Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

piensalo-build

Estrellas0

Forks0

Actualizado12 de julio de 2026 a las 23:11

Software build-and-debug workflow: symptom capture, minimal reproduction, ranked hypotheses, discriminating tests, minimal in-scope fix, regression proof with quoted output. Use when code is broken, failing, or behaving unexpectedly, or when implementing a change that must not regress anything. Trigger phrases: 'fix this bug', 'tests are failing', 'why is this crashing', 'implement X without breaking Y'.

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-build
description	Software build-and-debug workflow: symptom capture, minimal reproduction, ranked hypotheses, discriminating tests, minimal in-scope fix, regression proof with quoted output. Use when code is broken, failing, or behaving unexpectedly, or when implementing a change that must not regress anything. Trigger phrases: 'fix this bug', 'tests are failing', 'why is this crashing', 'implement X without breaking Y'.
license	MIT

piensalo-build

The build-and-debug workflow of Piénsalo (domain: software build & debugging). 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 - Per intent-clarity: decode what the requester actually needs before optimizing anything. Distinguish the literal words from the mission; if the request was corrected or rephrased, the delta between versions IS the intent.
Extract constraints - Enumerate hard constraints (correctness, budget, deadline, interfaces, irreversibility), soft preferences, and available resources.
Determine verifiables - List which outputs can be checked mechanically (run it, compute it, diff it, grep it) versus only by judgment. Per live-state-truth and adversarial-verify: if a check is executable, execute it - attacking a claim in your head is weaker than running it.
Capture symptom - Per debugging-playbook: capture the symptom verbatim - full error text, exact command, exact input, environment. 'Something about a timeout' is not a symptom.
Reproduce - Per debugging-playbook: find the smallest, fastest, most deterministic reproduction - every minute here is repaid at every hypothesis test.
Symptom vs cause - Separate the observed symptom from the causal layer beneath it. Per debugging-playbook and intent-clarity's symptom-fix rule: 'increase the timeout' treats the symptom; ask what produces the slowness.
Generate hypotheses - Per debugging-playbook: generate 2-4 ranked hypotheses, ranked by likelihood x cheapness-to-test. Sources: the error itself (read ALL of it), the diff since it last worked, known failure-mode catalogs, and where this class of bug usually lives.
Hypothesis discrimination - Per debugging-playbook: design a discriminating test per hypothesis - one with DIFFERENT predicted outcomes depending on truth; otherwise it is an activity, not a test. Write the prediction BEFORE running.
Minimal fix - Fix the confirmed cause with the smallest change that removes it. Per scope-fence: fix what was asked, flag what was found - the module's other bugs go to the flag list, not the diff.
Regression test - Per debugging-playbook: prove the fix by prediction - the reproduction that failed must now pass, and the previously-passing suite must still pass. Add a regression test that encodes the bug so it cannot silently return.
Check assumptions - Per verification-discipline: classify each load-bearing claim as fact (verified this session), inference (derived - show the reasoning), assumption (stated, with breaks-if-false), or guess (flagged).
Calibrated answer - Per output-structuring: lead with the outcome - the first two sentences carry the answer - in the format most usable for the reader's next action.

Conditional moves

When all hypotheses are eliminated: return to Generate hypotheses and rework from there.
When the fix did not remove the symptom or caused a regression: return to Hypothesis discrimination and rework from there.
When the reproduction contradicts the recorded symptom: return to Capture symptom and rework from there.

Output contract

A confirmed root cause with its evidence table (hypothesis | test | prediction | result | verdict), a minimal in-scope fix diff, quoted regression-test output proving repro-now-passes and suite-still-green, an out-of-scope flag list, and explicitly labeled residual assumptions.

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-build
description	Software build-and-debug workflow: symptom capture, minimal reproduction, ranked hypotheses, discriminating tests, minimal in-scope fix, regression proof with quoted output. Use when code is broken, failing, or behaving unexpectedly, or when implementing a change that must not regress anything. Trigger phrases: 'fix this bug', 'tests are failing', 'why is this crashing', 'implement X without breaking Y'.
license	MIT

piensalo-build

Primary workflow

Recover real objective - Per intent-clarity: decode what the requester actually needs before optimizing anything. Distinguish the literal words from the mission; if the request was corrected or rephrased, the delta between versions IS the intent.
Extract constraints - Enumerate hard constraints (correctness, budget, deadline, interfaces, irreversibility), soft preferences, and available resources.
Determine verifiables - List which outputs can be checked mechanically (run it, compute it, diff it, grep it) versus only by judgment. Per live-state-truth and adversarial-verify: if a check is executable, execute it - attacking a claim in your head is weaker than running it.
Capture symptom - Per debugging-playbook: capture the symptom verbatim - full error text, exact command, exact input, environment. 'Something about a timeout' is not a symptom.
Reproduce - Per debugging-playbook: find the smallest, fastest, most deterministic reproduction - every minute here is repaid at every hypothesis test.
Symptom vs cause - Separate the observed symptom from the causal layer beneath it. Per debugging-playbook and intent-clarity's symptom-fix rule: 'increase the timeout' treats the symptom; ask what produces the slowness.
Generate hypotheses - Per debugging-playbook: generate 2-4 ranked hypotheses, ranked by likelihood x cheapness-to-test. Sources: the error itself (read ALL of it), the diff since it last worked, known failure-mode catalogs, and where this class of bug usually lives.
Hypothesis discrimination - Per debugging-playbook: design a discriminating test per hypothesis - one with DIFFERENT predicted outcomes depending on truth; otherwise it is an activity, not a test. Write the prediction BEFORE running.
Minimal fix - Fix the confirmed cause with the smallest change that removes it. Per scope-fence: fix what was asked, flag what was found - the module's other bugs go to the flag list, not the diff.
Regression test - Per debugging-playbook: prove the fix by prediction - the reproduction that failed must now pass, and the previously-passing suite must still pass. Add a regression test that encodes the bug so it cannot silently return.
Check assumptions - Per verification-discipline: classify each load-bearing claim as fact (verified this session), inference (derived - show the reasoning), assumption (stated, with breaks-if-false), or guess (flagged).
Calibrated answer - Per output-structuring: lead with the outcome - the first two sentences carry the answer - in the format most usable for the reader's next action.

Conditional moves

When all hypotheses are eliminated: return to Generate hypotheses and rework from there.
When the fix did not remove the symptom or caused a regression: return to Hypothesis discrimination and rework from there.
When the reproduction contradicts the recorded symptom: return to Capture symptom and rework from there.

Output contract

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.