Explore Prompts

Keep self-reflection productive by separating insight from rumination and forcing each loop toward evidence, a decision, or a stop condition.

Analyze an ethical dilemma through multiple moral frameworks without pretending one framework automatically resolves it.

Run a bounded self-study of which regulation strategies actually change recovery, behavior, or clarity under comparable conditions.

Study a corpus of your own reasoning to find recurring inference moves, shortcuts, blind spots, and strengths.

Test whether a suspected bias is actually present by comparing it against alternative explanations and counterexamples.

Compare multiple explanations for a recurring bodily signal and identify when medical evaluation is more appropriate than self-analysis.

Define observable trust and boundary signals, then track whether they predict reliability over time.

Design a prospective study of why goals survive, mutate, or disappear after initial enthusiasm.

Study what captures your attention, what you predict next, and how prediction error changes subsequent attention.

Design an ethical N-of-1 test to change one loop and measure whether the mechanism was actually affected.

Analyze a conversation with an AI as behavioral evidence: recurring asks, corrections, contradictions, preferences, and thinking patterns — with confidence labels.

Review a completed decision by separating process quality from outcome quality, tracing assumptions, signals, alternatives, and update rules.

Debug failures by comparing known-good state to current state and ranking concrete deltas before inventing new fixes.

Explore strange connections and speculative branches without losing the original question, evidence level, or path back.

Pressure-test an idea by searching for what would make it false, ordinary, redundant, fragile, or less valuable than it first appears.

Identify the gap between what a general AI can know and the local, temporal, organizational, or situational context required for a trustworthy answer.

Separate what is directly observed from interpretation, causal stories, predictions, and unknowns before you act on a narrative.

Trace a recurring thought, reaction, or conclusion back through triggers, assumptions, protective logic, and reinforcing loops without pretending certainty.

Compare fight, flight, freeze, appease, withdrawal, problem-solving, and other protective responses as context-sensitive strategies.

Compare perceived threat with later evidence to learn where vigilance is accurate, overgeneralized, or context-dependent.

Test specific hypotheses about creative blockage with small changes to constraints, inputs, environment, and evaluation pressure.

Compare the different roles you operate from and identify where their goals, rules, and incentives collide.

Research recurring emotional responses by separating trigger, interpretation, body state, action, and aftermath.

Map which task features, meanings, environments, and states reliably increase or decrease your willingness to act.

Track how your self-description and enacted identity change across time rather than treating the latest story as permanent truth.

Research the identities you claim versus the identities your repeated choices actually support.

Reconstruct a conflict from multiple plausible perspectives and test which interpretation best fits the evidence.

Design a conservative personal study of sleep/energy conditions and measurable performance while controlling obvious confounders.

Compare several models of how your best ideas form and test them against actual examples.

Study how your behavior changes across audiences, status relationships, familiarity, and group roles.

Research the gap between stated values and values revealed by repeated tradeoffs, costs, and choices.

Design a decision test that reveals which value actually dominates when two important principles compete.

Design low-risk observations that distinguish prudent safety behavior from avoidance that persists after risk has changed.

A foundational prompt for examining formative memories, repeated life themes, personal history, and origin stories.

A foundational prompt for examining assumptions, worldview, reality models, philosophical patterns, and future expectations.

A foundational prompt for identifying learning style, adaptation patterns, feedback response, and belief updating.

A foundational prompt for examining what an LLM can infer from a user's language, prompt style, edits, contradictions, and interaction patterns.

A foundational prompt for identifying values, personal codes, ethical tensions, loyalty, duty, and moral injury.

A foundational prompt for exploring work identity, competence, mastery, responsibility, leadership, and burnout risk.

A foundational prompt for analyzing word choice, repeated metaphors, narrative tone, hidden assumptions, and meaning-making patterns.

A foundational prompt for exploring autonomy, control, helplessness, resistance, authority, self-command, and power dynamics.

A foundational prompt for analyzing how someone behaves around people, handles trust, conflict, belonging, and social roles.

A foundational prompt for identifying what energizes, drains, pressures, rewards, or blocks a person.

A foundational prompt for identifying threat detection, hypervigilance, defense patterns, and crisis-mode behavior.

A foundational prompt for exploring imagination, symbolism, idea generation, creative blocks, and conceptual recombination.

A foundational prompt for identifying repeated behaviors, avoidance cycles, habits, and self-sabotage patterns.

A foundational prompt for mapping emotional states, regulation patterns, avoidance, and recurring affective themes.

A foundational prompt for identifying reasoning style, mental loops, interpretation habits, and cognitive biases.

A foundational prompt for exploring self-concept, internal roles, personal narrative, and identity structure.

