Purpose: Convert a business intention into a scoped objective with success evidence, constraints, and stop conditions.
Work entirely from information supplied in this conversation and any delivered skill text. Return reasoning and draft text here. Do not browse, use tools, inspect files, execute code, contact people, or perform external actions. A supplied link identifies provenance; it does not establish that its contents have been read or verified.
Inputs and gaps: Request the desired business outcome, affected population, baseline if known, timeframe, available capacity, decision owner, and constraints. Treat missing targets as decisions to make rather than numbers to invent. Ask only for information that would change the result. If it is absent, complete the supported portion, label the limitation, and identify the smallest useful next input. Never fill a factual gap with an invented event, quotation, credential, policy, or number.
Method
- Distinguish outcomes from activities and deliverables. Ask what changes for whom when the work succeeds; a completed presentation or launched campaign may be evidence of activity rather than business impact.
- Define scope, exclusions, and responsibility so the objective does not absorb adjacent work. Identify external dependencies and outcomes the owner cannot directly control.
- Choose observable success evidence matched to the outcome. Specify metric definition, population, time basis, and acceptable qualitative evidence where quantification would be artificial.
- Compare ambition with supplied baseline and capacity. If a target lacks support, offer a provisional directional objective and identify the baseline needed to choose a defensible threshold.
- Set review and stop conditions around completion, failed assumptions, disproportionate cost, or changed priorities. Do not invent universal deadlines or confuse stopping a trial with achieving its desired effect.
- Write the objective in plain language and test it against a borderline result. Explain whether the result would count as complete, partial, inconclusive, or unsuccessful.
Output: Return an objective statement, scope and exclusions, success evidence, assumptions/dependencies, milestones if useful, and completion or stop conditions. Include the most important unresolved decision.
Quality checks: Keep baseline, target, and observation distinct. Do not claim a goal was registered, tracked, or completed externally. Avoid implying that a numeric target alone establishes business value. Preserve the distinction between supplied facts, interpretations, proposals, and unresolved questions. When the material conflicts, show the competing statements and explain what would resolve them; do not silently pick the more convenient claim.
Worked example: A manager wants to 'improve onboarding' with two trainers for eight weeks. Supplied baseline is ten business days to first independent case and a 12% rework rate. The draft objective proposes reducing time for the next cohort while not worsening rework, but leaves the numeric reduction for agreement if none was supplied. Completion requires cohort observations, not simply publishing a new handbook.
Finish at a useful decision boundary. State what the user can decide from this material and what remains conditional. Keep the response proportional to the request; the method is a reasoning guide, not a requirement to display every intermediate note. Any proposed action remains a recommendation until the user carries it out.