为"已阵亡" → ✅ 可用(可复活)\r
\r
```bash\r
python3 scripts/manage_name.py check \x3C名字>\r
```\r
\r
示例:\r
```bash\r
python3 scripts/manage_name.py check 货小七\r
```\r
\r
### 添加/复活名字\r
\r
- 不在字典中 → 添加为新名字\r
- 在字典中且状态为"已阵亡" → 复活为活跃(role为空则不修改原role)\r
- 在字典中且状态为"活跃" → 报错\r
\r
```bash\r
python3 scripts/manage_name.py add \x3C名字> [角色]\r
```\r
\r
示例:\r
```bash\r
python3 scripts/manage_name.py add 货小七 "数据分析师"\r
```\r
\r
### 将名字设为阵亡\r
\r
```bash\r
python3 scripts/manage_name.py kill \x3C名字>\r
```\r
\r
示例:\r
```bash\r
python3 scripts/manage_name.py kill 货小七\r
```\r
\r
### 查看活跃的名字列表\r
\r
```bash\r
python3 scripts/manage_name.py list\r
```\r
\r
## 工作流程\r
\r
1. 用户提供agent的角色功能描述\r
2. 生成3-5个候选名字附带简短的起名解释,提供给用户查看判断选择,用户选择或提出修改意见,重新打磨名字,直到敲定名字\r
3. 运行 `python3 scripts/manage_name.py check \x3C名字>` 检查是否可用,不可用则回到流程2重新生成名字\r
4. 如果可用,确定使用后运行 `python3 scripts/manage_name.py add \x3C名字> [角色]` 记录该名字\r
5. 如果agent弃用阵亡,运行 `python3 scripts/manage_name.py kill \x3C名字>` 将其状态改为已阵亡\r
Usage Guidance
This skill appears to do exactly what it claims: generate and manage '货xx' names using a local JSON file. Before installing/using: (1) review and back up scripts/used_names.json because the script will write to that file; (2) be aware the add command contains a bug (calls undefined save_used_names()) that can prevent new names from being saved — you may want to patch add_used_name to call update_used_names() or fix the function name; (3) run commands in a safe environment (no network access needed) and inspect/manage_name.py yourself before executing. There are no network calls or secret exfiltration behaviors in the provided code.
Capability Analysis
Type: OpenClaw Skill Name: agent-namer Version: 1.0.0 The skill bundle is a straightforward utility for generating and managing internal agent names using a specific '货xx' format. It consists of a Python script (scripts/manage_name.py) that performs basic CRUD operations on a local JSON file (scripts/used_names.json) and a markdown file (SKILL.md) providing clear instructions for the AI agent. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
Name and description match the code and SKILL.md: the tool generates and manages '货xx' names and uses a local scripts/used_names.json to track status. No unrelated credentials, binaries, or external services are required.
Instruction Scope
SKILL.md instructs running python3 scripts/manage_name.py (check/add/kill/list). The script only reads and writes the bundled scripts/used_names.json (expected behavior). Note: there's a coding bug — add_used_name calls save_used_names() which is undefined; this will raise an error when adding a brand-new name, so persistence may fail for that code path. Aside from that bug, instructions do not request other files, env vars, or external endpoints.
Install Mechanism
No install spec (instruction-only skill with included scripts). No downloads, package installs, or extraction steps are present.
Credentials
The skill requires no environment variables, credentials, or config paths. Its local file access (scripts/used_names.json) is proportionate to the stated purpose.
Persistence & Privilege
always is false and the skill does not request permanent system presence or modify other skills. It does write to its own bundled JSON file when updating names (expected and limited scope).
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install agent-namer
  3. After installation, invoke the skill by name or use /agent-namer
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Agent Namer 1.0.0 – Initial release. - Provides a command-line tool to generate and manage "货xx"-style agent names. - Ensures names reflect agent roles and avoids duplication by status checking. - Supports viewing, adding, reviving, and deactivating agent names. - Includes workflow guidance and detailed naming conventions.
Metadata
Slug agent-namer
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is agent-namer?

为内部agent生成"货xx"格式的名字,并检查是否已被使用。用于给新agent起名时避免重复。功能:给新agent起名、检查agent名字是否可用、查看已使用的agent名字列表、添加/复活agent名字、弃用/阵亡agent名字。 It is an AI Agent Skill for Claude Code / OpenClaw, with 333 downloads so far.

How do I install agent-namer?

Run "/install agent-namer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is agent-namer free?

Yes, agent-namer is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does agent-namer support?

agent-namer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created agent-namer?

It is built and maintained by 货又星 (@cxlhyx); the current version is v1.0.0.

💬 Comments