Menu
O SkillsMP coletou 655 skills de benjam3n/reasoningtool. Abra uma skill para revisar a origem e os detalhes.
Mostrando 40 de 655 skills coletadas.
Route any input through a branching question tree to narrow down the optimal response strategy before writing. Two stages — PERCEIVE (classify input) then ACT (select response). Covers all prompt types.
Idioma do texto original: inglês
Generate exhaustive guesses about user input using ALL search methods with coverage tracking. Guessing is SEARCH through possibility space. Tracks space created vs space covered to ensure comprehensive exploration.
Idioma do texto original: inglês
Systematically evaluate and select from a set of guesses, options, or possibilities. Combines ARAW analysis with prioritization to determine which guesses are strong, weak, actionable, or eliminable.
Idioma do texto original: inglês
Extract hidden assumptions from any content. Surfaces what must be true for claims to hold, enabling deeper analysis.
Idioma do texto original: inglês
Sub-orchestrator for analytical requests. Routes to decomposition, systems analysis, comparison, risk assessment, or synthesis based on what kind of analysis is needed.
Idioma do texto original: inglês
Assume Right - Deep recursive rightness search. For every claim, assume it's right — find what must follow, then assume THOSE implications are right too. Recurse until bedrock. Track every claim found.
Idioma do texto original: inglês
Sub-orchestrator for claims and assertions. Routes to ARAW-based testing with appropriate depth, balance, and supplementary analysis skills.
Idioma do texto original: inglês
Sub-orchestrator for decisions. Routes to comparison, ARAW testing, dominance analysis, or goal clarification based on what the user knows and the stakes involved.
Idioma do texto original: inglês
Sub-orchestrator for diagnostic questions. Routes to UAUA exploration, causal tracing, safety analysis, or direct debugging based on how much is known and the nature of the problem.
Idioma do texto original: inglês
Apply universal design principles to create or improve designs. Domain-adaptive, generative, grounded in exemplars. Embeds generate → critique → iterate.
Idioma do texto original: inglês
Determine how much thinking to invest in a decision. Maps stakes, reversibility, and diminishing returns to effort levels (minimum, standard, maximum).
Idioma do texto original: inglês
Sub-orchestrator for emotional inputs. Acknowledges the emotion, identifies the implicit request, and routes to the appropriate analytical skill — with expanded routing for reframing, scope control, and self-check skills.
Idioma do texto original: inglês
Sub-orchestrator for evaluation. Routes to ARAW, MECE validation, procedure validation, assumption extraction, risk analysis, or quality checks based on what's being assessed and what kind of evaluation is needed.
Idioma do texto original: inglês
Given any prompt, decompose it into implicit sub-tasks and extract every potentially useful skill, grouped by role and prioritized with invocation-ready suggestions.
Idioma do texto original: inglês
Systematic procedure for formulating testable hypotheses, designing tests, and updating beliefs based on evidence. Supports context-adaptive variants.
Idioma do texto original: inglês
Take something that works but could be better. Find the highest-leverage improvements and apply them. Not for broken things (/fix) — for things that work but underperform their potential.
Idioma do texto original: inglês
Meta-iteration skill. Identifies what needs iteration, at what level, in what dimension, at what scale, and what should be deleted — then executes the highest-value iteration.
Idioma do texto original: inglês
The deep analysis engine. Routes input by type, applies appropriate analysis depth, produces structured understanding and action.
Idioma do texto original: inglês
Systematically reframe a problem by changing the level of abstraction, stakeholder perspective, time horizon, success criteria, or constraint set. Generate genuinely different framings, not word substitutions.
Idioma do texto original: inglês
Analyze and improve relationships by identifying parties, assessing state, surfacing unmet needs, and finding actionable patterns.
Idioma do texto original: inglês
Generate comprehensive lists by systematically covering all dimensions. Ensures nothing is missed through structured enumeration.
Idioma do texto original: inglês
Identify what situation you are actually in before attempting to solve it. Prevents the most dangerous failure: solving the wrong problem perfectly.
Idioma do texto original: inglês
Construct the strongest possible version of an opposing argument before critiquing it. Ensures you're fighting the real argument, not a straw man. Includes finding the kernel of truth in positions you disagree with.
Idioma do texto original: inglês
Sub-orchestrator for goals and wants. Routes to WantTo analysis to trace what the want commits you to and find the actual want.
Idioma do texto original: inglês
Assume Wrong - Deep recursive wrongness search. For every claim, assume it's wrong — find why, then assume THOSE reasons are wrong too. Recurse until bedrock. Track every claim found.
Idioma do texto original: inglês
Systematic procedure for searching external sources to find evidence, data, and information relevant to a question.
Idioma do texto original: inglês
Goal-Oriented State Machine. Context-adaptive dispatcher that routes to the right analysis depth based on urgency, stakes, and expertise.
Idioma do texto original: inglês
Detect when reasoning is actually rationalization. Mechanical checks for motivated reasoning, emotional override, and evidence asymmetry.
Idioma do texto original: inglês
Systematically evaluate alternatives against weighted criteria using a structured decision matrix. Includes pairwise comparison for weighting, multi-criteria scoring, sensitivity analysis, and documented decision rationale.
Idioma do texto original: inglês
Grade any LLM output as an external grader who knows nothing about the project. Identifies systematic failures in reasoning, voice, and honesty that the LLM cannot see from inside its own generation.
Idioma do texto original: inglês
Detect when reasoning is working backwards from a predetermined conclusion. Surfaces the signs that the 'analysis' is actually a case built to support a thesis that was chosen before the evidence was examined.
Idioma do texto original: inglês
Force a full stop and honestly answer what is actually happening right now. Catches drift, confusion, lost purpose, cargo-culting, and the moment when activity replaced thinking.
Idioma do texto original: inglês
Assume Right / Assume Wrong search - For every claim, explore what follows if true (AR) and what breaks if false (AW). Number every finding. Recurse until bedrock. Compile a complete registry. Derive synthesis only from the registry.
Idioma do texto original: inglês
Construct a rigorous argumentative document with thesis, evidence, counterarguments, and structured reasoning.
Idioma do texto original: inglês
Break through creative or productive blocks when nothing comes to mind
Idioma do texto original: inglês
Orderings for presentations, writing, and communication where sequence affects audience engagement and comprehension.
Idioma do texto original: inglês
Designs a communication for any context. Identifies audience, determines goal, chooses medium, structures the message, and anticipates objections.
Idioma do texto original: inglês
Sub-orchestrator for creative and content production requests. Routes to appropriate writing skills based on content type and quality needs.
Idioma do texto original: inglês
Systematic procedure for generating novel ideas. Moves through divergent generation, combinatorial play, and convergent evaluation against the original need.
Idioma do texto original: inglês
Develop and execute content strategy that attracts, engages, and converts
Idioma do texto original: inglês