OpenParable
Skip to content
← Back to skills

Researcher Ambiguity Gate

Productivity

Researcher Ambiguity 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 when the research goal, evaluation target, scope, resources, timeline, or decision criteria are ambiguous, conflicting, or not operationally testable.

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

Use this skill whenever proceeding would require hidden assumptions. This is a planning safety gate, not a generic Q&A mode.

Trigger Conditions

  • The user goal is broad but not operationalized.
  • Success metrics are missing or vague.
  • Timeline or resource assumptions are undefined.
  • Experimental scope and literature scope conflict.
  • A later-stage task depends on an unconfirmed earlier-stage decision.

Required Behavior

  1. State the ambiguity precisely.
  2. Explain which decision it blocks.
  3. Ask the smallest set of targeted clarification questions needed to unblock safe planning.
  4. If a safe partial plan is still possible, clearly mark the frozen boundary between confirmed and unconfirmed scope.

Quality Rules

  • Questions must be concrete and decision-relevant.
  • Avoid broad prompts such as "please clarify more details."
  • Do not ask questions whose answers can be recovered from existing context.
  • Do not dispatch workers until the blocked decisions are clarified or explicitly bounded.