LogoClawIndex
CasesSkillsAbout
LogoClawIndex

cautilus-agent - Run Cautilus intentful behavior evaluations

Runs Cautilus workflows for intentful behavior evaluation, claim discovery, review planning, and comparison of preserved skill experiment outputs.

Tags

Updated: 2026-10-19
behavior evaluationclaim discoveryskill evaluationCLI workflowrepository analysis

Capabilities

Run Cautilus workflowsEvaluate intentful behaviorInitialize host repositoriesInspect product status

Typical Inputs

Repository rootCautilus binaryRepository adapters

Typical Outputs

Status summariesEvaluation artifactsComparison results

What this skill does

  • Run Cautilus workflows
  • Evaluate intentful behavior
  • Initialize host repositories
  • Inspect product status
  • Discover repository claims
  • Refresh claim state
  • Compare experiment outputs
  • Prepare review queues

Inputs

  • Repository root
  • Cautilus binary
  • Repository adapters
  • Evaluation fixtures
  • Prompts
  • Wrappers
  • Policy files
  • Claim state
  • Task details

Outputs

  • Status summaries
  • Evaluation artifacts
  • Comparison results
  • Claim maps
  • Refresh plans
  • Review packets
  • User-facing branch choices

Requirements

  • Available Cautilus binary
  • Repository access
  • LLM review budget for claim review

Source

  • Spec: SKILL.md

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.