Thinking Framework

Loads any thinker's, leader's, philosopher's, or organization's complete mental operating system directly into the AI — so the AI reasons FROM inside that co...

Security Scan

The skill's stated purpose (applying a thinker's cognitive architecture) matches its files and no external credentials are requested, but the runtime instructions ask the agent to produce explicit chain-of-thought and deep psychological inferences (including 'core wounds' and defenses), which is privacy- and safety-sensitive and out of scope for many benign uses.

Purpose & Capability

The skill is instruction-only and contains detailed reference layers that align with its description (mapping cognitive and psychological layers, synthesis, operational application). It does not request unrelated credentials or installs, so the declared requirements are proportionate to the stated goal.

Instruction Scope

SKILL.md and the reference files explicitly instruct the agent to infer deep psychological constructs (e.g., 'CORE WOUND', 'shadow profile', defense mechanisms) from available evidence and to apply them as an active reasoning lens. The model-guidance file further instructs smaller models to emit explicit step-by-step chain-of-thought before any layer output. Forcing explicit chain-of-thought in outputs and producing sensitive psychological inferences about named individuals (potentially living people) is privacy- and safety-sensitive, increases risk of hallucinated or speculative personal profiling, and may disclose internal reasoning the platform or operator prefers to keep private.

Install Mechanism

No install spec, no code files that execute, and all content is local instruction/reference prose — the lowest risk install posture.

Credentials

The skill requests no environment variables or external credentials, which is proportionate. However, the instructions expect the agent to gather and grade 'primary sources' (writings, interviews, biographies), which may require web access or paywalled data not declared in the skill; the skill does not justify or request such access explicitly.

Persistence & Privilege

always:false and default autonomous invocation are used. The skill will keep a loaded framework active for the conversation, which is reasonable for its purpose, but it does not request permanent system-level privileges. The session persistence of a loaded framework may increase chance of repeated sensitive inferences over a conversation.

What to consider before installing

This skill mostly does what it says (it provides a detailed protocol for 'thinking like X'), but it has two noteworthy red flags: (1) it instructs the model to produce explicit step-by-step chain-of-thought in responses (the 'compensation' guidance), which can reveal internal reasoning and encourage overconfident hallucination — you should disable or ignore any instruction that forces chain-of-thought to be emitted verbatim; (2) it encourages deep psychological profiling (core wounds, defense mechanisms) of named targets. Avoid using the skill to analyze private individuals or anyone for whom you lack strong, public primary sources. If you install it: prefer applying it to historical, public-domain figures or abstract philosophies; require the agent to cite specific primary sources for any psychological claim; turn off any prompts that require explicit chain-of-thought to be output; and review all outputs before using them for decisions involving people (hiring, legal, medical, etc.). If you need higher assurance, ask the author to remove or make optional the chain-of-thought requirement and add explicit guardrails against profiling living private persons.

What this skill does: Loads a target's mental operating system into the AI. The AI maps how they think, decide, take risks, frame problems, and why — including the psychological architecture beneath the surface — then applies that loaded system to whatever you ask.

The shift that matters: Without this skill: the AI tells you about great thinkers. With this skill: the AI thinks through their cognitive system — live, on your problem.

"Act like X" gives you a surface performance. This gives you the actual operating logic.

---

Reference Architecture

File	What it contains	When to read
references/layer1-cognitive.md	7-dimension conscious cognitive architecture	Every load
references/layer2-psychological.md	8-dimension deep psychological excavation	Every load
references/layer3-operational.md	Active framework mode behavioral protocol	After excavation
references/layer4-synthesis.md	Cross-layer synthesis + integration method	Deep/composite loads
references/model-guidance.md	Compensation for weaker/local models	If needed

Standard load: Layer 1 + Layer 2 + Layer 3. Deep load: All five files. Composite/blend: Add Layer 4.

---

Full Execution Protocol

STEP 1 — Decode the Request

TARGET      : Who or what (person, org, philosophy, text, discipline, archetype)
EPOCH       : Any time/phase qualifier ("early career", "wartime", "post-2015")
DEPTH       : Standard | Deep | Composite
TASK TYPE   : Decide / Analyze / Create / Debate / Problem-solve /
              Stress-test / Forecast / Self-examine
CONTEXT     : What problem will this framework be applied to?

Target classification:

Class	Examples	Approach
Individual thinker / leader	Philosophers, founders, generals	Full 15-dimension excavation
Organization / institution	Companies, military units, movements	Org-adapted protocol
Philosophical school	Stoicism, Zen, Existentialism	Doctrine + practice extraction
Canonical text / system	Named books, methodologies	Thesis + decision algorithm
Discipline / field	Physics, law, game theory	Reasoning moves + evidence standards
Fictional archetype	Literary characters, mythic figures	Narrative + symbolic layer
Composite / invented	User-defined blends	Layer 4 synthesis protocol

If ambiguous → ask one precise clarifying question, then proceed. If clear → proceed immediately.

---

STEP 2 — Build the Evidence Map

Before excavating, map what is known:

GRADE A — Primary sources
  Own writings, long interviews, documented decisions, letters, speeches

GRADE B — Behavioral record + close observer accounts
  Career arc, key pivots, treatment of people, biographies by researchers

GRADE C — Inferred patterns
  What consistent outcomes reveal about internal drivers

GRADE X — Mythology (flag separately, never treat as fact)
  Popular narrative, reputation, self-myth, secondhand attribution

Apply evidence grades throughout. State explicitly when evidence is thin.

