Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

piensalo

Estrellas0

Forks0

Actualizado12 de julio de 2026 a las 23:11

Domain-general deep problem-solving loop distilled from curated expert reasoning traces: objective recovery, constraint and contradiction extraction, distinct mechanisms, cheapest discriminating test, adversarial verification, calibrated synthesis. Use when a task is non-trivial and a shallow first answer is risky - hard analysis, debugging, design, or any question where being confidently wrong is expensive. Trigger phrases: 'think this through', 'get this right', 'hard problem', or any multi-constraint ask.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

ralfyishere

ralfyishere/piensalo

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

Explorador de archivos

10 archivos

SKILL.md

readonly

name	piensalo
description	Domain-general deep problem-solving loop distilled from curated expert reasoning traces: objective recovery, constraint and contradiction extraction, distinct mechanisms, cheapest discriminating test, adversarial verification, calibrated synthesis. Use when a task is non-trivial and a shallow first answer is risky - hard analysis, debugging, design, or any question where being confidently wrong is expensive. Trigger phrases: 'think this through', 'get this right', 'hard problem', or any multi-constraint ask.
license	MIT

piensalo

The core reasoning loop of Piénsalo (domain: any). Work the numbered steps in order; each step's output feeds the next. Do not skip steps silently - if one does not apply, say so in one line.

Primary workflow

Recover real objective - State what the requester actually needs (not the stated ask); one interpretation line.
Separate objective from proxy - Name the attractive proxy the stated ask suggests; show it differs from the real objective or confirm they match.
Extract constraints and contradictions - List explicit+implicit constraints AND any contradictions in the given evidence; a contradiction is load-bearing until resolved.
Load-bearing uncertainty - Identify the ONE uncertainty that most changes the answer if wrong; say how it could be reduced cheaply.
Representation and verification - Choose the working representation (table/causal model/formal statement) and what can be DETERMINISTICALLY verified vs judged.
Adversarial verify - Attack the winner: counterexamples, boundary cases, arithmetic re-check with tools where cheap; use the criteria in references/verification.md.
Calibrated answer - Deliver the final result with confidence per component and the uncertainty that remains; never invent certainty.

Conditional moves

When the solution space is non-trivial, also: Distinct mechanisms - Generate 2-4 GENUINELY different mechanisms/answers (different algorithms, not paraphrases).
When >1 candidate survives or a kill-gate is required, also: Cheapest discriminating test - Design the cheapest test whose outcomes DIFFER across surviving candidates; pre-register its threshold. OUTPUT KEYS VERBATIM: test, threshold, kills_which.
When >1 candidate survives, also: Compare and synthesize - Compare candidates on decomposed criteria incl. constraint fit; keep the winner; harvest unique discoveries from losers (distill, do not replay).
When falsifiable claims are present, also activate: counterexample search.
When (and only when) it changes the answer, also activate: tool use.
When the solution space is non-trivial, also activate: multi-candidate generation.
When >1 candidate survives, also activate: loser distillation.
When deciding under uncertainty, also activate: scenario analysis.
For invention/novelty tasks, also activate: prior-art search.
For math/quantitative tasks, also activate: independent derivation.

Output contract

Calibrated final answer + residual uncertainty.

Delivery notes (small-model packets)

If delegating steps to a smaller model: one bounded objective per packet, all inputs named explicitly, facts separated from instructions, uncertainty marked 'UNCERTAIN: ...' rather than invented away.

Before answering

Check the draft against references/failure-checks.md (the failure-mode catalog) and references/verification.md (domain verifier criteria). Repair procedures live in references/contracts.md.

Más de este repositorio

mismo repositorio

audience-constraint-check

ralfyishere/piensalo

Check a deliverable against its actual consumer: who reads it, what they do next, what format and register they need, and what they will assert downstream on its basis. Activate when the deliverable has a named audience beyond the requester, or its text will be forwarded, announced, or acted on by someone absent from the conversation.

2026-07-120

boundary-case-check

ralfyishere/piensalo

For any rule-like deliverable — code, regex, query, formula, validator, policy — enumerate the boundary inputs (empty, zero, one, max, duplicate, malformed, hostile) and actually exercise the most breakable three before shipping. Activate when the deliverable is executable or rule-like and will meet inputs the author didn't type.

