jellydn
UserComprehensive 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.
Categories
Indexed Skills (33)
blindspot-pass
Find unknown unknowns before starting implementation — searches git history, patterns, and architecture for hidden gotchas
capability-experiments
Experiment with model capabilities — HTML reports, embedded questionnaires, proactive research, multi-step reasoning
code-quality-review
Run an extremely strict maintainability and structural code quality review — flags abstraction issues, spaghetti growth, and boundary leaks
code-review
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, work-in-progress changes, or ask to "review since X".
codemap
Map codebase structure with parallel analysis — produces 7 documents about architecture, concerns, and conventions
commit-atomic
Group staged changes into atomic commits with commitizen convention
context-discovery
Discover context using MCP tools — fff, sem, ctx, qmd, codebase-memory-mcp for codebase understanding
doc-search
Search project documentation — ADRs, wiki entries, conventions via ripgrep, qmd, fff, and ctx
docs-update
Update docs when code changes — reviews commits and syncs user-facing documentation
draft-pull-request
Draft pull requests with structured descriptions using gh CLI
git-context
Search git history for context — commit messages, blame, related changes, impact analysis
handoffs
Create handoff plans for continuing work across sessions
implementation-logger
Log implementation decisions — tracks deviations from plan and captures rationale
llm-wiki
Build a persistent compounding wiki from raw sources using the LLM Wiki pattern
orchestrating-fusion
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.
plannotator-setup-goal
Turn ideas into executable goal packages with guided interviews and codebase analysis
portless-local
Replace port numbers with stable named .localhost URLs for local development
pr-review
Fix PR review comments by implementing requested changes
prd
Generate Product Requirements Documents from feature ideas — plans specs and requirements
qmd-knowledge
Manage project knowledge with qmd — captures learnings, decisions, and conventions
quiz-me
Verify understanding after implementation with targeted quizzes
ralph
Convert PRDs to prd.json format for the Ralph autonomous agent system
slop
Remove AI-generated code slop from git diffs to maintain code quality
spec-interview
Clarify requirements through targeted questions — uncovers unknown unknowns in specs
tdd
Guide through the Red-Green-Refactor cycle for test-driven development
tmux
Control tmux sessions remotely — send commands, capture output, manage panes
accountable-engineering
Guides disciplined AI-assisted engineering that avoids cognitive surrender and keeps humans accountable. Use for non-trivial implementation, architecture, security, or operational tasks.
adr
Record architecture decisions with ADRs — captures why, alternatives considered, and consequences
pickup
Resume work from previous handoff sessions stored in .planning/handoffs/
security-audit
Audit code for security vulnerabilities — read-only analysis
ai-slop-remover
Remove AI-generated code patterns that don't match codebase style
code-reviewer
Review code for quality, security, and best practices — read-only analysis
test-generator
Generate comprehensive tests for code changes
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.