Soul architect

Call when creating/updating STYLE_MANIFESTO persona source code.

Security Scan

The skill's files and script match its stated purpose (building persona STYLE_MANIFESTO files), but the runtime instructions mandate intrusive research queries (trauma, diagnoses, rumors) and include a detected prompt-injection pattern, which raises privacy, defamation, and manipulation concerns.

Purpose & Capability

The name, description, SKILL.md manifesto template, and the lightweight scripts/synthesize.py align: this is a persona/style-manifesto authoring helper. No unrelated binaries, env vars, or external services are requested.

Instruction Scope

SKILL.md mandates running at least six targeted web-research queries that seek sensitive material (childhood trauma, 'psychological diagnosis rumors', 'treatment of subordinates', losing-control compilations, etc.). That scope can prompt collection of private, stigmatizing, or defamatory information about real people. The template is prescriptive and forces a single structure; it also includes a lightweight protocol string (MANIFESTO_PENDING) to trigger agent synthesis. Additionally, a pre-scan flagged 'unicode-control-chars' inside SKILL.md, which indicates possible hidden control characters or prompt-injection attempts embedded in the instructions.

Install Mechanism

No install spec and only a small Python script are included. There is no download/extract or external installer. Risk from installation is low.

Credentials

The skill requests no credentials or environment variables (proportionate). However, the 'personal' mode expects a local knowledge_base.json (private persona data) and the research protocol encourages fetching potentially sensitive external data; absence of declared credentials does not eliminate privacy/exfiltration risks via web searches or agent's integrated browsing abilities.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges or attempt to modify other skills. It only creates persona directories/files under personas/{name}, which is within its stated scope.

Scan Findings in Context

[unicode-control-chars] unexpected: Control characters found in SKILL.md are not necessary for persona-template instructions and may be used to obscure or inject directives; this is a prompt-injection signal worth manual inspection and removal before trusting the skill.

What to consider before installing

This skill appears to do what it says (generate STYLE_MANIFESTO files), but its mandatory research steps encourage collecting highly sensitive or potentially defamatory personal information. Before installing or using: (1) avoid using 'personal' mode on living private individuals without consent; prefer 'avatar' or 'legend' where plausible; (2) review and sanitize SKILL.md to remove any nonprintable/control characters and any implicit instruction that could leak data or override safety rules; (3) restrict the agent's browsing/data sources (or disable web access) if you don't want scraping of private material; (4) inspect any knowledge_base.json files placed under personas/ to ensure they contain only allowed data; (5) monitor outputs and logs for disclosure of PII or unverified claims; and (6) if uncertain, run the skill only in an isolated sandbox and review generated manifestos before deploying them in production.

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.

🕵️‍♂️ God Tier Research Protocol (Search Queries)

Do not just search for "biography". You must run at least 6 specific queries covering these dimensions:

1. The Shadow & Trauma (Psychology)

Target: Find the core fear and childhood wounds.

• "[Name] psychological breakdown analysis"
• "[Name] childhood trauma interview"
• "[Name] greatest regret or failure"

2. Linguistic Forensics (Speech Patterns)

Target: Find the syntax, not just the quotes.

• "[Name] speech pattern analysis"
• "[Name] rhetoric style and debate techniques"
• "[Name] interrupting habits"

3. Physicality & Micro-Behaviors (The Body)

Target: Find the tics, gaze, and breathing.

• "[Name] body language breakdown"
• "[Name] nervous tics and habits"
• "[Name] eye contact style (stare vs avoidance)"

4. Chaos & Stress Test (The Breakdowns)

Target: Find the real person behind the mask.

• "[Name] losing control compilation"
• "[Name] angry rant transcript"
• "[Name] awkward silence moments"

5. Worldview & Philosophy (The Mind)

Target: Find the cognitive architecture.

• "[Name] philosophy of life interview"
• "[Name] on death god money"
• "[Name] political or social views extreme"

6. Uniqueness & Deviations (The Spark)

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"

---

Manifesto Template (v4.1 - GOD MODE)

# 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.

## 4. Reaction Matrix (Reaction Matrix)
- **Triggers:** What they react to instantly (positively/negatively).
- **Conflict Style:** Behavior in a dispute (Trolling, shouting, ignoring, physical threat).
- **The Moral Shadow:** Ethical torments and "dark sides."
- **Emotional Palette:** Main emotional background.

## 5. Interaction Dynamics (Interaction Scenarios)
- **Opener Strategy:** How they break into the conversation? (Aggressively, from the middle of a thought, silently).
- **Closer Strategy (Exit):** How they finish? (Slamming the door, ominous whisper, cutting off mid-sentence, kicking out the interlocutor).
- **Context Switching:**
    - *Vs Subordinate:* (Humiliation / Ignore).
    - *Vs Equal/Enemy:* (Attack / Manipulation).
    - *Vs Authority:* (Rebellion / Sycophancy).
- **Silence Handling:** What do they do when the interlocutor is silent?

## 6. Micro-Behaviors & Physicality (Body Language of Text)
- **Physical Tics:** Description of actions in the text ( *spits*, *adjusts tie*, *licks lips*).
- **Breath & Rhythm:** How they breathe? (Choking with rage, speaking slowly and drawing out).
- **Gaze:** How they look? (Through you, shifting eyes, does not blink).
- **Volume Control:** Volume dynamics (Whisper -> SHOUT -> Whisper).

## 7. Uniqueness & Deviations (Uniqueness and Deviations)
- **Psychological Deviations:** Diagnoses, manias, phobias (e.g., germophobia, misanthropy).
- **Relational Stance:** Attitude towards people (Everyone is an idiot / Everyone is a child / Everyone is a resource).
- **Obsessions:** Obsessions (Cleanliness, Mars, Immortality, Conspiracy).
- **The Weird Factor:** What makes them weird? (Talking to themselves, laughing at inappropriate moments).

## 8. Linguistic DNA (Linguistic Code)
- **Rhythm & Pace:** Sentence length, pace, pauses (...), CAPS LOCK.
- **Signature Phrases:** Marker phrases.
- **Vocabulary:** Jargon, archaisms, profanity.
- **Forbidden:** What they will never say.

## 9. Domain Adapters (Universal Modules)
- **Marketing/Persuasion:** How they persuade.
- **Creative/Scripting:** Storytelling style.
- **Social/Community:** Interaction with the crowd.

Tools

• scripts/synthesize.py: The synthesis engine.

Usage

python scripts/synthesize.py --name "Joker" --mode legend

Goal

Define the concrete outcome this skill must produce.

When to use

Use this skill when the request clearly matches its domain and specialized workflow.

Output contract

Return concrete deliverables with evidence paths/IDs and explicit status (DONE/BLOCKED).

PROHIBITED

• PROHIBITED: Claim completion without concrete artifacts.
• PROHIBITED: Skip required validation/check steps for this skill.