slgoodrich/agents/team-deliverables

Team Deliverables

Templates and scoring rubrics for the final outputs of multi-agent team workflows.

When to Use This Skill

Auto-loaded by all six agents:

• idea-researcher, market-researcher, idea-skeptic - For validation verdict and competitive synthesis scoring rubrics
• market-fit-reviewer, feasibility-reviewer, scope-reviewer - For PRD review report scoring rubrics

Use when you need:

• Generating the final output of a team workflow
• Scoring ideas, PRDs, or competitive positions
• Structuring multi-perspective findings into a single deliverable
• Ensuring consistent output format across team workflows

Template Selection Guide

Scoring Rubrics

Validation Sprint Scores (1-10)

User Problem Score

Market Opportunity Score

Defensibility Score

PRD Review Scores (1-5)

Market Fit Score

Feasibility Score

Scope Score

Template Standards

Required Elements in Every Deliverable

1. Header: Command name, date, subject (idea/PRD/competitors)
2. Scores: Numerical scores with brief justification
3. Verdict: Clear recommendation (BUILD / DON'T BUILD / READY / NEEDS REVISION / etc.)
4. Evidence: Key findings from each agent's investigation
5. Conflicts: Where agents disagreed and why
6. Next Steps: Specific, actionable recommendations

Formatting Rules

• Use tables for scores (scannable)
• Use bullet points for findings (not paragraphs)
• Bold the verdict and any blocking issues
• Keep the executive summary under 5 lines
• Put detailed evidence in expandable sections when the report is long

Ready-to-Use Resources

In assets/:

• validation-verdict-template.md: Go/No-Go format with three perspectives for validation sprints
• prd-review-report-template.md: Multi-dimensional review with conflicts section for PRD stress tests
• competitive-synthesis-template.md: Positioning map and battle cards format for competitive war rooms

Troubleshooting

"The template doesn't fit our findings": Adapt it. Drop sections that add nothing, expand sections where you have depth. A template that forces empty placeholder text is worse than no template. The structure is a starting point, not a constraint.

"Scores across reviewers aren't comparable": Check that all reviewers used the same rubric anchors. A 4/5 from one reviewer should mean the same thing as a 4/5 from another. If they're using different mental scales, re-calibrate by sharing the rubric definitions before the next run.

"The verdict is ambiguous (BUILD IF with too many conditions)": That usually means the idea needs more validation, not a conditional pass. If there are more than 3 conditions, downgrade to NEEDS MORE EVIDENCE and list what to validate next.

Related

• /agent-teams:validation-sprint - Produces validation verdicts using these templates
• /agent-teams:prd-stress-test - Produces PRD review reports using these templates
• /agent-teams:competitive-war-room - Produces competitive syntheses using these templates
• team-coordination - Debate and synthesis protocols that feed into these deliverables

Remember: Templates create consistency, not rigidity. Adapt sections when the findings demand it. A template that forces you to fill in blanks with nothing useful is worse than no template.