opportunity-report-next-steps-one

name	opportunity-report-next-steps-one
description	Produces next-steps markdown for a single opportunity from opportunities.yaml using opportunity_report_next_steps_one template. Use when the user asks for one-opportunity next actions, 24–72h moves, or snapshot for a given id.

Report — next steps for one opportunity

Role: Assistant — career / opportunity tracking (see docs/AGENT_ROLES.md).

Context to load:

• data/opportunities.yaml
• Output skeleton: templates/opportunity_report_next_steps_one.md

Scope:

• Load only specific YAML record.
• Skip unrelated opportunity/role reports unless user asks.

Task:

1. Select record by id: <OPPORTUNITY_ID> (or company + role — resolve ambiguity).
2. Produce Snapshot + Next actions from next_action, next_action_date, notes, stage.
3. Populate Contacts table from contacts[]; if empty: "None recorded."
4. Populate Check here (manual) table from links; if empty: "None recorded."
5. Add Blockers / risks from notes and stage.
6. Add Suggested 24–72h moves aligned with docs/framework/workflows.md (Workflow 2).
7. Assumptions / Risk.

Output: Markdown for data/reports/pipeline/opportunity-next-steps-<id>-<YYYY-MM-DD>.md or paste-only.

Constraints:

• Full detail stays under data/ (gitignored — real names fine).
• No fabrication. Every sentence traceable to YAML field (stage, next_action, notes, history, contacts, links). No career advice, invented timelines, assumed details.
• Missing data → state explicitly. No supporting data → write "No data recorded." No gap-filling.
• Assumptions section mandatory. Any interpretation beyond direct field read must be listed, labeled as inference.

My inputs (collect, confirm, or ask):

• If opportunity id (or company + role) not in memory/chat/opportunities.yaml: ask before generating.
• If id inferred from company + role: state resolved id, ask user to confirm or correct before final output.
• Opportunity id (or company + role): <...>