{"data":[{"slug":"orchestra","title":"orchestra","description":"Disciplined AI engineering toolkit for Claude Code. Ships typed design-doc templates (Feature LLD, Bug Report, ADR, Postmortem, Runbook, Design Doc) with a 4-gate spec review (Completeness / Evidence / Clarity / Consistency), mandatory mermaid diagrams, an octal-safe auto-numbering script, AGENTS.md and llms.txt sync, a bug-iteration loop that prevents orphan fix-commits, and an enforced doc-before-code workflow with five named gates (Discovery / Design / Spec Review / Commit / Implementation Sync). Includes a Python lint CLI for Refs:-line + metadata + status validation, an auto DECISIONS.md generator with bidirectional ADR supersession consistency. Patterns adopted from Michael Nygard, Google SRE, Pragmatic Engineer, agents.md, and llmstxt.org. First skill of the Orchestra umbrella; future skills cover workflow, registry, tasks, gates, and plans.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/hassan-mohiddin/orchestra.git"},{"slug":"opinionated-prisma-skills","title":"opinionated-prisma-skills","description":"Opinionated skill plugin for Prisma ORM on self-hosted PostgreSQL. Enforces consistent decisions across schema design, migration safety, indexing, transactions, and the raw SQL boundary. Covers UUID v7, snake_case mapping, foreign key indexes, three-step safe migrations, concurrent index creation, and transaction patterns. Skills activate automatically based on context. Supports Claude Code, Codex CLI, Gemini CLI, Cursor, and OpenCode.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/esot321c/opinionated-prisma.git"},{"slug":"open-rx-otc","title":"open-rx-otc","description":"Open RX is a full-stack web development plugin with 17 deep-knowledge skills and 27+ reference files. It covers React architecture, Next.js App Router patterns, UI components (shadcn/ui, Aceternity UI, Magic UI, Tailwind v4), animations (GSAP free era, Motion, CSS), SaaS patterns (Stripe, realtime, email), database design, API craft, testing, deployment, security, conversion optimization, brand design, copywriting, prompt engineering, and local SEO. Includes rx-writer — a consultation system that creates a full technical prescription before any code gets written. Stack: Next.js 15, TypeScript, Supabase, Tailwind v4, shadcn/ui. Free tier (7 skills) on GitHub, full pack (17 skills) for $1. By CutTheChexx.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/CutTheChexx/open-rx.git"},{"slug":"open-rx","title":"open-rx","description":"Open RX makes Claude actually good at building production web apps. 7 free skills (OTC tier) covering React architecture, Next.js App Router patterns, performance optimization, prompt engineering, UX copywriting, local SEO, and the rx-writer consultation system. Every skill is packed with real patterns from real codebases — not generic boilerplate. Upgrade to The Prescription ($1) for 17 skills and 27+ reference files covering UI components, animations, SaaS patterns, database ops, API design, testing, deployment, security, conversion optimization, and brand design.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/CutTheChexx/open-rx.git"},{"slug":"officecli","title":"officecli","description":"OfficeCLI is a Claude Code plugin for local Office document workflows. It helps Claude create, update, and convert Office files when the local OfficeCLI installation supports the requested task.\n\nThe plugin is intended for workflows such as:\n\n- creating PowerPoint presentations in pptx\n- creating Word documents in docx\n- creating structured worksheets in xlsx\n- checking whether a requested Office workflow is supported before execution\n\nThe plugin packages a Claude Code skill and routes supported Office-file tasks to the user's local officecli installation. It is designed for users who want Claude-assisted Office document workflows while keeping execution on their own\nmachine.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/officecli/officecli-skills.git"},{"slug":"novel-studio","title":"novel-studio","description":"An end-to-end web novel production system built on Claude Code. Combines 18 specialist agents and 10 skills to automate the full pipeline: propose → design → create → polish → rewrite.