Developer Tools●●Solid
Anti-regression setup Claude Code – subagents, hooks, and Claude.md
CLAUDE.md + subagent isolation for Claude Code context drift—addresses real pain.
Solve My ProblemShip It
Creatman
413mo ago
Back to browse
GitHub Repository
4 stars
Regression-dog – A 20-line skill that reviews your code for regressions
by itay-maman·Apr 5, 2026·5 points·0 comments
AI Analysis
●MidCozyShip It
Useful Claude Code skill, but it's config for an existing tool, not a product.
Strengths
- •Twenty lines means genuinely easy to audit, modify, and understand what it does.
- •Addresses regression detection friction that slips through standard code reviews.
Weaknesses
- •Entirely dependent on Claude Code platform with no standalone functionality.
- •Similar regression checking available in GitHub Copilot, CodeRabbit, and other review tools.
Category
Target Audience
Developers already using Claude Code for code review workflows
Similar To
GitHub Copilot review · CodeRabbit · Claude Code built-in review
Similar Projects
AI/ML●Mid
Claude Code skills for building LLM evals
Structured eval workflow for Claude Code when LangSmith and Braintrust already exist.
Niche GemShip It
paulaq
201mo ago
Developer Tools●●Solid
SnapDrift – a pluggable visual regression workflow for GitHub Actions
Route scoping from changed files cuts noise versus Percy's blanket screenshot approach.
Niche GemShip It
ranacseruet
102mo ago
Developer Tools●●●Banger
TracePact – Catch tool-call regressions in AI agents before prod
VCR cassettes for agent tool sequences—catches prompt regressions before deploy.
Solve My ProblemShip ItNiche Gem
soydanicg
102mo ago
Security●●●Banger
OpenClaw skills degrade agent safety
Behavioral safety testing reveals 45 regressions static analysis misses—guardrails provided.
Big BrainWizardryZero to One
shadab_nazar
123mo ago
Finance●●Solid
ZcoreAI – Z-score regression channel screener
Regression channel Z-scores across timeframes, but TradingView and QuantConnect dominate quant screening.
Niche Gem
tchantchov
103mo ago