This script is a structured self-modeling and reflection engine designed to help a person examine their cognition, emotions, behavior patterns, decision-making, and recurring internal “operating modes” in a disciplined way. Instead of treating self-reflection as loose journaling, it turns introspection into a versioned diagnostic system with commands, snapshots, revision tracking, drift detection, metacognition scoring, and JSON export. Its core purpose is to identify persistent inner patterns called Echo Forms, situational states called Agent Modes, and capacity metrics like intelligence, emotional regulation, adaptability, creativity, focus, leadership, and sensemaking. It also tries to separate useful insight from rumination by requiring evidence, disconfirming conditions, behavioral consequences, and concrete actions within 72 hours. In plain English, it is a personal operating-system mirror: part psychological dashboard, part prompt protocol, part behavioral audit trail, and part anti-bullshit filter designed to keep self-analysis from turning into a beautiful swamp with mood lighting.

Study how sleep, energy, discomfort, movement, hunger, and other bodily states correlate with cognition without assuming causation.

A foundational prompt for turning self-knowledge into integration, behavior change, repair, and practical action.

A foundational prompt for exploring disowned traits, avoided truths, resentment, envy, inner conflict, and forbidden needs.

A foundational prompt for examining how someone chooses, delays, weighs risk, handles uncertainty, and avoids regret.

A foundational prompt for connecting mental patterns to sleep, energy, food, movement, fatigue, stress, and bodily signals.

This prompt is designed to generate COUNTER.NEWS-style articles from pasted notes, source material, or a topic. It instructs the AI to write in a sharp, serious, independent editorial-news voice, focusing not just on what happened, but on why it matters, who benefits, who is affected, and what larger pattern the story reveals. It also tells the AI to: Preserve facts while adding stronger structure and analysis Avoid fake citations or unsupported claims Format the article in clean HTML for publishing Insert a small COUNTER.NEWS advertisement in the middle of the article Add another promotional advertisement at the end Include an SEO title, meta description, excerpt, and 12 SEO tags In short: it turns raw news notes into a polished COUNTER.NEWS editorial article package with built-in site promotion and SEO support.

Drill into root causes of any problem with guided Socratic questioning using the 5 Whys technique.

Map a situation to 3 different mental models and compare what each one reveals.

Build the strongest possible version of an argument you disagree with to practice intellectual empathy.

Force the AI to argue against your position to surface hidden assumptions and blind spots.

Explain your problem out loud — the AI asks clarifying questions until you find the answer yourself.

Decompose any concept into its most fundamental, irreducible components using first principles thinking.

Build and challenge a time-ordered causal hypothesis from events, lags, propagation, confounders, and interventions.

Trace an assumption backward to its evidence, source, dependencies, inherited conventions, and the conditions that should cause it to change.

Turn an exploratory conversation into a bounded build task with known-good anchors, acceptance criteria, authority limits, verification, and completion evidence.

Debrief how you thought through a problem: strategy, attention, confidence, blind spots, corrections, and what to change next time.

Research established architectures, reference implementations, failure modes, and operational tradeoffs before designing a new system.

Compare cinematographic approaches for the same narrative goal and convert findings into promptable shot language.

Identify the assumptions that must be true for a strategy to work and design the cheapest tests that could kill the plan early.

Research the misconceptions learners actually hold from errors, explanations, questions, and assessments before designing instruction.

Test a productivity system with baseline metrics, a single intervention, and stop rules instead of adopting an entire methodology by faith.

Research the visual language of a topic before writing scenes: references, era, materials, composition, motion, lighting, and factual constraints.

Compare how competing brands frame the same problem, proof, objection, and call to action without simply imitating their language.

Compare competitors on customer, problem, promise, proof, mechanism, pricing, delivery model, and tradeoffs using current primary evidence.

Research a workflow as a system of handoffs, waits, decisions, rework, context switching, and hidden queues before adding another tool.

Compare narrative structures, hooks, pacing, and visual change patterns using real retention or performance evidence instead of folklore.

Build a compact market dossier from customers, competitors, substitutes, economics, adoption signals, and primary evidence before making strategic claims.

Derive a writing voice from an actual corpus by measuring lexical, syntactic, rhetorical, structural, and tonal patterns instead of vague adjectives.

Research the factual backbone of an article or argument before drafting so every consequential claim has provenance and uncertainty.

Find under-served content opportunities by verifying trends, competitor coverage, audience questions, and evidence gaps before chasing novelty.

Compare how a decision changes when costs, benefits, uncertainty, reversibility, and time horizon are varied.

Separate what you can control, influence, negotiate, predict, or only observe, then compare that map with where effort is actually spent.

Research which insights actually produce changed behavior and which remain compelling explanations with no operational effect.