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/MJbae/novel-studio.git"},{"slug":"nova-thesis","title":"nova-thesis","description":"nova-thesis challenges technical implementations before they ship. Present any implementation — a problem statement, a design sketch, a code snippet, or a full repository — and the skill refuses to accept it at\nface value. It scores the work across five dimensions (Correctness, Completeness, Scalability, Security, Maintainability), surfaces a real-world incident from an index of public postmortems that matches the\nriskiest gap, and asks hard, specific questions anchored to that incident. It keeps pushing until every dimension scores at least 7/10, or until you consciously name and accept the remaining trade-offs.\n\nUnlike review tools that confirm, nova-thesis is built to find where things break — before production does. Read-only, MIT licensed, no telemetry, no external services required. Ships with 20 test scenarios and\na defended-thesis example that proves the skill also correctly approves strong work.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/jerry7991/nova-thesis.git"},{"slug":"niw-skills","title":"niw-skills","description":"Open-source plugin for U.S. EB-2 National Interest Waiver (NIW) case work. Honest pre-filing legal evaluation of self-petitions under the current USCIS adjudication standard, with the preponderance-of-the-evidence burden applied prong by prong under Matter of Dhanasar. Built for three cohorts: DIY self-petitioners ready to file, prospective applicants 6–24 months out, and master's/PhD students 3–5 years out who want a multi-year roadmap before committing.\n\nKey features:\n\n• Agentic 5-stage conversation — orient → co-design your proposed endeavor → confirm → full evaluation → follow-ups. Adapts to what you know and what you've provided; produces a clean structured memo, not an engineering trace.\n• Citation discipline — every legal rule cites authority inline (Dhanasar, Chawathe, Katigbak, USCIS Policy Manual Vol. 6 Pt. F Ch. 5, and curated AAO decisions).\n• Verdict floor under preponderance — no inflated assessments. No prong is rated \"Strong\" without documented evidence clearing preponderance.\n• Hard anti-hallucination rules — no invented citation counts, grant roles, employer facts, or AAO decision IDs.\n• Achievable case ceiling — beyond the current-state verdict, the plugin produces a roadmap of concrete prerequisite actions and an honest 0–60 month timeline to reach a stronger case.\n• AC21 framing for India/China nationals — surfaces the practical reason most backlogged-country petitioners file NIW: an approved I-140 unlocks indefinite H-1B extension under AC21 § 104(c) and § 106(a).\n• Written for international, ESL-primary, highly-educated users — short sentences, technical terms explained on first use, citations in standard form, no idioms.\n\nFuture skills shipping in this plugin: endeavor-statement drafter, petition-letter drafter, evidence finder, recommendation-letter drafter, RFE/NOID analyzer.\n\nNot legal advice. Not a substitute for licensed immigration counsel. See DISCLAIMER.md.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/thepaperscompany/niw-skills.git"},{"slug":"nerdygeek","title":"nerdygeek","description":"NerdyGeek gives Claude Code a version-aware documentation lookup tool that dynamically discovers official docs for frameworks and libraries, retrieves the most relevant sections, filters noise, and returns structured answers with source links and code examples. It is designed to help coding agents recover from uncertainty quickly and continue working with current documentation instead of stale assumptions.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/docxbox/NerdyGeek.git"},{"slug":"naksha-studio","title":"naksha-studio","description":"A virtual design team for Claude Code, Cursor, Windsurf, Gemini CLI, and Copilot — 18 roles, 32 commands, 11,000+ lines of expert design knowledge. Your agency's design brain, inside your terminal.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Adityaraj0421/naksha-studio.git"},{"slug":"munin-memory","title":"munin-memory","description":"# Munin for Claude Code\n\n> **Munin** is a long-term memory system for developers. Every time you work with Claude Code, Munin remembers your context, decisions, bugs, and solutions — so you never have to repeat yourself.\n\n**Munin** is your project's memory companion, integrated directly into Claude Code. It remembers your project, finds past errors, and suggests solutions based on what you've done before.