ywc-agent-toolkit
claudecodexYWC skill distribution toolkit for Claude Code — skills covering planning, commits, PR creation, spec writing, code review, security audit, and development workflows
60 skills · 1 MCP server
Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
YWC skill distribution toolkit for Claude Code — skills covering planning, commits, PR creation, spec writing, code review, security audit, and development workflows
60 skills · 1 MCP server
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
52 skills
My Original and Collected skills, agents, commands, and hooks. Writing, reviewing, planning, QA, and shipping across the dev cycle.
31 skills · 9 commands · 1 agent · hooks
A thin layer of engineering judgment for AI-assisted coding: it classifies each change, then applies the right depth and lenses across planning, review, verification, debugging, and communication, instead of one uniform pass regardless of risk.
29 skills · 12 commands
Portable Codex, Claude, and Cursor workflow pack.
36 skills
Author models in Three.js or Blender MCP, code Three.js motion and interaction for both, and approve results on localhost.
35 skills · hooks
AI agent skills for the Spark CLI - email, calendar, contacts, teams, and meetings workflows.
34 skills
Ironclad workflow discipline for Claude Code — professional mode, systematic planning, and multi-session orchestration
27 skills · 2 agents · 3 MCP servers · hooks
General-purpose Langfuse integration for data exploration, dashboard management, prompt versioning, datasets, and experiments.
28 skills · 5 agents
Markdown-based work-tracking substrate for AI-driven projects. Items as files in .work/, late-binding releases, gates that produce items, goal-backed autopilot queue runner.
32 skills · hooks
Cekura voice AI testing & evaluation: onboarding, agent setup, metrics, and evals — all in one plugin.
14 skills · 15 commands · 1 MCP server · hooks
Find, verify and enrich every B2B contact via the Tomba MCP server
29 skills · 1 MCP server
1Sat ecosystem tools for BSV — unified indexing and collection overlay guidance, ordinals minting and marketplace (list/buy/cancel), BSV21 token operations, wallet setup (BRC-100), transaction building, time locks, sweep/import, OpNS claiming at 1sat.name and owned-name management, dApp wallet connection, CLI tool, media extraction, and MCP server for wallet-desktop browser automation.
27 skills · 1 agent · 1 MCP server
Sentimony agent skills: scope triage, planning, plan execution, test-driven development, debugging, code review, verification, and branch finishing; prose editing, dashes, and negative parallelism; skill crafting; Apache ECharts; frontend design, Vitest, TypeScript, agent context maintenance, secret hygiene, browser debugging, GitHub account switching, and committing the working tree.
28 skills
Australian tax prep skills and prep-only runtime tools for Claude Code.
25 skills · 1 MCP server
Software development workflow skills — design features, implement from plans, refactor codebases, extract patterns, design tests, and ship releases.
24 skills · 1 agent
Plan, execute, review and ship work items end-to-end with a predictable agent loop.
3 skills · 20 commands · hooks
Quality enforcement: TDD discipline, code review workflows, release verification, and CI failure analysis.
13 skills · 4 commands · 7 agents
Core developer workflow skills: planning, execution, communication, and powerup discovery.
16 skills · 4 commands · 3 agents
Spec-Driven Development harness with auto-loop sprint execution. Pipeline: /proposal -> /tdd-align -> /decompose -> /sprint -> /verify
21 skills · hooks
Grok as a peer implementer for Claude Code: default integration=direct lands live-tree edits for one-shot code (no consent gate); auto/review are opt-in worktrees; ACP peer is opt-in multi-turn (always external worktree; stop-time apply). runMode direct is a separate installed-home security posture. Review, reason, setup, continue-run, and verified handoff included. See plugin/references/integration-modes.md. Not affiliated with xAI.
19 skills · 2 agents · hooks
Massively Decomposed Agentic Processes (MAD) - Break complex tasks into atomic steps with near-zero errors
5 skills · 4 commands · 11 agents · 1 MCP server · hooks
MCP tools for the Kages operation set, authoring skills for each design system, improvement moves and an edit hook.
20 skills · 1 MCP server · hooks
Git, PRs, tickets, releases, visual diffs, debugging, and review workflows.
17 skills · 4 agents
A full-lifecycle research pipeline for OR & ML, 17 skills + 2 subagents take a project from prior-art survey to the conference talk, poster, and social note cards — Zotero literature intake, structured reading notes, note-driven PDF category highlighting, publication-grade figures, top-journal-style section drafting, LaTeX polishing, noun-term jargon auditing, defensive-writing (over-hedging) auditing, Chinese academic AI-tone auditing, citation verification against official APIs, three-blind adversarial review, point-by-point rebuttal, venue-transfer resubmission, and Xiaohongshu (RedBook) multi-image note cards with optional auto-publish. Its prior-art survey covers research-grade questions across engineering and academic sources, not just papers.
18 skills · 2 agents · hooks
An opinionated go-to-market operator for Apollo.io: open-source skills for Claude Code, Codex, and any AI chat.
20 skills
Create, package, and recut VidMuse projects — script- and Style-directed H3 AI music videos, generation-first reusable IP-led films, focused product skills, 162 locally installable Shotcraft effects, on-demand official VidMuse CLI setup, and official HyperFrames domain skills.
19 skills
Yet another AI workflow: planning, implementation, PR delivery, review, simplification, and investigation skills that wire into one another
16 skills · 2 agents · hooks
A retrieval architecture that pre-projects sources to task domains at ingestion time. Runtime becomes lookup, not reshape. Ships skills for ingesting sources under a 9-pass source-only protocol, retrieving via two-layer indexes (corpus catalogue + per-task distillation indexes), and a PreToolUse hook that enforces deep-reference structural discipline at write time.
18 skills
Minimal, composable skill toolkit for AI coding agents: intent-first routing, self-contained skills, TDD, opt-in session learning
17 skills