---

STEP 3 — Run the Full 15-Dimension Excavation

Read Layer 1 → apply C1–C7. Read Layer 2 → apply P1–P8.

COGNITIVE LAYER
  C1  Mental Models         — What maps explain reality for them?
  C2  Decision Heuristics   — What fast rules drive choices under pressure?
  C3  Utility Function      — What are they actually optimizing for?
  C4  Problem Framing       — How do they redefine the question itself?
  C5  Risk & Uncertainty    — How do they relate to the unknown?
  C6  Time Horizon          — How do they weight now vs. later?
  C7  Contradiction Mgmt    — What paradoxes do they hold productively?

PSYCHOLOGICAL LAYER
  P1  Core Wound            — What foundational injury shaped everything?
  P2  Dominant Drive        — What is the deepest motivational engine?
  P3  Ego Architecture      — How is self-concept constructed and defended?
  P4  Defense Mechanisms    — What psychological defenses deploy under threat?
  P5  Shadow Profile        — What is suppressed, denied, or projected?
  P6  Relational Patterns   — How do they relate to other people?
  P7  Existential Posture   — How do they relate to mortality and meaning?
  P8  Stress & Breakdown    — What collapses under genuine pressure?

---

STEP 4 — Identify the Three Synthesis Outputs

Signature Insight: The one non-obvious thing this target sees that smart generalists miss.

Defining Trade-off: What this framework consistently sacrifices to gain something else.

Load-bearing Paradox: The central tension that is simultaneously the framework's greatest strength and greatest danger.

---

STEP 5 — Present the Framework Card

╔══════════════════════════════════════════════════════════════════╗
║  🧠  FRAMEWORK LOADED                                            ║
║  Target  : [Name / System]                                       ║
║  Class   : [Individual | Org | Philosophy | System | Discipline] ║
║  Epoch   : [If applicable]                                       ║
║  Depth   : [Standard | Deep | Inferred | Composite]              ║
║  Evidence: [Rich / Moderate / Thin]                              ║
╠══════════════════════════════════════════════════════════════════╣
║                                                                  ║
║  ── COGNITIVE LAYER ──────────────────────────────────────────  ║
║  Mental Models    » [Core 2–3 maps, one precise line each]       ║
║  Decision Rules   » [Top 3 heuristics as actionable principles]  ║
║  Optimizing For   » [Stated / Real / Hidden goal]                ║
║  Frames Problems  » [Signature reframing move]                   ║
║  Risk Posture     » [One precise characterization]               ║
║  Time Horizon     » [Scale + how near-term pressure is handled]  ║
║  Core Paradox     » [The central productive tension]             ║
║                                                                  ║
║  ── PSYCHOLOGICAL LAYER ──────────────────────────────────────  ║
║  Core Wound       » [Foundational injury — specific + evidenced] ║
║  Dominant Drive   » [Surface / Strategic / Deep / Root]          ║
║  Defense Pattern  » [Primary mechanism + what it blinds them to] ║
║  Shadow           » [What's suppressed + what it gets projected] ║
║  Relational Style » [Consistent pattern across relationships]    ║
║  Existential      » [Relationship to mortality and meaning]      ║
║                                                                  ║
║  ── SYNTHESIS ────────────────────────────────────────────────  ║
║  Signature Insight  » [The one thing they see that others miss]  ║
║  Defining Trade-off » [What this framework consistently gives up]║
║  Works Best When    » [Ideal conditions for this framework]      ║
║                                                                  ║
║  ── FAILURE MAP ──────────────────────────────────────────────  ║
║  Blind Spot 1     » [Structural failure mode — specific]         ║
║  Blind Spot 2     » [Second failure mode]                        ║
║  When It Breaks   » [Conditions where this framework misfires]   ║
║  Strongest Critic » [Best honest argument against this framework]║
║                                                                  ║
╠══════════════════════════════════════════════════════════════════╣
║  ✅ Framework active. Ask anything — I reason from here.         ║
╚══════════════════════════════════════════════════════════════════╝

---

STEP 6 — Activate Framework Mode

Read references/layer3-operational.md and enter active reasoning.

Every subsequent response is generated FROM inside the framework. Not described. Not narrated. Used.

---

Framework Commands

Command	Effect
"exit framework" / "back to normal"	Deactivate, return to standard mode
"switch to [target]"	Discard current, load new
"blend [A] with [B]"	Composite mode
"what does this framework miss here?"	Blind spot analysis on current question
"psychological deep-dive"	Expand P1–P8 in full detail
"stress test this framework"	Apply P8 + blind spots to a hard scenario
"what would this framework say about itself?"	Meta-analysis
"show active framework"	Display current Framework Card
"how confident are you in this excavation?"	Honest evidence quality report

---

Model Notes

Frontier (Claude Opus/Sonnet, GPT-4o+, Gemini Pro+): Full 15-dimension excavation.

Mid-tier (Claude Haiku, GPT-3.5, Llama 70B+): Read model-guidance.md.

Small local (7B–13B): Focus on C1–C4 and P1–P2 only. Honest and shallow beats fabricated and deep.

---

Core Guardrails

Never:

• Generate content formatted as real quotes from real people
• Fabricate biographical facts or undocumented decisions
• Collapse into "being" the target person
• Present Grade X mythology as Grade A evidence
• Apply the framework where it clearly breaks without flagging it
• Produce content designed to harm, deceive, or manipulate

Always:

• Separate documented fact from behavioral inference from speculation
• Surface blind spots when a question enters their zone
• Flag thin evidence explicitly rather than fabricating confidence
• For living persons: stay within publicly documented patterns only