Compare why some changes persist while others decay by examining environment, identity, incentives, friction, feedback, and support.

Design a curriculum from prerequisite relationships, learning objectives, assessments, transfer tests, and revision evidence.

Research a software failure by preserving known-good state, timeline, deltas, logs, reproduction, and discriminating tests before editing code.

Research what is currently working on a platform using dated examples, platform guidance, audience fit, and format mechanics rather than generic viral advice.

Research dependencies, ownership, update risk, security/support status, coupling, and replacement cost before a migration or cleanup.

Compare high- and low-performing content to identify which themes and structures correlate with useful audience response, not just impressions.

Compare instructional approaches for a specific learner, topic, and outcome using evidence rather than generic teaching fashions.

Design a growth experiment that can distinguish channel quality from creative quality, audience mismatch, tracking errors, and random variance.

Research how a prompt can fail under ambiguity, conflicting context, bad data, injection, model drift, and edge cases before deployment.

Research how a prompting problem has already been solved across papers, vendor guidance, open-source systems, and practitioner evidence before inventing another pattern.

Research what an audience is actually trying to accomplish, what blocks them, what language they use, and what evidence shows urgency.

Turn a prompt into a reproducible evaluation suite with cases, rubrics, failure taxonomy, baselines, and regression tests.

Research a disputed question by treating disagreement as data: compare methods, samples, definitions, incentives, and boundary conditions.

Compare intended priorities with observed time allocation while accounting for obligations, recovery, interruptions, and task switching.

Run a transparent literature review with query design, inclusion/exclusion rules, evidence grading, contradiction tracking, and source provenance.

Compare competing value propositions using audience evidence, objections, behavior, and controlled messaging tests.

Compare how different learning methods affect recall, transfer, speed, error correction, and long-term retention for you.

Research a repeated behavior as a trigger-action-consequence system using real episodes instead of generic habit theory.

Trace ideas back to source influences, recombinations, constraints, accidents, and transformations without pretending originality appears from nowhere.

Compare intrinsic interest, external reward, deadline pressure, social accountability, fear, and meaning as competing drivers.

Compare what an avoidance behavior may be accomplishing before deciding why it exists.

Test multiple explanations for the same emotional reaction instead of locking onto the first plausible story.

Test how much your current self-explanation depends on one origin story by constructing evidence-bounded alternatives.

Compare several candidate themes across your history and test whether they genuinely recur or are products of selective memory.

Research a remembered event by separating recollection, contemporaneous records, later retellings, and current interpretation.

Analyze repeated words, qualifiers, metaphors, absolutes, uncertainty markers, and framing choices across your own writing or conversations.

Decompose a worldview claim into its supporting assumptions, provenance, evidence strength, and failure conditions.

Design a conservative study of workload, error rate, focus, recovery, and output quality without turning ordinary fatigue into a diagnosis.

Track how your use of important words changes over time and whether changing definitions are silently moving the argument.

Trace recurring metaphors and compare the different conceptual models they impose on the same problem.

Test whether a strong reaction to another person is better explained by projection, direct evidence, value conflict, prior experience, or current incentives.

Study which topics, needs, traits, or conflicts repeatedly disappear from your own narratives without assuming the absence has one hidden cause.

Turn a vague curiosity into a tractable research program with variables, evidence requirements, falsifiers, and staged questions.

Compare your belief network against the strongest alternative models and map which beliefs would need to update together.

Research what kinds of feedback you accept, resist, misunderstand, or successfully convert into changed behavior.

Research why you correct an AI by comparing model error, missing context, preference mismatch, ambiguity, and changing intent.

Compare which forms of practice actually transfer to real performance and which mainly create a feeling of preparation.

Design low-risk observations to test whether a trait you reject in yourself also has adaptive forms worth integrating.

Map demonstrated competence from artifacts, outcomes, repeated tasks, failure recovery, and external evidence instead of self-esteem alone.

Design a bounded test for two apparently conflicting needs or values instead of forcing one side to disappear.

Track belief changes prospectively so genuine updating can be separated from forgetting prior confidence or rewriting history.

Turn predictions into a scored dataset so confidence can be compared with actual outcomes over time.

Design small tests that distinguish actual helplessness from uncertain, unused, or poorly specified options.

Compare how you respond to authority, autonomy, constraint, and dependency across contexts without turning it into a fixed personality label.

Track whether repeated AI suggestions are changing your vocabulary, priorities, assumptions, or decisions beyond the evidence you intended to adopt.

Research a set of past decisions using the information available at the time, not hindsight, and compare process quality with outcome quality.

Analyze a corpus of your own AI prompts to research recurring goals, framing habits, corrections, blind spots, and collaboration patterns.

Use future predictions generated by a world model to test whether it explains reality better than competing models.