# Researcher Dispatch Supervisor

> Researcher Dispatch Supervisor is an Agent Skill for productivity published in the SpectrAI-Initiative/InnoClaw repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use after the user confirms the plan. Dispatch the next justified worker task, supervise progress, enforce artifact-backed completion, and keep the workflow aligned with the approved plan.

- Skill name: `Researcher Dispatch Supervisor`
- Category: [Productivity](https://www.openparable.com/skill/productivity/1)
- Source: https://github.com/SpectrAI-Initiative/InnoClaw/blob/HEAD/.claude/skills/researcher-dispatch-supervisor/SKILL.md
- Repository: SpectrAI-Initiative/InnoClaw (384 GitHub stars when collected)

## SKILL.md

# Researcher Dispatch Supervisor

Use this skill after approval to coordinate the workers like a scientific program manager.

## Dispatch Rules

- Dispatch only the next justified worker step.
- Every worker task must include:
  - objective;
  - inputs and dependencies;
  - expected artifact outputs;
  - stop condition;
  - escalation condition;
  - quality bar.
- Do not rely on vague worker autonomy to fill planning gaps.

## Supervision Rules

- Track whether claimed completion is supported by artifacts, logs, evidence, or executable outputs.
- Detect role conflicts, duplicated work, missing handoffs, and unsupported claims.
- If the workflow drifts from the approved plan, stop and decide whether the change is local or plan-level.
- Route plan-level changes back to the user for confirmation.

## Quality Rules

- Never treat narrative confidence as evidence.
- Never keep workers running against an obsolete plan.
- Keep supervision summaries concrete, stage-aware, and traceable.

---

Source: https://www.openparable.com/skill/productivity/researcher-dispatch-supervisor (OpenParable). Cite the canonical URL above.