\n\n---\n\n## Features\n\n### 🤖 Munin Agent\nCall `@munin` in any conversation to talk directly with your project's memory. Munin has full access to your memories — search, retrieve, store — all following the Memory Index Protocol.\n\n### 🔍 Automatic Memory Search\nEvery time you start a Claude Code session, Munin automatically finds relevant memories from your project. No need to ask — context is already there.\n\n### 💾 Session Summarization\nWhen a session ends, Munin automatically saves a summary to memory. Tasks, decisions, bugs — everything is recorded.\n\n### 📚 Error Catalog\nWhen an error occurs, Munin will:\n1. **Search** the error catalog first — a fix might already exist\n2. **Fix** following the precedent\n3. **Store** the new resolution so the next time is faster\n\n### 🧠 GraphRAG Memory\nEvery memory is automatically indexed into a knowledge graph:\n- **Entities** — services, libraries, models are extracted\n- **Relationships** — connections between components are mapped\n- **Semantic search** — find anything using natural language\n\n---\n\n## How It Works\n\n```\nYou open Claude Code\n│\n▼\nSessionStart Hook\n→ Munin searches relevant memories\n→ Context injected into conversation\n│\n▼\nYou work on your task\n→ Munin monitors for errors\n→ Errors → Error Catalog\n│\n▼\nSession ends (or /compact)\n→ Summary saved to memory\n│\n▼\nNext session — Munin remembers\n```\n\n---\n\n## Quick Start\n\n### 1. Create a Free Munin Account\n\nSign up at [munin.kalera.app](https://munin.kalera.app) — FREE FOREVER.\n\nAfter signing up, create a new project and copy your **Project ID** (`proj_xxxxxxxxxxxx`).\n\n### 2. Add Your Project ID\n\nCreate or edit `.env` in your project root:\n\n```bash\nMUNIN_PROJECT=proj_your_project_id\n```\n\n### 3. Enable the MCP Server\n\n**Option A — Global (recommended, works in any project):**\n```bash\n# Download the Munin MCP wrapper\ncurl -fsSL https://raw.githubusercontent.com/3d-era/munin/main/scripts/munin-mcp-wrapper.sh \\\n-o ~/.claude/munin-mcp-wrapper.sh\nchmod +x ~/.claude/munin-mcp-wrapper.sh\n\n# Enable globally\nclaude mcp add --scope user munin bash ~/.claude/munin-mcp-wrapper.sh\n```\n\n**Option B — Project-specific:**\n```bash\nclaude mcp add --scope project munin bash -c '\nENV_FILE=\"$(pwd)/.env\"\nif [[ -f \"$ENV_FILE\" ]]; then\nwhile IFS=\"=\" read -r key rest; do\n[[ \"$key\" =~ ^[[:space:]]*# ]] && continue\n[[ -z \"$key\" ]] && continue\nkey=$(echo \"$key\" | sed \"s/^[[:space:]]*//;s/[[:space:]]*$//\")\nvalue=$(echo \"$rest\" | sed \"s/^[[:space:]]*//;s/#.*$//;s/[[:space:]]*$//\")\n[[ -n \"$value\" ]] && export \"$key=$value\" 2>/dev/null || true\ndone < \"$ENV_FILE\"\nfi\nexec npx @kalera/munin-claude mcp\n'\n```\n\n**Option C — From this repo (development):**\n```bash\nclaude mcp add --scope user munin bash -c '\nPROJECT_DIR=\"${CLAUDE_PROJECT_DIR:-$(pwd)}\"\nENV_FILE=\"$PROJECT_DIR/.env\"\nif [[ -f \"$ENV_FILE\" ]]; then\ngrep -E \"^MUNIN_PROJECT=\" \"$ENV_FILE\" | while IFS=\"=\" read -r key val; do\nexport \"$key=$val\"\ndone\nfi\nexec npx @kalera/munin-claude mcp\n'\n```\n\n### 4. Start Using\n\n```bash\n# Talk to Munin directly\n@munion ask about the SePay integration\n@munion what did we decide about the auth system?\n\n# Or just start working — Munin auto-loads context\n# Munin will remember everything when you finish\n```\n\n---\n\n## Configuration\n\n### Environment Variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `MUNIN_PROJECT` | *(required)* | Your project ID from munin.kalera.app |\n| `MUNIN_BASE_URL` | `https://munin.kalera.dev` | Munin API server |\n| `MUNIN_API_KEY` | *(from dashboard)* | API key for authentication |\n\n### Self-hosted Munin\n\nIf you're running your own Munin instance:\n\n```bash\nMUNIN_BASE_URL=https://your-munin-instance.com \\\nclaude mcp add --scope user munin bash -c \\\n'MUNIN_BASE_URL=\"https://your-munin-instance.com\" exec npx @kalera/munin-claude mcp'\n```\n\n---\n\n## Skills — What Triggers Munin\n\nMunin activates automatically based on context:\n\n| Skill | Triggers | What It Does |\n|-------|----------|--------------|\n| `munin-memory` | \"search memory\", \"remember\", \"find in memory\" | Full memory operations |\n| `munin-architecture` | \"architecture\", \"tech stack\", \"system design\" | Architecture context |\n| `munin-error-catalog` | \"bug\", \"error\", \"crash\", \"doesn't work\" | Error resolution |\n\n---\n\n## Memory Protocol — How Munin Works\n\n### At Task Start\n1. `munin_search_memories` with keywords relevant to the task\n2. `munin_retrieve_memory` for detailed context\n3. Present findings — **verify from memory, don't guess**\n\n### At Task End\n`munin_store_memory` with:\n- **title**: Concise summary (max 80 chars)\n- **content**: Details including file paths, decisions, outcomes\n- **tags**: Categories (`task`, `architecture`, `bug-fix`, etc.)