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 →

119Stars on the repository
54Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

jellydn/my-ai-tools

Skill Claude Code

Guides disciplined AI-assisted engineering that avoids cognitive surrender and keeps humans accountable. Use for non-trivial implementation, architecture, security, or operational tasks.

not rated 119 3d ago A SkillSpector: warn 35 tokens original MIT

adr

02

jellydn/my-ai-tools

Skill Claude Code

Record architecture decisions with ADRs — captures why, alternatives considered, and consequences.

not rated 119 3d ago A SkillSpector: pass 17 tokens original MIT

blindspot-pass

03

jellydn/my-ai-tools

Skill Claude Code

Find unknown unknowns before starting implementation — searches git history, patterns, and architecture for hidden gotchas.

not rated 119 3d ago A SkillSpector: pass 24 tokens original MIT

jellydn/my-ai-tools

Skill Claude Code

Experiment with model capabilities — HTML reports, embedded questionnaires, proactive research, multi-step reasoning.

not rated 119 3d ago A SkillSpector: pass 23 tokens original MIT

code-quality-review

05

jellydn/my-ai-tools

Skill Claude Code

Run an extremely strict maintainability and structural code quality review — flags abstraction issues, spaghetti growth, and boundary leaks.

not rated 119 3d ago A SkillSpector: pass 26 tokens original MIT

code-review

06

jellydn/my-ai-tools

Skill Claude Code

Review the diff since a fixed point along two axes — Conventions (does the code follow this repo's coding standards and Tidy First practices?) and Intent (does the change do what it claims to do?). Runs both reviews in parallel sub-agents and reports them side by side. Use when you want to review a branch, a PR…

not rated 119 3d ago A SkillSpector: pass 85 tokens original MIT

codemap

07

jellydn/my-ai-tools

Skill Claude Code

Map codebase structure with parallel analysis — produces 7 documents about architecture, concerns, and conventions.

not rated 119 3d ago A SkillSpector: pass 22 tokens original MIT

commit-atomic

08

jellydn/my-ai-tools

Skill Claude Code

Group staged changes into atomic commits with commitizen convention.

not rated 119 3d ago A SkillSpector: pass 14 tokens original MIT

context-discovery

09

jellydn/my-ai-tools

Skill Claude Code

Discover context using MCP tools — fff, sem, ctx, qmd, codebase-memory-mcp for codebase understanding.

not rated 119 3d ago A SkillSpector: pass 29 tokens original MIT

doc-search

10

jellydn/my-ai-tools

Skill Claude Code

Search project documentation — ADRs, wiki entries, conventions via ripgrep, qmd, fff, and ctx.

not rated 119 3d ago A SkillSpector: warn 26 tokens original MIT

docs-update

11

jellydn/my-ai-tools

Skill Claude Code

Update docs when code changes — reviews commits and syncs user-facing documentation.

not rated 119 3d ago A 17 tokens copy · 89% MIT

draft-pull-request

12

jellydn/my-ai-tools

Skill Claude Code

Draft pull requests with structured descriptions using gh CLI.

not rated 119 3d ago A SkillSpector: warn 14 tokens original MIT

git-context

13

jellydn/my-ai-tools

Skill Claude Code

Search git history for context — commit messages, blame, related changes, impact analysis.

not rated 119 3d ago A SkillSpector: pass 19 tokens original MIT

handoffs

14

jellydn/my-ai-tools

Skill Claude Code

Create handoff plans for continuing work across sessions.

not rated 119 3d ago A SkillSpector: pass 12 tokens original MIT

jellydn/my-ai-tools

Skill Claude Code

Log implementation decisions — tracks deviations from plan and captures rationale.

not rated 119 3d ago A SkillSpector: warn 15 tokens original MIT

llm-wiki

16

jellydn/my-ai-tools

Skill Claude Code

Build a persistent compounding wiki from raw sources using the LLM Wiki pattern.

not rated 119 3d ago A SkillSpector: pass 20 tokens original MIT

jellydn/my-ai-tools

Skill Claude Code

Coordinates a strong read-only lead with a cheaper implementation executor. Use for non-trivial coding tasks that benefit from separate planning, execution, and independent verification.

not rated 119 3d ago A SkillSpector: warn 37 tokens original MIT

pickup

18

jellydn/my-ai-tools

Skill Claude Code

Resume work from previous handoff sessions stored in .planning/handoffs/.

not rated 119 3d ago A SkillSpector: pass 17 tokens original MIT

jellydn/my-ai-tools

Skill Claude Code

Turn ideas into executable goal packages with guided interviews and codebase analysis.

not rated 119 3d ago A SkillSpector: pass 21 tokens original MIT

portless-local

20

jellydn/my-ai-tools

Skill Claude Code

Replace port numbers with stable named .localhost URLs for local development.

not rated 119 3d ago B SkillSpector: warn 16 tokens original MIT

pr-review

21

jellydn/my-ai-tools

Skill Claude Code

Fix PR review comments by implementing requested changes.

not rated 119 3d ago A SkillSpector: pass 11 tokens original MIT

prd

22

jellydn/my-ai-tools

Skill Claude Code

Generate Product Requirements Documents from feature ideas — plans specs and requirements.

not rated 119 3d ago A 14 tokens copy · 86% MIT

qmd-knowledge

23

jellydn/my-ai-tools

Skill Claude Code

Manage project knowledge with qmd — captures learnings, decisions, and conventions.

not rated 119 3d ago A SkillSpector: warn 20 tokens original MIT

quiz-me

24

jellydn/my-ai-tools

Skill Claude Code

Verify understanding after implementation with targeted quizzes.

not rated 119 3d ago A SkillSpector: pass 10 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: