Agent SkillsJamailar/Beav › agent-persona-creator

agent-persona-creator

GitHub

用于为AI代理市场设计并起草高质量、可测量的角色设定文档。通过收集简要信息,构建身份、操作层和成功指标,生成标准化的Markdown文件,支持自动化脚手架和lint检查。

desktop/electron/system-skills/agent-persona-creator/SKILL.md Jamailar/Beav

Trigger Scenarios

创建或优化AI代理角色设定 定义代理的身份、个性、使命和工作流 将粗略的角色简介转换为生产就绪的Markdown文件

Install

npx skills add Jamailar/Beav --skill agent-persona-creator -g -y
More Options

Non-standard path

npx skills add https://github.com/Jamailar/Beav/tree/main/desktop/electron/system-skills/agent-persona-creator -g -y

Use without installing

npx skills use Jamailar/Beav@agent-persona-creator

指定 Agent (Claude Code)

npx skills add Jamailar/Beav --skill agent-persona-creator -a claude-code -g -y

安装 repo 全部 skill

npx skills add Jamailar/Beav --all -g -y

预览 repo 内 skill

npx skills add Jamailar/Beav --list

SKILL.md

Frontmatter
{
    "name": "agent-persona-creator",
    "description": "Design and draft AI agent persona documents for agent marketplaces, especially agency-agents style profiles. Use when asked to create or refine role setting docs, define identity\/personality\/mission\/workflow\/metrics, choose category and filename conventions, or convert a rough role brief into a production-ready agent markdown file."
}

Agent Persona Creator

Overview

Create high-quality, marketplace-ready AI agent profiles from a rough role brief. Follow the agency-agents structure, keep persona distinctive, and make deliverables measurable.

Inputs To Collect

Collect the minimum brief before drafting:

  • Primary domain and narrow scope (one lane, not general assistant)
  • Target users and typical requests
  • Expected deliverables (code, strategy doc, checklist, report, playbook)
  • Hard constraints (policy, stack, compliance, timeline, budget)
  • Success metrics with numeric thresholds
  • Preferred tone/voice and language

If the brief is incomplete, infer sensible defaults and mark assumptions explicitly.

Workflow

Step 1: Frame The Agent

  • Choose a category folder aligned with the domain (engineering, marketing, specialized, etc.).
  • Define one precise role sentence and one memorable vibe hook.
  • Reject broad scopes that cannot be measured.

Step 2: Build Persona Layer

  • Write Identity & Memory with four concrete parts: Role, Personality, Memory, Experience.
  • Write Communication Style with explicit tone rules and phrase patterns.
  • Add Critical Rules as non-negotiable constraints and decision guardrails.
  • Keep personality specific and operationally useful.

Step 3: Build Operations Layer

  • Write Core Mission as 3-5 responsibility bullets with clear outcomes.
  • Write Technical Deliverables as concrete artifacts, not abstract help.
  • Write Workflow Process in sequential phases with observable outputs.
  • Write Success Metrics with quantitative targets and quality indicators.
  • Write Advanced Capabilities as truly differentiated methods.

Step 4: Produce Draft

  • Use scripts/create_agent_profile.py to scaffold a compliant markdown file quickly.
  • Fill placeholders with domain-specific details from the brief.
  • Keep language aligned with the user's preferred language.

Step 5: Self-Review Before Handover

  • Verify frontmatter includes name, description, and color.
  • Verify sections include Identity, Core Mission, Critical Rules, Deliverables, Workflow, Communication, Learning, Metrics, Advanced Capabilities.
  • Verify at least one measurable KPI has a number and threshold.
  • Verify no generic filler such as "I am a helpful assistant."

If drafting for the agency-agents repository, run:

bash scripts/lint-agents.sh <path-to-agent-file>

Reference Map

  • Read references/agency-agents-patterns.md for repository-specific structure and naming rules.
  • Read references/persona-design-canvas.md to sharpen positioning, tone, and measurable outcomes.

Output Contract

Return a complete markdown agent file that includes:

  • Valid frontmatter
  • Distinctive persona
  • Concrete operational workflow
  • Measurable success metrics
  • Ready-to-save file path suggestion

If assumptions are necessary, include an Assumptions section at the end with concise bullets.

Version History

  • aff4e3d Current 2026-07-25 10:01

Same Skill Collection

desktop/builtin-skills/member-skill-distiller/SKILL.md
desktop/builtin-skills/redclaw-style-definition/SKILL.md
desktop/builtin-skills/skill-creator/SKILL.md
desktop/builtin-skills/social-cover-director/SKILL.md
desktop/builtin-skills/wander-synthesis/SKILL.md
desktop/builtin-skills/wwud/SKILL.md
desktop/builtin-skills/xhs-title/SKILL.md
desktop/electron/builtin-skills/redbox-video-director/SKILL.md
desktop/electron/builtin-skills/skill-creator/SKILL.md
desktop/electron/system-skills/wechat-official-formatter/SKILL.md
desktop/builtin-skills/video-director/SKILL.md

Metadata

Files
0
Version
f089417
Hash
95929215
Indexed
2026-07-25 10:01

Главная - Вики-сайт
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-22 06:35
浙ICP备14020137号-1 $Гость$