Score and verify code review findings against repository code.
npx skills add https://github.com/axel-kaliff/dotfiles --skill score-findings
Please help me install this Agent Skill. Skill: score-findings Source: https://github.com/axel-kaliff/dotfiles/tree/main/claude/.claude/skills/score-findings Command: npx skills add https://github.com/axel-kaliff/dotfiles --skill score-findings
Pull requests and automated review tools generate many findings, including duplicates, vague suggestions, and false positives, which waste reviewer time and slow merges. This Skill automates verification against the actual repository code, filters out low-value findings, and prioritizes actionable fixes so reviewers can focus on real regressions.
Score the provided list of findings for the current branch and return the high-confidence findings along with counts of filtered results.
High-intent search queries and answers about installing and using this skill.
You can automatically verify code review findings by spawning parallel Sonnet agents that read code context, compare branches against origin/master, and evaluate semantic regressions to filter out false positives.
Automated deduplication merges code review findings by file, line, and category, then surfaces possible shared root causes when multiple related findings appear in the same function or code block.
Yes, you can batch verify pull request findings by spawning parallel Sonnet agents that process up to five findings per agent while keeping file context together for pre-merge checks.
Score and filter low-value code review suggestions by assigning a 0-100 rating based on accuracy and actionability, returning only findings scoring 50 or above along with a breakdown of filtered items.
Detect pre-existing code changes by using git to compare the current branch against origin/master before evaluating code review findings, ensuring automated scoring only accounts for new regressions.
Automated code review tools generate duplicates and false positives because they lack semantic context, which parallel Sonnet agents can resolve by reading actual repository code and applying deterministic scoring.
carlos-algmsGenerate a file-by-file code review from a git diff against a target branch.
tuanldasGenerate confidence-scored code review findings with actionable fixes.
qiphonCoordinate parallel GitHub pull request reviews with gh CLI and ruv-swarm agents.
mpelissariDetect security risks in AgentSkill packages across local and ClawHub files.
