review-reviewers

Analyze Claude CI session logs to identify behavioral problems and workflow gaps.

30|5|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/max-sixty/tend --skill review-reviewers
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-reviewers
Source: https://github.com/max-sixty/tend/tree/main/plugins/tend-ci-runner/skills/review-reviewers
Command: npx skills add https://github.com/max-sixty/tend --skill review-reviewers

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Hourly analysis of Claude CI session logs identifies behavioral problems, skill gaps, and workflow inefficiencies to improve reliability and guide targeted fixes.

Core Features & Use Cases

  • Analyze Claude-powered CI runs from the past hour to surface behavioral issues, skill gaps, and workflow bottlenecks.
  • Automatically create PRs or issues to fix identified problems and improve repos and workflows.
  • Maintain a monthly tracking issue and deduplicate findings across runs to build evidence without noise.
  • Cross-check historical outcomes against bot decisions to verify impact and reduce regressions.

Quick Start

Trigger the review-reviewers skill to begin hourly Claude CI session log analysis.

Frequently Asked Questions about review-reviewers

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

FAQPage Schema
How do I analyze Claude CI session logs to find behavioral issues?

You can analyze Claude CI session logs hourly to surface behavioral problems and workflow gaps by tracking historical evidence and automatically generating PRs or issues to fix identified inefficiencies.

What is the best way to track and deduplicate findings from automated CI runs?

Maintain a monthly tracking issue to cross-reference historical outcomes and deduplicate findings across CI runs, verifying bot decisions and reducing regressions while building evidence without noise.

Does this CI session analysis approach work with Tend adopter repositories?

Yes, this CI session analysis applies specifically to Tend adopter repositories running Claude-powered CI, parsing hourly session logs to identify workflow gaps and automatically creating PRs or issues with run IDs and logs.

How do I automatically create PRs from CI workflow gaps without false positives?

Implement gating for confidence and magnitude to filter CI session findings, deduplicating results against a tracking issue to ensure only high-evidence workflow gaps generate actionable PRs and reduce false positives.

When do I need automated hourly analysis for Claude-powered CI workflows?

Automated hourly analysis is needed when Claude-powered CI runs frequent sessions and you want to quickly spot behavioral problems, surface skill gaps, and verify bot decisions before regressions compound across repositories.