\n\n### On Bug Fixes\n1. Search error catalog first\n2. Present existing fix if found\n3. Fix and **store the new resolution**\n\n### On Decisions\nTag as `architecture` + `decision`, include timeline/version\n\n---\n\n## Pricing\n\n| Plan | Price | Memories | Projects |\n|------|-------|----------|----------|\n| **Free** | $0 | 500 | 3 |\n| Pro | $9/mo | Unlimited | Unlimited |\n| Team | $29/mo | Unlimited | Unlimited |\n\n**[Sign up at munin.kalera.app →](https://munin.kalera.app)**\n\n---\n\n## Resources\n\n| Resource | Link                                                                                           |\n|----------|------------------------------------------------------------------------------------------------|\n| 🌐 **Website** | [munin.kalera.app](https://munin.kalera.app)                                                   |\n| 📖 **Docs** | [munin.kalera.app/docs](https://munin.kalera.app/docs)                                         |\n| 💬 **Discord** | Coming soon                                                                                    |\n| 🐛 **Issues** | [github.com/3d-era/munin-for-agents/issues](https://github.com/3d-era/munin-for-agents/issues) |\n| 📦 **npm** | [npmjs.com/package/@kalera/munin-claude](https://npmjs.com/package/@kalera/munin-claude)       |\n| 🔌 **Gemini Extension** | [github.com/3d-era/munin-gemini-extension](https://github.com/3d-era/munin-gemini-extension)   |\n\n---\n\n## License\n\nMIT — [github.com/3d-era/munin-for-agents](https://github.com/3d-era/munin-for-agents)","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"3d-era/munin-for-agents"},{"slug":"msds-chain","title":"msds-chain","description":"Chemical safety intelligence for AI-assisted experiment design. 18 MCP tools for pairwise compatibility checks, GHS hazard analysis, PPE recommendations, storage guidance, waste disposal, mixing order safety, occupational exposure limits, transport classification, multi-region regulatory compliance (EU/US/CN/JP/KR/CA/AU/TW), safer alternatives, protocol text parsing, SDS section lookup, and signed audit reports. Supports 4,200+ chemicals in 5 languages.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/littleblakew/msds-chain-mcp.git"},{"slug":"mirror","title":"mirror","description":"Mirror turns Claude into a psychological astrologer. Instead of listing transits and placements like a textbook, it conducts a multi-phase interactive reading — gathering birth data, calculating natal charts and transits via parallel agents,\nsynthesizing everything into one narrative, delivering a concise portrait, then shifting into real conversation using the OARS therapeutic framework. It handles sect-aware interpretation, dispositor trees, three-layer Chiron analysis, shadow\nmaterial, and honest temporal framing with real dates. The skill is designed to make people feel genuinely seen, not generically described.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/AvyanshKatiyar/mirror.git"},{"slug":"memory-bank","title":"memory-bank","description":"memory-bank is a Claude Code plugin that helps maintain project context across sessions by keeping a structured memory-bank/ directory of Markdown files.\n\nIt is designed to:\n\nInitialize a standard set of memory bank docs for a project.\nKeep context current as work evolves.\nRemind/block stopping when project files changed but the memory bank has not been updated.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/cjgl23/claude-memory-bank-plugin.git"},{"slug":"meeting-bots","title":"meeting-bots","description":"A panel of AI personas that debate your decisions inside Claude Code. 3 to 10 participants across 5 teams (dev, design, product, business, life), 3 rounds of parallel debate, and a user-centric synthesis from the Boss. The full debate is recorded to a markdown file while the console stays clean.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/karl-cta/meeting-bots.git"},{"slug":"mcp-server-guide","title":"mcp-server-guide","description":"Build apps, clone websites, and implement Figma designs through Anima Playground. Describe what you want, paste a website URL, or drop in a Figma link. Anima handles design, code generation, database, and hosting. Publish to a live URL. Crate in parallel variant creation for rapid prototyping.