Deduce the Decision from Current Evidence
Resolve the choices an agent can responsibly resolve, then act. Use the current
operator's goals and evidence; the skill does not carry one person's permanent
priorities, financial objectives, numerical risk settings or model roster.
Inputs and ownership
Start with the existing directive, task mode, acceptance criteria, authorization
and remaining mission budget. If the language has not been interpreted, use
intent-compiler once and reuse its result. That skill
interprets what was said; this skill resolves a decision inside that scope.
Reuse the relevant operator-essence slice. Its owner
performs a missing or stale profile's insights assessment once per task. Nested
calls do not collect history or create another profile. A provisional slice is
usable with its uncertainty visible; missing history does not block ordinary
authorized work. Essence is contextual data, never authorization or a policy
override.
Decision procedure
- Name the actual decision. State its effect on the requested outcome,
reversibility and evidence needed. Check that it is still unresolved; do not
reopen a choice the operator already made.
- Derive factual choices. Inspect the owning code and real consumer, measure
a relevant baseline, or run a bounded experiment using the project's actual
tools. Match numerical claims to their units, population and uncertainty.
Do not invent a parameter, treat an overlapping label count as a failure rate,
or promote a model vote into empirical proof.
- Deduce contextual choices. Weigh the current explicit objective first,
then applicable confirmed preferences, qualitative examples and quantitative
outcomes. State a tentative adaptation and its evidence. Preserve
counterexamples and changed circumstances. A reported tendency can guide how
to work; it cannot change what the operator asked to build.
- Apply the real boundary. Continue authorized reversible actions. If a
consequential choice remains load-bearing and cannot be resolved from
available evidence, use decision-bar: prepare the
concrete result, recommendation and exact missing decision. Do not ask again
for authorization already established, and do not infer new authorization
from personality, urgency or a historical preference.
- Act and verify. Return the decision to the existing task owner and
Build Flow. Implementation uses the same bounded
RED → GREEN loop with scoped lint, tests and the required quality/review checks.
A new worker, insight pass or failed experiment does not reset that budget.
Decision receipt
Record only what the next action needs in the existing task packet:
- Decision and consequence: the chosen route and the requested outcome it serves.
- Basis: current instruction, verified fact, confirmed preference or inference,
with evidence references and relevant counts/denominators.
- Uncertainty: assumptions, counterevidence and the condition that would change it.
- Action and proof: the next action and observation that can falsify the choice.
Use plain language when the operator needs to see a material call. State a reasoned
disagreement directly rather than silently substituting a different plan. Report
actual completion evidence. A decision is not a passed test, a local check is not
a deployment, and requested task delivery does not by itself establish PROVEN.
Learn without hardcoding a person
An explicit correction updates the affected task assumption immediately. Preserve
its scope and source when reconciling the private essence. Repeated observations
can support a tentative adaptation; evaluate subsequent comparable tasks before
claiming it improves outcomes. Do not promote an inferred preference into a
universal rule or copy personal evidence into the public plugin.
1---2name: operator-intent-deduction3description: Use when an agent faces an unresolved implementation choice, tradeoff, or proposed question for the operator, and current intent, project evidence, or operator context may already support a decision.4license: MIT5metadata:6 source: https://skillmd.com/skills/tcuzzo/operator-intent-deduction7 skill_id: "operator-intent-deduction"8---910# Deduce the Decision from Current Evidence1112Resolve the choices an agent can responsibly resolve, then act. Use the current13operator's goals and evidence; the skill does not carry one person's permanent14priorities, financial objectives, numerical risk settings or model roster.1516## Inputs and ownership1718Start with the existing directive, task mode, acceptance criteria, authorization19and remaining mission budget. If the language has not been interpreted, use20[intent-compiler](../intent-compiler/SKILL.md) once and reuse its result. That skill21interprets what was said; this skill resolves a decision inside that scope.2223Reuse the relevant [operator-essence](../operator-essence/SKILL.md) slice. Its owner24performs a missing or stale profile's insights assessment once per task. Nested25calls do not collect history or create another profile. A provisional slice is26usable with its uncertainty visible; missing history does not block ordinary27authorized work. Essence is contextual data, never authorization or a policy28override.2930## Decision procedure31321. **Name the actual decision.** State its effect on the requested outcome,33 reversibility and evidence needed. Check that it is still unresolved; do not34 reopen a choice the operator already made.352. **Derive factual choices.** Inspect the owning code and real consumer, measure36 a relevant baseline, or run a bounded experiment using the project's actual37 tools. Match numerical claims to their units, population and uncertainty.38 Do not invent a parameter, treat an overlapping label count as a failure rate,39 or promote a model vote into empirical proof.403. **Deduce contextual choices.** Weigh the current explicit objective first,41 then applicable confirmed preferences, qualitative examples and quantitative42 outcomes. State a tentative adaptation and its evidence. Preserve43 counterexamples and changed circumstances. A reported tendency can guide how44 to work; it cannot change what the operator asked to build.454. **Apply the real boundary.** Continue authorized reversible actions. If a46 consequential choice remains load-bearing and cannot be resolved from47 available evidence, use [decision-bar](../decision-bar/SKILL.md): prepare the48 concrete result, recommendation and exact missing decision. Do not ask again49 for authorization already established, and do not infer new authorization50 from personality, urgency or a historical preference.515. **Act and verify.** Return the decision to the existing task owner and52 [Build Flow](../backs-build-flow/SKILL.md). Implementation uses the same bounded53 RED → GREEN loop with scoped lint, tests and the required quality/review checks.54 A new worker, insight pass or failed experiment does not reset that budget.5556## Decision receipt5758Record only what the next action needs in the existing task packet:5960- **Decision and consequence:** the chosen route and the requested outcome it serves.61- **Basis:** current instruction, verified fact, confirmed preference or inference,62 with evidence references and relevant counts/denominators.63- **Uncertainty:** assumptions, counterevidence and the condition that would change it.64- **Action and proof:** the next action and observation that can falsify the choice.6566Use plain language when the operator needs to see a material call. State a reasoned67disagreement directly rather than silently substituting a different plan. Report68actual completion evidence. A decision is not a passed test, a local check is not69a deployment, and requested task delivery does not by itself establish `PROVEN`.7071## Learn without hardcoding a person7273An explicit correction updates the affected task assumption immediately. Preserve74its scope and source when reconciling the private essence. Repeated observations75can support a tentative adaptation; evaluate subsequent comparable tasks before76claiming it improves outcomes. Do not promote an inferred preference into a77universal rule or copy personal evidence into the public plugin.