thinking-framework

by alradyin

>

View Chinese version with editor review

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/alradyin/thinking-framework

文档

Thinking Framework

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

FileWhat it containsWhen to read
references/layer1-cognitive.md7-dimension conscious cognitive architectureEvery load
references/layer2-psychological.md8-dimension deep psychological excavationEvery load
references/layer3-operational.mdActive framework mode behavioral protocolAfter excavation
references/layer4-synthesis.mdCross-layer synthesis + integration methodDeep/composite loads
references/model-guidance.mdCompensation for weaker/local modelsIf 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

code
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:

ClassExamplesApproach
Individual thinker / leaderPhilosophers, founders, generalsFull 15-dimension excavation
Organization / institutionCompanies, military units, movementsOrg-adapted protocol
Philosophical schoolStoicism, Zen, ExistentialismDoctrine + practice extraction
Canonical text / systemNamed books, methodologiesThesis + decision algorithm
Discipline / fieldPhysics, law, game theoryReasoning moves + evidence standards
Fictional archetypeLiterary characters, mythic figuresNarrative + symbolic layer
Composite / inventedUser-defined blendsLayer 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:

code
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.

code
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

code
╔══════════════════════════════════════════════════════════════════╗
║  🧠  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

CommandEffect
"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