haku
claudeLean leadership plugin that runs the decide → spec → evidence loop — 8-skill core + 5 gate agents, with 8 opt-in role packs (product, people, engineering)
52 skills · 5 agents · hooks
Essential Claude Code workflow and context engineering tools for productive development
Plugin base from marketplace vibekit in shrwnsan/vibekit-claude-plugins. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
branch-hygieneClassify and clean up merged, stale, and orphaned git branches and worktrees. Detects squash-merges that git branch --merged cannot see, stale worktrees, and remote-gone branches. Use when user asks to clean up branches, prune worktrees, tidy the repo, or perform git housekeeping.
crafting-commitsGenerates git commit messages following conventional commit standards with collaborative attribution. Use when user requests commit message creation, drafting, or help with formatting.
handoff-contextDetects natural language handoff requests and generates structured context summaries for seamless thread continuation. Use when user says "handoff", "new thread", "continue in fresh thread", or similar phrases.
systematic-debuggingSystematic debugging approach for errors, test failures, and unexpected behavior. Use when encountering bugs, test failures, errors, or when debugging is needed. Prevents common anti-patterns like random fixes, skipping root cause analysis, and thrashing.
/base:commitCreate a git commit with intelligent message drafting (-f for fast, -v for verbose)
/base:review-archReview app architecture: components, data flows, risks, and prioritized improvements
workflow-orchestratorCoordinates development workflows and orchestrates base plugin operations including git workflows, quality checks, and productivity automation
"${CLAUDE_PLUGIN_ROOT}/scripts/filter-test-output.sh"
Lean leadership plugin that runs the decide → spec → evidence loop — 8-skill core + 5 gate agents, with 8 opt-in role packs (product, people, engineering)
52 skills · 5 agents · hooks
Safety-proportional process for agentic SDLC: trivial changes skip ceremony, risky changes earn it. Risk-tiered loop with fail-twice auto-promotion and a verify-before-done hard gate.
4 skills · hooks
Enhanced web search with multi-service fallback (TinyFish, Tavily, Brave, Exa, Jina, plus keyless Firecrawl/Defuddle) — works without API keys
1 skill · 1 agent · hooks
Sound notifications and alerts for Claude Code tasks
hooks
Pre-classifier permission gate for auto mode: System One decision models (TypeSafe Jev, Liquid d1, compatible endpoints) as typed allow/ask/deny PreToolUse decisions. Fails safe — errors hand back to Claude Code's own classifier.
hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.