jellydn/my-ai-tools

Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, Amp, Li, Codex and Claude Code Switch with custom configurations, MCP servers, plugins, and commands.

This repository also configures its own agents. See what my-ai-tools tells them →

124Stars on the repository
60Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

ralph

25

jellydn/my-ai-tools

Skill Claude Code

Convert PRDs to prd.json format for the Ralph autonomous agent system.

not rated 124 +1 today A 17 tokens copy · 97% MIT

security-audit

26

jellydn/my-ai-tools

Skill Claude Code

Use when reviewing code for security vulnerabilities, hardening an application, or deriving security requirements from OWASP/ASVS guidance.

not rated 124 +1 today A SkillSpector: pass 29 tokens original MIT

slop

27

jellydn/my-ai-tools

Skill Claude Code

Remove AI-generated code slop from git diffs to maintain code quality.

not rated 124 +1 today A SkillSpector: pass 17 tokens original MIT

spec-interview

28

jellydn/my-ai-tools

Skill Claude Code

Clarify requirements through targeted questions — uncovers unknown unknowns in specs.

not rated 124 +1 changed 21d ago A SkillSpector: pass 18 tokens original MIT

tdd

29

jellydn/my-ai-tools

Skill Claude Code

Guide through the Red-Green-Refactor cycle for test-driven development.

not rated 124 +1 changed 21d ago A SkillSpector: pass 17 tokens original MIT

tmux

30

jellydn/my-ai-tools

Skill Claude Code

Control tmux sessions remotely — send commands, capture output, manage panes.

not rated 124 +1 today A SkillSpector: pass 17 tokens original MIT

ai-slop-remover

31

jellydn/my-ai-tools

Skill Claude Code

Remove AI-generated code patterns that don't match codebase style.

not rated 124 +1 today A SkillSpector: pass 17 tokens original MIT

code-reviewer

32

jellydn/my-ai-tools

Skill Claude Code

Review code for quality, security, and best practices — read-only analysis.

not rated 124 +1 today A SkillSpector: pass 18 tokens original MIT

jellydn/my-ai-tools

Skill Claude Code

Create clear documentation for code and APIs.

not rated 124 +1 today A SkillSpector: pass 11 tokens original MIT

test-generator

34

jellydn/my-ai-tools

Skill Claude Code

Generate comprehensive tests for code changes.

not rated 124 +1 today A SkillSpector: pass 9 tokens original MIT

babysit-pr

35

jellydn/my-ai-tools

Skill Codex

Use when monitoring an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.

not rated 124 +1 today A 29 tokens copy · 91% MIT

diagnosing-bugs

36

jellydn/my-ai-tools

Skill Claude Code

Build a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock the fix with a regression test.

not rated 124 +1 changed 20d ago A 34 tokens original MIT

implement-spec

37

jellydn/my-ai-tools

Skill Claude Code

Implement a complete spec from its ticket graph, using isolated workers and one integration branch.

not rated 124 +1 today A 20 tokens original MIT

pr

38

jellydn/my-ai-tools

Skill Claude CodeCodex

Write a fast-to-review pull request body with a visual summary, before/after evidence, and merge-risk analysis.

not rated 124 +1 today A 25 tokens original MIT

retro

39

jellydn/my-ai-tools

Skill Claude Code

Review a coding session and propose environment changes that prevent repeated agent mistakes.

not rated 124 +1 today A 16 tokens original MIT

visual-pr

40

jellydn/my-ai-tools

Skill Claude Code

Posts a concise visual outline as a GitHub pull request comment. Use only when the user explicitly asks for visual-pr.

not rated 124 +1 today A 27 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: