用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/tomevault-io/skills-registry --skill hugin-scaffold命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | hugin-scaffold |
| description | Generate starter files for a new Hugin agent Use when this capability is needed. |
| metadata | {"author":"gimlelabs"} |
Generate starter files for a new Hugin agent by reading templates from this plugin and customizing them.
Parse the user's arguments to extract:
minimal, tool, or pipeline (default: minimal)Example invocations:
/hugin-agent-creator:hugin-scaffold my_agent - Creates minimal agent/hugin-agent-creator:hugin-scaffold data_processor tool - Creates agent with custom tool/hugin-agent-creator:hugin-scaffold report_generator pipeline - Creates multi-stage pipelineExtract agent_name and type from user input. Validate agent_name is snake_case.
Use Bash to create the directories:
mkdir -p [agent_name]/configs [agent_name]/tasks [agent_name]/templates
# For 'tool' type also:
mkdir -p [agent_name]/tools
IMPORTANT: Read the actual template files from this plugin, then customize them.
Read templates/minimal-config.yaml from this plugin
my_agent with [agent_name]my_system with [agent_name]_system[agent_name]/configs/[agent_name].yamlRead templates/minimal-task.yaml from this plugin
my_task with [agent_name]_task[agent_name]/tasks/[agent_name]_task.yamlRead templates/minimal-template.yaml from this plugin
my_system with [agent_name]_system[agent_name]/templates/[agent_name]_system.yamlRead templates/tool-definition.yaml from this plugin
my_tool with [agent_name]_tool[agent_name]/tools/[agent_name]_tool.yamlRead templates/tool-implementation.py from this plugin
my_tool with [agent_name]_tool[agent_name]/tools/[agent_name]_tool.pyInstead of the single task, create 3 stage tasks:
Read templates/minimal-task.yaml as base, then create:
tasks/stage_1_extract.yaml:
name: stage_1_extract
description: Extract data from input (Stage 1)
parameters:
raw_input:
type: string
description: Raw input data
required: false
default: "Sample input data"
task_sequence:
- stage_2_transform
- stage_3_output
pass_result_as: extracted_data
prompt: |
STAGE 1: EXTRACT
Raw Input: {{ raw_input.value }}
Your task:
1. Parse the raw input
2. Extract key information
3. Use finish with your structured extraction
After creating all files, print:
Created [agent_name] agent ([type] type)
Directory: ./[agent_name]/
Files created:
- configs/[agent_name].yaml
- tasks/[task_name].yaml
- templates/[agent_name]_system.yaml
[If tool type:]
- tools/[agent_name]_tool.yaml
- tools/[agent_name]_tool.py
Run your agent:
uv run hugin run --task [task_name] --task-path ./[agent_name]
Next steps:
1. Edit configs/[agent_name].yaml to customize the agent
2. Edit tasks/[task_name].yaml to define your task logic
3. Edit templates/[agent_name]_system.yaml for the system prompt
[If tool type:]
4. Implement your tool in tools/[agent_name]_tool.py
[If pipeline type:]
4. Customize each stage task in tasks/
For more guidance: /hugin-agent-creator:hugin-guide
All templates are in this plugin's templates/ directory:
templates/minimal-config.yamltemplates/minimal-task.yamltemplates/minimal-template.yamltemplates/tool-definition.yamltemplates/tool-implementation.pyAlways read these files rather than hardcoding their content. This ensures scaffolded agents use the latest template versions.
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
tasks/stage_2_transform.yaml:
name: stage_2_transform
description: Transform extracted data (Stage 2)
parameters:
extracted_data:
type: string
description: Data from Stage 1
required: false
default: ""
pass_result_as: transformed_data
prompt: |
STAGE 2: TRANSFORM
Extracted Data: {{ extracted_data.value }}
Your task:
1. Transform the extracted data
2. Apply any necessary processing
3. Use finish with your transformed result
The result will be passed to Stage 3.
tasks/stage_3_output.yaml:
name: stage_3_output
description: Generate final output (Stage 3)
parameters:
transformed_data:
type: string
description: Data from Stage 2
required: false
default: ""
prompt: |
STAGE 3: OUTPUT
Transformed Data: {{ transformed_data.value }}
Your task:
1. Generate the final output
2. Format it appropriately
3. Use finish with your final result
Update the system template for pipeline context:
name: [agent_name]_system
template: |
You are a data processing assistant working in a multi-stage pipeline.
Follow your stage instructions carefully. Your output will be passed to the next stage.
Always use the finish tool when your stage is complete, including your result.