Researcher Plan Architect
ProductivityResearcher 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.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
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:
- Core research objective and success criteria.
- Task division by worker role.
- Dependencies and milestone order.
- Resource assumptions, tooling, and compute needs.
- Evidence requirements and quality gates.
- Risk register with mitigation actions.
- 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.