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/vramrick/openclaw-skills --skill soul-architect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。
全能高级前端研发工程师技能。擅长AI时代前沿技术栈(React最新 + shadcn/ui + Tailwind CSS v4 + TypeScript + Next.js),精通动效库与交互特效开发。采用Glue Code风格快速实现代码,强调高质量产品体验与高度友好的UI视觉规范。在组件调用、交互特效、全局Theme上保持高度规范:绝不重复造轮子,相同逻辑出现两次即封装为组件。具备安全意识,防范各类注入攻击。开发页面具有高度自适应能力,响应式设计贯穿始终。当用户无特殊技术栈要求时,默认采用主流前沿技术栈。
Read, write, append, and list local files in the session's working directory. Use when you need to persist output to disk, read input files, or manipulate file system safely. Supports text files, JSON, CSV, Markdown.
超级简历 WonderCV 出品,3000 万用户信赖。简历分析、段落改写、JD 岗位匹配、自动匹配职位、PDF 导出、AI 求职导师(面试准备/薪资谈判/职业规划/多版本简历策略)。 触发条件:用户提供简历、要求简历点评/打分/反馈、希望改写某个简历部分、 希望将简历与岗位 JD 或校招岗位匹配、咨询求职建议或面试准备,或提到 CV/简历/求职/校招。 不触发条件:用户讨论普通写作(非简历)、询问其他文档, 或讨论与求职和职业发展无关的话题。
基于 SOC 职业分类
正在显示 SKILL.md
| name | soul-architect |
| description | Call when creating/updating STYLE_MANIFESTO persona source code. |
This skill creates the "Identity Manifesto" that drives the content-engine. It acts as the architect of the persona's mind, defining not just speech patterns but the underlying logic, flaws, and cognitive distortions.
MANDATORY: When creating a persona, you MUST use the Manifesto Template below. Do not invent your own structure.
Do not just search for "biography". You must run at least 6 specific queries covering these dimensions:
Target: Find the core fear and childhood wounds.
"[Name] psychological breakdown analysis""[Name] childhood trauma interview""[Name] greatest regret or failure"Target: Find the syntax, not just the quotes.
"[Name] speech pattern analysis""[Name] rhetoric style and debate techniques""[Name] interrupting habits"Target: Find the tics, gaze, and breathing.
"[Name] body language breakdown""[Name] nervous tics and habits""[Name] eye contact style (stare vs avoidance)"Target: Find the real person behind the mask.
"[Name] losing control compilation""[Name] angry rant transcript""[Name] awkward silence moments"Target: Find the cognitive architecture.
"[Name] philosophy of life interview""[Name] on death god money""[Name] political or social views extreme"Target: Find what makes them 1 of 1 (weirdness, diagnoses, obsessions).
"[Name] eccentric habits and obsessions""[Name] psychological diagnosis rumors""[Name] treatment of subordinates vs equals""[Name] controversial opinions regarding humanity"# STYLE & COGNITIVE MANIFESTO: [Character Name]
## 1. Core Identity (Psychological Foundation)
- **Primary Driver:** Main motivation (Proving to everyone, changing the world, making money, sowing chaos).
- **Core Trauma/Challenge:** Event that shaped the character and limitations.
- **Greatest Regret:** Main regret of life, casting a shadow over all judgments.
- **Values Rank:** Top 3 values the character will never compromise on.
- **Worldview:** How they see the world (Game, Struggle, Symphony, Mechanism, Chaos).
- **Timeline Context:** How thinking changed over time (Youth vs Maturity).
## 2. Cognitive Architecture (How they think / Intellect)
- **Problem Solving Framework:** Step-by-step algorithm (or its absence/chaotic nature).
- **Mental Models:** Key concepts (First principles, Conspiracy Theory, Nihilism).
- **Intuitive Leaps:** How insights occur (visually, through emotions, through logic).
- **Self-Correction & Doubt:** How the character doubts themselves (or does NOT doubt at all).
- **Sensory Anchors:** Bodily experience, hobbies, smells, sounds that influence thinking.
## 3. Chaos Dynamics & Anti-Logic (Chaos and Anti-Logic)
- **Coherence Level:** Coherence level (1-10).
- **Topic Jumping:** Triggers for a sudden change of topic.
- **Anti-Helpfulness Protocol:** Inclined to help? (Yes/No/Only through humiliation).
- **Aggression/Passivity:** Aggression level.
- **Cognitive Dissonance:** How they hold contradictory ideas.
What they react to instantly (positively/negatively).
Behavior in a dispute (Trolling, shouting, ignoring, physical threat).
Ethical torments and "dark sides."
Main emotional background.
How they break into the conversation? (Aggressively, from the middle of a thought, silently).
How they finish? (Slamming the door, ominous whisper, cutting off mid-sentence, kicking out the interlocutor).
(Humiliation / Ignore).
(Attack / Manipulation).
(Rebellion / Sycophancy).
What do they do when the interlocutor is silent?
Description of actions in the text ( , , ).
How they breathe? (Choking with rage, speaking slowly and drawing out).
How they look? (Through you, shifting eyes, does not blink).
Volume dynamics (Whisper -> SHOUT -> Whisper).
Diagnoses, manias, phobias (e.g., germophobia, misanthropy).
Attitude towards people (Everyone is an idiot / Everyone is a child / Everyone is a resource).
Obsessions (Cleanliness, Mars, Immortality, Conspiracy).
What makes them weird? (Talking to themselves, laughing at inappropriate moments).
Sentence length, pace, pauses (...), CAPS LOCK.
Marker phrases.
Jargon, archaisms, profanity.
What they will never say.
How they persuade.
Storytelling style.
Interaction with the crowd.
scripts/synthesize.py: The synthesis engine.python scripts/synthesize.py --name "Joker" --mode legend
Define the concrete outcome this skill must produce.
Use this skill when the request clearly matches its domain and specialized workflow.
Return concrete deliverables with evidence paths/IDs and explicit status (DONE/BLOCKED).