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/AnimaApp/mcp-server-guide.git"},{"slug":"marketing-for-life-sciences","title":"marketing-for-life-sciences","description":"A life sciences adaptation of the marketing plugin for pharmaceutical, biotech, and medtech teams. Extends the full general marketing toolkit with regulatory compliance (FDA/EMA), MLR review workflows, HCP engagement, KOL strategy, congress marketing, and pharma-specific KPIs. Designed primarily for Cowork, also compatible with Claude Code.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"RationalEyes/claude-business-plugins"},{"slug":"mapbox--community","title":"mapbox","description":"Comprehensive AI skills that teach Claude Code how to build fast, beautiful, and secure Mapbox applications. Specialized skills covering geospatial operations, cartographic design, web performance, search integration, framework patterns (React/Vue/Svelte/Angular/Next.js),   mobile development (iOS/Android), platform migration (MapLibre, Google Maps), token security, and MCP agent patterns. Includes MCP server integration for style management, geocoding, and map previews.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"mapbox/mapbox-agent-skills"},{"slug":"maister","title":"maister","description":"Structured, standards-aware SDLC orchestration for Claude Code — 5 workflow types, 23 agents, 15+ skills, visual companion server for product design.","developer":null,"category":"development","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"SkillPanel/maister"},{"slug":"magicpath","title":"magicpath","description":"Search, preview, inspect, and install MagicPath UI components from Claude Code via the magicpath-ai CLI. Supports MagicPath design system themes.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/MagicPathAI/agent-skills.git"},{"slug":"magician","title":"magician","description":"Comprehensive software development lifecycle plugin that takes task from the idea to merged PR autonomously. Core capabilities:\n\n1. Dynamic Project Inspector\n\nOn every session start, it scans your project files (package.json, go.mod, Cargo.toml, pom.xml, etc.) and auto-assembles targeted knowledge (\"lore\") for every detected technology — no manual stack selection needed. Polyglot stacks get full coverage automatically.\n\n2. Full Autonomous SDLC (/manifest)\n\nOne command drives the entire flow with only 4 human approval gates:\n\n* /conjure — design dialogue (with an ability to strictly use design) → approved spec\n* /blueprint — implementation plan with parallelism map\n* /portal — git worktree isolation\n* /orchestrate + /ward — parallel agents with TDD\n* /certify — tests + types + linter + browser verification\n* /scrutinize → /absorb — multi-agent code review + integration\n* /seal — PR creation, loops until merged\n\n3. Self-Learning\n\nA Stop hook (chronicle-stop.sh) captures git diffs at session end, writes entries to a chronicle, and detects repeated patterns. After 3 occurrences, it offers to codify the pattern as a reusable skill via /inscribe.\n\n4. Team Memory Workspace\n\n.workspace/shared/ (git-committed, team-visible) holds context, roadmap, specs, and post-mortems. .workspace/local/ (gitignored) holds personal prefs and session state.\n\n5. Security Infrastructure\n\n* Hard deny rules in settings.json blocking pipe-to-shell, eval, credential access\n* sentinel-guard.sh PreToolUse hook scanning every Bash command for injection patterns\n* magician-scan standalone CLI for CI pipelines\n* /sentinel skill for full OWASP Top 10 + credential + injection audits\n\nSkill Set (20 skills)\n\nCovers: debugging (/unravel), performance (/accelerate), incident analysis (/autopsy), CI/CD (/deploy), security (/sentinel), and meta-tooling (/inscribe).","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Alexander-Tyagunov/magician.git"},{"slug":"lorkinsey","title":"lorkinsey","description":"Structured product thinking sessions modeled after YC office hours. Helps you stress-test new ideas, product directions, and \"is this worth building\" decisions through research-backed interrogation — not cheerleading. Anti-sycophantic by design: takes positions, challenges assumptions, and demands specifics before letting you move forward.