Skip to content
Back to skills

Researcher Plan Architect

ASecurity

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.

  • 390 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added June 6, 2026
ai-agentsgo

Security analysis

A100/100

Scanned June 6, 2026

npx -y skills add SpectrAI-Initiative/InnoClaw --skill researcher-plan-architect --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Researcher Plan Architect?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Researcher Plan Architect
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/spectrai-initiative-researcher-plan-architect/badge)](https://www.skillsdirectory.com/skills/spectrai-initiative-researcher-plan-architect)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "Researcher Plan Architect"
slug: "researcher-plan-architect"
description: "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."
allowed-tools:
  - listDirectory
  - readFile
  - grep
  - searchArticles
  - readPaper
---

# 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.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…