OpenParable
Skip to content
← Back to skills

Researcher Rigor Gate

Productivity

Researcher Rigor Gate 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 before plan submission, major plan revision, and major stage transitions. Verify alignment, feasibility, rigor, completeness, and prevent unjustified regressions to earlier workflow phases.

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-rigor-gate/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/researcher-rigor-gate, 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 Rigor Gate

This skill is the main scientific quality gate for the automated research commander.

Four Required Checks

Alignment

  • Does the active plan actually match the user’s current confirmed goal?
  • Are outdated assumptions or rejected directions still leaking into the workflow?

Feasibility

  • Are assignments compatible with the responsible worker roles?
  • Are resources, compute, and time nodes realistic?
  • Are dependencies satisfiable in the current state?

Rigor

  • Are baselines, controls, metrics, and validation logic explicit enough to reproduce?
  • Are conclusions proportional to the available evidence?

Completeness

  • Are any mandatory stages or handoffs missing?
  • Are there unaddressed blockers, contradictions, or risk items?

Anti-Regression Rule

Do not recommend broad early-stage restarts once the workflow has reached a later phase such as experiment design, implementation, execution, synthesis, or final reporting, unless:

  • a specific blocking gap is identified;
  • a narrower correction is not sufficient; and
  • the change is surfaced to the user as a material workflow revision.

Prefer targeted supplementation over phrases like "go back to round 1 literature search."