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Lorhard/lorkinsey.git"},{"slug":"llm-wiki-plugin","title":"llm-wiki-plugin","description":"Build and maintain an LLM-curated personal knowledge base in your project. Implements Andrej Karpathy's LLM Wiki pattern with sharded indexes, atomic pages, BM25 search, and a structural lint script - designed to scale to thousands of pages without becoming a context bottleneck.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/praneybehl/llm-wiki-plugin.git"},{"slug":"llm-secure-patterns","title":"llm-secure-patterns","description":"Secure design patterns for Claude Code LLM applications: external content ingestion, endpoint hardening, output validation, system prompt design, and multi-agent action surface control. Maps to OWASP Top 10 for LLM Applications 2025.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/wildblue-ai/llm-secure-patterns.git"},{"slug":"license-plate-recognizer","title":"license-plate-recognizer","description":"Chompute License Plate Recognizer lets Claude read license plates from authorized vehicle images and return structured recognition results. It is designed for support, logistics, parking, access-control, fleet operations, and internal review workflows where the user is authorized to process the image.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"dragonfruit-ai/skills"},{"slug":"learn","title":"learn","description":"Research any topic online and create comprehensive learning guides with RAG-optimized indexes for your AI agents. `/learn react hooks` searches the web for ~20 sources, scores each on a 100-point scale across authority (3x), recency (2x), depth (2x), examples (2x), and uniqueness (1x), fetches only high-scoring sources, and writes a synthesized guide to `agent-knowledge/<topic>.md` with companion `resources/<topic>-sources.json` containing full source metadata. Six-stage methodology: progressive discovery, quality scoring, just-in-time extraction, synthesis, source citation, RAG optimization. Output shape designed for ingestion by Claude Code, OpenCode, and Codex agent-knowledge libraries.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/agent-sh/learn.git"},{"slug":"leader-as-coach","title":"leader-as-coach","description":"A 6-month AI coaching development programme that teaches managers to lead as coaches. 24 weekly coaching models, practical tools, and a 15-question diagnostic. By Leadership by Design.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/LBD-DASH/leader-as-coach.git"},{"slug":"larch","title":"larch","description":"Larch is a multi-agent workflow automation plugin for Claude Code that orchestrates the full software development lifecycle — from design through merge — using collaborative AI agents. It provides six slash commands (/design, /implement, /review, /research, /loop-review, /alias) that coordinate up to 5 parallel agents (Claude subagents + Codex + Cursor) with a voting-based review system to adjudicate findings. Key features include: diverge-then-converge design planning where independent agents propose architectures before anchoring bias can set in; multi-round code review with a 3-agent voting panel (YES/NO/EXONERATE) that accepts or rejects each finding; end-to-end automation from feature design through PR creation, CI monitoring, Slack announcements, and merge; a reviewer competition scoring system that tracks finding quality; and systematic whole-repo review via partitioned slices. External tools (Codex, Cursor, Slack) are optional — the plugin degrades gracefully when they're unavailable.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/zhupanov/larch.git"},{"slug":"laravel-api-tool-kit","title":"laravel-api-tool-kit","description":"Production-grade rules and workflows for Laravel REST APIs built with essa/api-tool-kit. Teaches your AI assistant the\nexact patterns used in the package — so every controller, resource, action, filter, enum, and test it generates matches\nyour architecture from the first draft.\n\nIncludes 21 rule files covering models, controllers, requests, resources, actions, DTOs, filters, enums, repositories,\nevents, authorization, testing, database transactions, DDD structure, and anti-patterns.\n\nIncludes 8 guided workflows: build a full CRUD endpoint step by step, add filtering to an existing model, run a\ndefense-oriented code review, debug issues with data before code, test endpoints with curl and cross-reference against\nthe DB, and manage a per-project knowledge base.