tonone
claude23-agent engineering + product team with 125 skills for Claude Code
49 skills · 100 agents · hooks
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
23-agent engineering + product team with 125 skills for Claude Code
49 skills · 100 agents · hooks
Multi-agent orchestration system with 51 specialized agents for development workflows, code quality, deployment, research, games, and more. Includes orchestrators for checkpoint, deploy, quality, fullstack, research, games, corpus, web, and python workflows.
51 agents
Point it at a GitHub issue and get back a reviewed pull request. Hyperflow turns one AI coding session into a structured engineering pipeline: plan sharpens and decomposes the work, dispatch fans out parallel workers, and a domain specialist reviews every step — nothing ships unreviewed. 18 skills, 22 specialist reviewer and investigator agents, adaptive depth so a 5-line fix never triggers a deep run, and persistent per-project memory that lives in your repo and never leaves it. Runs on whatever model your session already uses — zero config, no API keys, no daemon. Works across Claude Code, Codex App/CLI, OpenCode, Grok, Antigravity, and Cursor.
18 skills · 23 agents · hooks
A subconscious for Claude Code. A Letta agent watches your sessions, accumulates context, and whispers guidance back.
hooks
Full context on the TypeSafe API: question types, architectural patterns, and best practices
1 skill
A Terraforming MCP for Knowledge Graphs: validate, classify, and govern AI-generated ontologies.
2 skills · 1 MCP server
Korean law for Claude via the official 법제처 Open API: statutes, precedents, administrative rules, local ordinances, treaties and interpretations, with citation verification. 법제처 42개 API → 10개 통합 도구. 법령·판례·행정규칙·자치법규·조약·해석례 + LLM 환각 방지 인용 검증 + 조문 영향 그래프 + 시점 비교 자동 diff + 판례 생사 확인(Citator) + 행위시법 판단 + 이럴 땐 이렇게 5단계 안내
1 skill · 1 MCP server
Automatic semantic memory for Claude Code — remembers what you worked on across sessions
3 skills · hooks
Gives AI agents the function they asked for, not the file. Commercial use needs a license.
1 skill · 1 MCP server
Section-level documentation retrieval across Markdown, RST, notebooks, and OpenAPI specs.
1 skill · 1 MCP server
Tabular data retrieval over CSV and Excel. Query rows and aggregate without loading the file.
1 MCP server
API design, documentation, and testing with OpenAPI spec generation
2 commands · 1 agent
Automated code review, security scanning, and quality enforcement
2 commands · 1 agent
Deployment automation with Dockerfile generation, CI/CD pipelines, and infrastructure as code
3 commands
Operate NVIDIA DGX Cloud Lepton through the globally installed `lep` CLI.
1 skill
Protocol guidance for deterministic agent context lifecycles
2 skills · hooks
Persistent memory across Claude Code sessions using Supermemory
2 commands · 1 agent · 1 MCP server · hooks
Set up and use Gonzo, the open-source terminal log analysis tool. Detects deployment platforms (Vercel, Supabase, K8s, Docker, AWS, Cloudflare, Fly, Render, Railway, Netlify), generates the right pipe command with platform-specific normalizers, and configures AI analysis. Use when the user wants to tail, watch, stream, or analyze logs in their terminal.
1 skill
Webcmd browser skill for live, authenticated browser automation with local sitemap memory. Requires the @agentrhq/webcmd npm CLI.
1 skill
Shows a plain-English rewrite of each Claude Code assistant message, produced by a local LLM (ollama, default), the Anthropic API, or any OpenAI-compatible API. Display-only.
1 skill · 1 command · hooks
Essential development commands for coding, debugging, testing, optimization, and documentation
11 commands · 5 agents
Full BMAD agile workflow with role-based agents (PO, Architect, SM, Dev, QA) and interactive approval gates
1 command · 7 agents
Requirements-driven development workflow with quality gates for practical feature implementation
1 command · 4 agents
AI-powered blog creation, optimization, and management with 32 skill directories (1 orchestrator + 31 sub-skills), 5 agents, FLOW framework integration, semantic topic-cluster execution, multilingual publishing, brand and discourse context auto-load, and 5-category scoring. Optimized for Google rankings and AI citations.
33 skills · 5 agents
Optional companion to claude-blog (needs claude-blog 2.3.2 or later): article status band, live pipeline and five-gate review panel, history of past blogs, and an explicit Run checks control. A Claude Code mod served from the blog-studio branch; install it separately.
Public-content reader for AI agents — reaches public pages, official APIs, and feeds via a Phase 0→3 adaptive access chain (curl_cffi impersonation, mobile/URL transforms, headless-browser fallback). No API keys. Dual-use developer tool; the user is responsible for lawful, authorized use.
1 skill
Product strategy and innovation frameworks including Jobs to Be Done (Clayton Christensen) for customer discovery and product design, tactical negotiation skills (Chris Voss), willingness-to-pay pricing (Monetizing Innovation), and startup metrics (Lean Analytics)
65 skills
UX and UI design skills including Refactoring UI, iOS HIG design, usability heuristics, habit-forming product design, behavior design for retention, web typography, award-winning top-design, Steve Jobs-style design reviews, and Don Norman's foundational design principles
65 skills
Marketing and conversion optimization skills including CRO methodology, StoryBrand messaging, Scorecard Marketing lead generation, viral marketing (Contagious), and 1-Page Marketing Plan
65 skills
Computer use in a separate virtual Mac, with MCP tools and an agent skill.
1 skill · 1 MCP server