feiskyer/claude-code-settings

Curated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub automation & more.

1.6kStars on the repository
28Mods indexed here, across every type
19d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

deep-reflector

01

feiskyer/claude-code-settings

Agent

Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.

1.6k 19d ago A 40 tokens original MIT

github-issue-fixer

02

feiskyer/claude-code-settings

Agent

GitHub issue resolution specialist. Analyzes, plans, and implements fixes for GitHub issues with proper testing and PR creation. Use when fixing specific GitHub issues.

1.6k 19d ago A 40 tokens original MIT

insight-documenter

03

feiskyer/claude-code-settings

Agent

Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when documenting important discoveries, optimizations, or problem solutions.

1.6k 19d ago A 36 tokens original MIT

feiskyer/claude-code-settings

Agent

Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.

1.6k 19d ago A 42 tokens original MIT

pr-reviewer

05

feiskyer/claude-code-settings

Agent

Expert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.

1.6k 19d ago A 40 tokens original MIT

ui-engineer

06

feiskyer/claude-code-settings

Agent

Expert UI/frontend developer for creating, modifying, or reviewing frontend code, UI components, and user interfaces. Use when building React components, responsive designs, or any frontend development tasks. PROACTIVELY use for UI/UX implementation, component architecture, and frontend best practices.

1.6k 19d ago A 59 tokens original MIT

analyzer

07

feiskyer/claude-code-settings

Agent

Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.

1.6k 19d ago A 29 tokens copy · 95% MIT

comparator

08

feiskyer/claude-code-settings

Agent

Compare two skill outputs blindly to determine which better accomplishes the eval task. Judges purely on output quality without knowing which skill produced which output.

1.6k 19d ago A 31 tokens copy · 92% MIT

grader

09

feiskyer/claude-code-settings

Agent

Evaluate expectations against an execution transcript and outputs. Grades assertions pass/fail with evidence, verifies claims, and critiques evals for the skill-creator benchmarking pipeline.

1.6k 19d ago A 34 tokens copy · 98% MIT