LogoClawIndex
CasesSkillsAbout
LogoClawIndex

validate-run - Validate agent run checkpoints in parallel.

Validates all checkpoints from an agent run directory in parallel by spawning test-validator agents and summarizing verified results.

Tags

Updated: 2026-09-19

Capabilities

Typical Inputs

Typical Outputs

What this skill does

  • Discover checkpoints in run directory
  • Launch test-validator agents in parallel
  • Collect reports from test validators
  • Verify sub-agent results and findings
  • Generate consolidated run summary report

Inputs

  • Agent run directory path
  • Optional problem name
  • Problem specifications and test files

Outputs

  • Checkpoint validation Markdown reports
  • Consolidated run validation summary

Requirements

  • Bash environment with find utility
  • Task tool for sub-agent spawning

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.
testing
validation
checkpoint
sub-agent
evaluation
Discover checkpoints in run directory
Launch test-validator agents in parallel
Collect reports from test validators
Verify sub-agent results and findings
Agent run directory path
Optional problem name
Problem specifications and test files
Checkpoint validation Markdown reports
Consolidated run validation summary