OpenParable
Skip to content
← Back to skills

Researcher Dispatch Supervisor

Productivity

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.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/SpectrAI-Initiative/InnoClaw/blob/HEAD/.claude/skills/researcher-dispatch-supervisor/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/researcher-dispatch-supervisor, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

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.