2026-07-120

calibrated-uncertainty

ralfyishere/piensalo

State every claim at its actual evidence level — verified, inferred, assumed, guessed — and give credences only where an observable could score them; ban certainty language on unverified claims. Activate when a response makes claims about unobserved, future, or unverified state, or when the user asks how confident or likely something is.

2026-07-120

causal-model-construction

ralfyishere/piensalo

Before intervening in a system, write the explicit causal chain from the proposed action to the intended outcome — every arrow marked verified or assumed — and check the weakest assumed arrow first. Activate when an intervention (fix, optimization, policy change, growth action) is proposed on a system whose mechanism has not been written down.

2026-07-120

cheapest-discriminating-test

ralfyishere/piensalo

With multiple live hypotheses and a limited test budget, design the cheapest single test whose possible outcomes separate the hypotheses — with a results-to-verdict table committed before running anything. Activate when two or more competing hypotheses are on the table and the next step is choosing what test, experiment, or probe to run.

2026-07-120

complete-the-delivery

ralfyishere/piensalo

Enumerate every deliverable the request actually asked for and map each one to the work produced, so nothing asked-for is silently dropped, stubbed, or rounded up to done. Activate when a request contains multiple parts — an enumerated list, several 'and'/'also' clauses, or a spec with more than one required artifact — or before delivering a draft against such a request.

2026-07-120

name	piensalo
description	Domain-general deep problem-solving loop distilled from curated expert reasoning traces: objective recovery, constraint and contradiction extraction, distinct mechanisms, cheapest discriminating test, adversarial verification, calibrated synthesis. Use when a task is non-trivial and a shallow first answer is risky - hard analysis, debugging, design, or any question where being confidently wrong is expensive. Trigger phrases: 'think this through', 'get this right', 'hard problem', or any multi-constraint ask.
license	MIT

piensalo

The core reasoning loop of Piénsalo (domain: any). Work the numbered steps in order; each step's output feeds the next. Do not skip steps silently - if one does not apply, say so in one line.

Primary workflow

Recover real objective - State what the requester actually needs (not the stated ask); one interpretation line.
Separate objective from proxy - Name the attractive proxy the stated ask suggests; show it differs from the real objective or confirm they match.
Extract constraints and contradictions - List explicit+implicit constraints AND any contradictions in the given evidence; a contradiction is load-bearing until resolved.
Load-bearing uncertainty - Identify the ONE uncertainty that most changes the answer if wrong; say how it could be reduced cheaply.
Representation and verification - Choose the working representation (table/causal model/formal statement) and what can be DETERMINISTICALLY verified vs judged.
Adversarial verify - Attack the winner: counterexamples, boundary cases, arithmetic re-check with tools where cheap; use the criteria in references/verification.md.
Calibrated answer - Deliver the final result with confidence per component and the uncertainty that remains; never invent certainty.

Conditional moves

When the solution space is non-trivial, also: Distinct mechanisms - Generate 2-4 GENUINELY different mechanisms/answers (different algorithms, not paraphrases).
When >1 candidate survives or a kill-gate is required, also: Cheapest discriminating test - Design the cheapest test whose outcomes DIFFER across surviving candidates; pre-register its threshold. OUTPUT KEYS VERBATIM: test, threshold, kills_which.
When >1 candidate survives, also: Compare and synthesize - Compare candidates on decomposed criteria incl. constraint fit; keep the winner; harvest unique discoveries from losers (distill, do not replay).
When falsifiable claims are present, also activate: counterexample search.
When (and only when) it changes the answer, also activate: tool use.
When the solution space is non-trivial, also activate: multi-candidate generation.
When >1 candidate survives, also activate: loser distillation.
When deciding under uncertainty, also activate: scenario analysis.
For invention/novelty tasks, also activate: prior-art search.
For math/quantitative tasks, also activate: independent derivation.

Output contract

Calibrated final answer + residual uncertainty.

Delivery notes (small-model packets)

Before answering

Check the draft against references/failure-checks.md (the failure-mode catalog) and references/verification.md (domain verifier criteria). Repair procedures live in references/contracts.md.