feature-decision

<!-- Generated from `.claude/skills/_available/product/feature-decision/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. --> ## Purpose Make and document feature prioritization decisions with a structured framework. Ensures key factors are considered, stakeholders are consulted, and rationale is preserved for future reference. ## Evidence, authority, and recovery Treat this skill as decision support: a recommendation is analysis, while the decision belongs to an identified human authority. - Attach a source ID or path, source date, and as-of date to every material claim, quote, estimate, stakeholder input, and roadmap fact. Keep the evidence date separate from the date the human confirms a decision. - Expose unknown effort and unknown evidence as first-class values. `Unknown` effort is not Small, and missing evidence is not evidence of no impact; name the missing input or assumption instead of choosing a convenient rating. Preserve contradictory evidence with both sources and dates rather than reconciling it silently. - Never invent absent customer names, user counts, revenue, effort estimates, dates, stakeholder alignment, owners, quotes, or dependencies. If a field is not supported, record `unknown` or `not provided` and explain what would resolve it. - Keep the recommendation separate from the decision authority: label the output `Recommendation` and `Human decision authority` separately. Recommendations are not human decisions; only the human authority ...