OpenParable
Skip to content
← Back to skills

Researcher Plan Architect

Productivity

Researcher Plan Architect 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 when the Researcher must convert a confirmed scientific goal into a staged, executable research plan with role assignments, milestones, resources, checkpoints, and risk controls.

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-plan-architect/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/researcher-plan-architect, 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 Plan Architect

Use this skill to design the authoritative plan that the user will confirm. Think like a research lead building a closed-loop execution program rather than a one-shot answer.

Plan Requirements

The plan must explicitly specify:

  1. Core research objective and success criteria.
  2. Task division by worker role.
  3. Dependencies and milestone order.
  4. Resource assumptions, tooling, and compute needs.
  5. Evidence requirements and quality gates.
  6. Risk register with mitigation actions.
  7. User confirmation gate before worker dispatch.

Planning Principles

  • Each worker assignment should have one owner and one clear deliverable.
  • Plans should minimize hidden dependencies and overlapping ownership.
  • Prefer targeted and testable sub-goals to vague exploration.
  • Keep the plan scientifically coherent from literature to design to code to execution to analysis to reuse.

Output Style

When presenting to the user, use a structured format that makes it easy to approve or revise:

  • context review summary;
  • detailed plan sections;
  • explicit verification statement;
  • confirmation request.