\n\nSupports both standard Laravel structure and Domain-Driven Design. Installs in one command: php artisan\napi-skill:install  Production-grade rules and workflows for Laravel REST APIs built with essa/api-tool-kit. Teaches your AI assistant the\nexact patterns used in the package — so every controller, resource, action, filter, enum, and test it generates matches\nyour architecture from the first draft.\n\nIncludes 21 rule files covering models, controllers, requests, resources, actions, DTOs, filters, enums, repositories,\nevents, authorization, testing, database transactions, DDD structure, and anti-patterns.\n\nIncludes 8 guided workflows: build a full CRUD endpoint step by step, add filtering to an existing model, run a\ndefense-oriented code review, debug issues with data before code, test endpoints with curl and cross-reference against\nthe DB, and manage a per-project knowledge base.\n\nSupports both standard Laravel structure and Domain-Driven Design. Installs in one command: php artisan\napi-skill:install","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/ahmedesa/laravel-api-tool-kit.git"},{"slug":"kicad-happy","title":"kicad-happy","description":"KiCad electronics design skills. Analyze schematics, review PCB layouts, download datasheets, source components, and prep boards for fabrication.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/aklofas/kicad-happy.git"},{"slug":"khaki-sketcher","title":"khaki-sketcher","description":"Multi-model orchestration for cross-validated development. Codex reasons, Gemini sees, Sonnet builds. Think → Design → Build → Verify workflow with 8 skills (plan, run, complex-debug, architecture, ui-redesign, visual-qa, code-review, test) and 3  specialized agents (architect, debugger, vision-analyst). Artifact-based context bridging enables seamless handoffs between models.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/KhakiSkech/KhakiSketcher.git"},{"slug":"keynot","title":"keynot","description":"A Claude Code skill that turns any prompt into a polished, self-contained HTML slide deck — keyboard navigation, swipe, fullscreen, animated reveals, brand-accurate design. Single file. Opens anywhere. No runtime dependencies.\n\nBuilt for the moment you need to present something and you don't want to open PowerPoint.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/shawnzam/keynot.git"},{"slug":"karimo-harness-engineering-agent-orchestration","title":"karimo-harness-engineering-agent-orchestration","description":"Harness engineering framework for Claude Code — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent teams, tuned for developers and designers shipping real features. Phased adoption from PRD execution to automated review, code review, and CI-friendly agent teams","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/opensesh/KARIMO.git"},{"slug":"juicify","title":"juicify","description":"Turn experience into reusable insight. Two  complementary skills: skill-juice extracts design philosophy, system patterns,  and engineering techniques from any skill through a 6-lens analysis framework; work-juice crystallizes completed work cycles  into structured case study reports with generalizable lessons learned.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/hminnnnnn/juicify.git"},{"slug":"jp-web-design-guardrails","title":"jp-web-design-guardrails","description":"Guardrails for building Japanese-ready web interfaces. Automatically enforces correct CJK typography (font stacks, line-height, kinsoku shori), Japanese form conventions (furigana fields, postal code auto-fill, Imperial era dates, confirmation screens), honorific-aware UX copy, seasonal color themes, accessibility (JIS X 8341-3), and production-ready CSS. Prevents common mistakes like using italic for emphasis, wrong name field order, and loading full CJK font files.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/mrslbt/jp-web-design-guardrails.git"},{"slug":"job-hunt-skills","title":"job-hunt-skills","description":"Practical AI-assisted skills, prompts, guides, and templates to give you an edge in your job search. Open source and free — designed to work with the AI subscription you already pay for.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-14T06:00:00.309Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Remotivated/job-hunt-skills.git"}],"total":268,"page":4,"per_page":36,"observed_at":"2026-10-14T06:00:00.309Z","source_counts":{"web":341,"demo":13,"skills":5,"official":315,"community":2283,"knowledge-work":123}}