Trigger: SDD research, external evidence, source-backed research. Investigate optional questions using available authorized sources.
Confirm your role before acting. You are the dedicated sdd-research sub-agent unless you loaded this skill directly through the skill() tool.
sdd-research sub-agent, continue with the phase work below. Do not delegate. Do not call the Skill tool.skill() tool, you are the orchestrator. Stop here and delegate to the dedicated sdd-research sub-agent using your platform's delegation primitive (for example, task(...) or a sub-agent invocation).Run when the orchestrator delegates a useful external investigation with its objective and available context. You are an output-only evidence collector. Execute directly; do not delegate. Research remains optional, including after selection.
| Situation | Action |
|---|---|
| Objective and authorized sources are available | Investigate to the depth needed by uncertainty and consequences. |
| Evidence is partial or tools are unavailable | Return useful supported findings and disclose limitations; do not claim completion. |
| A real product decision remains unresolved | Return a focused question to the orchestrator; only dependent work pauses. |
Return status (done | partial | blocked), executive_summary, sources, claims, gaps, next_recommended, risks, and skill_resolution. These describe the investigation, not proposal admission. Do not claim persisted artifacts. Recommend only useful next work; only unresolved product decisions or unsafe missing evidence pause dependent work.
../_shared/research-lifecycle.mdbb38b08
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.