Workflow plugins

32 curated agents (Boss meta-orchestrator + OMO sub-orchestrators + OMC specialists + vendored engineering agents), 139 curated skills, rules, 8 behavioral hooks (vault enforcement, agent logging, verification), and MCP servers (Context7, Exa, grep.app)

4 skills · 5 MCP servers · hooks · LSP

Tune a car-audio DSP with REW — intake → crossovers → time alignment → phase → EQ → imaging → taste voicing, via a Generator-Critic-Arbiter review loop. Any car, any DSP. Bundles the review-loop method (independent multi-AI review + anti-anchoring).

1 skill · 2 commands · hooks

Behavioral guidelines to reduce common LLM coding mistakes: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution

1 skill

Nuxt/Vue/TS workflow hooks and tools: auto-lint, typecheck, test on save, pnpm enforcement, pre-commit checks

35 skills · hooks

Fuse Claude with the Codex CLI: Watchdog auto-reviews each turn, Duel Plan co-plans with debate, Duel Review reviews a PR with two agents, Consult fetches a second opinion.

3 skills · 1 command · hooks

Interview the user about a project, then produce a production-ready SPEC.md (plus CLAUDE.md and an optional private spec).

1 skill

Multi-agent orchestration plugin - a virtual dev crew with intelligent model routing (Opus/Sonnet/Haiku), lite mode, 3-layer codebase indexing, auto-skill selection, task history, rollback, and custom agents

12 skills · 10 commands · 11 agents · hooks

Convert prompts, vague tasks, and agent workflows into repeatable, verifiable loops with goal/scope/verification/escalation/stop conditions.

1 skill

Session-closeout audit and skill-forging rules: reconcile every user ask, sweep scratchpad residue, run the seven hard obligations before retiring a skill.

1 skill

Small things for Claude Code: plain explanations, a confidence % on every option, a cross-check by a different model, a read-only audit, agents with their own model and effort, and a compact rule.

2 skills · 4 agents · hooks

Multi-LLM orchestration: parallel plan review, task generation, implementation, and code review across 19 coding harnesses (Codex, Cursor, opencode, pi, omp, fx, aider, Antigravity…).

1 skill · hooks

Generates a PR body that matches the repo's mandatory format (Goal / Files changed / Verification / Known limits / User-visible benefit / Next step), with honest 'Not run' handling for unrun checks.

1 command

Install all 81 Skill-Madness skills: the 14-phase orchestrator, 10 role agents with exclusive file ownership, 2 contract skills (OpenAPI/AsyncAPI/Pydantic/TS/JSON Schema), 4 git workflow skills, 9 meta/skill-management skills, 42 cross-cutting workflow skills (plan-builder, repo-deep-dive, ui-brief, mermaid-charts, llm-wiki, …), and 13 autonomous-loop skills (fix-until-green, babysit, coverage-loop, …).

87 skills

Teaches agents how to use Dispatch: shared memory, task boards, subagents, repo tools, reaching the user, sharing artifacts, review workflow, UI validation, personas, jobs, templates, and personalities.

12 skills

干中学: turn-based guess→reveal→principle loop, cold-read sub-agent, cross-session knowledge map. Cures vibe-coding (delivery up, understanding flat).

1 skill

18 specialized marketing agents, 55+ skills, 22 commands, and production-ready hooks for campaign planning, copywriting, SEO, analytics, and growth experimentation

72 skills · 22 commands · 18 agents · hooks

Guard agents, auto-triggered skills and path-scoped rules that make Claude Code behave like a senior engineering team.

30 skills · 7 commands · 9 agents · hooks

Frontend development discipline — validation, pixel-perfect measurement, editing, comments, code style, testing, migration baselines.

13 skills

Six ROS2 domain skills, engineering references, scrapling, verify-* quality gates, and gen-docs. Invoked as /ccg:<skill>.

10 skills

A comprehensive suite of Claude Code ultracode multi-agent workflow scripts, along with a workflow-authoring skill, a live-progress statusline, enhanced observation UI, and diagram tools. Everything composes into a full-lifecycle orchestration pipeline

1 skill · 7 commands · hooks

You do the specs and systems engineering. shiploop ships the code: a self-improving multi-agent harness that dispatches the tickets you name across every repo in your product with a fresh agent per ticket and guarded auto-merge, and every resolved ticket writes a lesson into your git-tracked CLAUDE.md so the next run is smarter. Tickets dispatch at a fixed floor tier and escalate once on measured failure, rather than a tier predicted per ticket up front.

1 skill · 7 commands

An agentic workflow engine for GTM/RevOps automation. Includes tools for workflow compilation and integration with the crayon SDK.

5 skills

Agent-to-agent messaging for AI coding agents. Sessions, direct/broadcast/channel messages, shared state (TTL + atomic CAS), threaded replies, real-time WebSocket feed, and a local dashboard on :3421. Ships a file-coordination hook that gives parallel agents automatic per-file locking on shared edits.

1 MCP server

Convenes several expert perspectives that challenge each other on a design decision with real trade-offs before code is written; quick mode runs a single round. Not for a one-question-at-a-time interrogation of a plan; use plan-interview. Not for splitting implementation across workers; use dispatch directly.

1 skill

Stress-tests a plan, design, or idea through a phased one-question-at-a-time interview before code is written, ending in a compact decision log. Not for a multi-perspective debate; use design-council.

1 skill

Slices an existing plan, PRD, or milestone into an executable sprint of dependency-ordered vertical slices sized for one agent run each, with done-when verification per slice; never fabricates a plan. Not for deciding the approach; use architecture.

1 skill

The verified workflow engine for Claude Code: durable .planning state, phased roadmaps, specialized subagents, deterministic verification gates.

97 skills

Your Claude workforce: 62 skills across 7 departments (developers, design, marketing, social, finance, operations, legal) behind one router. Invoke with /omniskill, or let it offer itself when you start a new project.

70 skills · hooks

Two-agent (Product Owner + AI Developer) spec-to-deploy lifecycle for building internal and client apps with AI, plus FuseBase Apps domain skills. Repo-local, tool-portable, no SaaS.

56 skills

23 battle-tested copywriting skills built on the Prometheus library — Ogilvy, Schwartz, Halbert, Hopkins, Hormozi, Fladlien and more.

23 skills · 23 commands