skills.rest
pshirshov
pshirshovCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

bench-validate

Execute automated checklists, review code, and report benchmark run results.

Updated Jun 10, 2026
Search Tags:#automation#developer tools#quality assurance#code review#benchmark validation
One-click install
npx skills add https://github.com/pshirshov/llm-bench-pi-oneshot --skill bench-validate
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bench-validate
Source: https://github.com/pshirshov/llm-bench-pi-oneshot/tree/main/.claude/skills/bench-validate
Command: npx skills add https://github.com/pshirshov/llm-bench-pi-oneshot --skill bench-validate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the validation of finished coding benchmark runs, reducing the need for manual checks and speeding up the review process.

Core Features & Use Cases

  • Automated Checklist Execution: Execute the automated checklist from a prompt's checklist file within each workspace.
  • Code Review: Perform a code review on the source code, scoring each item with a one-line justification.
  • Results Reporting: Generate a comparison table and summary of the run status and findings.

Quick Start

Run the bench-validate skill with the latest run ID by saying: /bench-validate or specify a run ID: /bench-validate [run-id]

Frequently Asked Questions about bench-validate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate benchmark validation for coding tasks?▼

Automated benchmark validation executes predefined checklists and performs code reviews on workspace source code to report quality findings. It operates by checking out workspaces and reading source code directly, requiring no installation or modification.

What is automated checklist execution for code review?▼

Automated checklist execution reads a prompt's checklist file within each workspace and scores each code review item with a one-line justification. This mechanism ensures quality standards are systematically verified across development workflows.

Does benchmark validation require installing dependencies to read source code?▼

Benchmark validation requires no installation or modification, functioning by simply checking out workspaces and reading source code. It operates purely as an automated review layer analyzing existing code artifacts.

How do I generate a comparison table from a benchmark run status?▼

Generating a comparison table and summary of run status findings is the final reporting stage of benchmark validation. It aggregates the scored checklist items and code review justifications into a unified results view.

Can I validate a specific coding benchmark run ID instead of the latest one?▼

Validating a specific coding benchmark run is supported by specifying the run ID directly in the command. If no run ID is provided, the validation defaults to processing the latest available run.

Related Skills

Explore More Software Engineering Skills→
EurecaMomentEurecaMoment

benchclaw-stage4-per-template-batch-synthesis

Generate grey-batch items from template configurations using Python scripts.

Official
Intermediate
tvishwanadhatvishwanadha

review-codex

Dispatch reviewer:self-review into a Codex thread for parallel review.

Community
Advanced
barikata1984barikata1984

quality-review

Automates git-based code quality reviews for commits and pull requests.

Community
Intermediate
Buntyarora97Buntyarora97

validation

Execute and monitor named shell commands as validation steps.

Community
Advanced