{"id":38171385,"url":"https://github.com/zot24/skills","last_synced_at":"2026-06-06T03:01:20.969Z","repository":{"id":332596044,"uuid":"1134228559","full_name":"zot24/skills","owner":"zot24","description":null,"archived":false,"fork":false,"pushed_at":"2026-05-28T19:05:56.000Z","size":5023,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-28T21:08:06.001Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zot24.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-14T12:36:47.000Z","updated_at":"2026-05-28T19:06:00.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/zot24/skills","commit_stats":null,"previous_names":["zot24/claude-plugins","zot24/skills"],"tags_count":60,"template":false,"template_full_name":null,"purl":"pkg:github/zot24/skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zot24%2Fskills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zot24%2Fskills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zot24%2Fskills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zot24%2Fskills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zot24","download_url":"https://codeload.github.com/zot24/skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zot24%2Fskills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33967641,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-06T02:00:07.033Z","response_time":107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-01-16T23:27:10.881Z","updated_at":"2026-06-06T03:01:20.962Z","avatar_url":"https://github.com/zot24.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI Agent Skills\n\nAn opinionated selection of skills for daily dev workflows.\n\n**Agent Skills Compatible** - All skills follow the [Agent Skills](https://agentskills.io) open format specification.\n\n## Available Skills\n\n| Skill | Description |\n|-------|-------------|\n| [umbrel-app](./skills/umbrel-app) | Expert assistant for developing, packaging, testing, and submitting apps for umbrelOS |\n| [claude-code-expert](./skills/claude-code-expert) | Comprehensive Claude Code \u0026 Anthropic ecosystem knowledge. Official patterns for agents, skills, hooks, commands, MCP. |\n| [agent-browser](./skills/agent-browser) | Expert on agent-browser - Vercel's headless browser automation CLI for AI agents with 50+ commands, snapshots, and multi-session support |\n| [chat-sdk](./skills/chat-sdk) | Expert on Chat SDK - Vercel's open-source template for building production-ready AI chatbots with generative UI, artifacts, and multi-provider support |\n| [ai-sdk](./skills/ai-sdk) | Expert on AI SDK - Vercel's TypeScript toolkit for building AI applications with unified LLM API, streaming, tool calling, and agents |\n| [agent-skills](./skills/agent-skills) | Expert at the Agent Skills open format for extending AI agent capabilities - create, validate, and understand SKILL.md files |\n| [hermes](./skills/hermes) | Expert at understanding and working with Hermes Agent - its memory system, skills, cron jobs, tools, and behavioral conventions |\n| [honcho](./skills/honcho) | Expert on Honcho — AI-native memory and context platform for LLM applications with persistent memory, user modeling, and context management |\n| [safe-delete](./skills/safe-delete) | Prevents catastrophic file deletion by transforming rm commands to trash and blocking dangerous patterns like `rm -rf /` |\n| [x-engagement](./skills/x-engagement) | Crafts high-engagement X (Twitter) content using conversation hijacking, authority building, and strategic hooks |\n| [gh-issue-tracker](./skills/gh-issue-tracker) | Install, configure, and manage gh-issue-tracker — lightweight error tracking that creates GitHub Issues with deduplication, fingerprinting, and rate limiting |\n| [firecrawl](./skills/firecrawl) | Expert on Firecrawl — web scraping, crawling, search, and browser automation API for AI agents with clean LLM-ready output |\n| [servarr](./skills/servarr) | Deploy, configure, and manage the full media stack — Sonarr, Radarr, Lidarr, Prowlarr, Plex, Overseerr, qBittorrent, Bazarr, and Recyclarr |\n| [obsidian](./skills/obsidian) | Manage and optimize Obsidian vaults — organization, Dataview, Templater, workflows, MCP integration, plugins, sync, and publishing |\n| [adguard](./skills/adguard) | Deploy, configure, and manage AdGuard Home — network-wide DNS ad blocking, filtering, DHCP, client management, and REST API automation |\n| [immich](./skills/immich) | Deploy, configure, and manage Immich — self-hosted photo and video management with machine learning, facial recognition, mobile backup, and REST API |\n| [glinet](./skills/glinet) | Configure and manage GL.iNet routers — VPN, AdGuard Home, DNS, multi-WAN failover, drop-in gateway, firewall, and network modes |\n| [umami](./skills/umami) | Deploy, configure, and manage Umami — open-source privacy-focused web analytics with API client, tracker, events, statistics, and reports |\n\n## Installation\n\n### Recommended: install with zskills (Rust CLI package manager)\n\n[`zskills`](https://github.com/zot24/zskills) is a Rust package manager built specifically for managing Claude Code skills — declarative install, multi-marketplace, atomic settings.json round-trip.\n\n```bash\ncargo install --git https://github.com/zot24/zskills\n\nzskills marketplace add zot24/skills\nzskills install umbrel-app servarr immich    # name resolution is unambiguous\n```\n\nDeclarative `skills.toml` in any repo or in `~/.config/zskills/`:\n\n```toml\n[[skills]]\nname = \"umbrel-app\"\nmarketplace = \"zot24-skills\"\n\n[[skills]]\nname = \"servarr\"\nmarketplace = \"zot24-skills\"\n```\n\n```bash\nzskills sync                  # idempotent, applies the manifest\nzskills sync --dry-run        # preview changes first\n```\n\n### Inside Claude Code (built-in)\n\n```bash\n/plugin marketplace add zot24/skills\n/plugin install umbrel-app@zot24-skills\n```\n\n### Or add to project settings manually\n\n`.claude/settings.json`:\n\n```json\n{\n  \"extraKnownMarketplaces\": {\n    \"zot24-skills\": {\n      \"source\": { \"source\": \"github\", \"repo\": \"zot24/skills\" }\n    }\n  },\n  \"enabledPlugins\": {\n    \"umbrel-app@zot24-skills\": true\n  }\n}\n```\n\n## Usage\n\nOnce installed, you can use skills via **slash commands** or **natural language**.\n\n### Slash Commands\n\nFormat: `/skill-name:command-name [arguments]`\n\n```bash\n# Umbrel app development\n/umbrel-app:umbrel scaffold my-app        # Create new app structure\n/umbrel-app:umbrel validate ./my-app      # Validate app configuration\n/umbrel-app:umbrel convert ./docker-app   # Convert Docker Compose to Umbrel\n/umbrel-app:umbrel pr ./my-app            # Generate PR submission\n/umbrel-app:umbrel debug ./my-app         # Troubleshoot issues\n\n# Claude Code expertise\n/claude-code-expert:claude create agent    # Guide for creating agents\n/claude-code-expert:claude create skill    # Guide for creating skills\n/claude-code-expert:claude validate ./x    # Validate against best practices\n/claude-code-expert:claude features        # Show Claude Code capabilities\n\n# Agent browser automation\n/agent-browser:agent-browser open \u003curl\u003e    # Open a webpage\n/agent-browser:agent-browser snapshot      # Get element refs\n/agent-browser:agent-browser click @e2     # Click by ref\n/agent-browser:agent-browser screenshot    # Capture viewport\n\n# Hermes Agent\n/hermes:hermes memory                    # How Hermes memory works\n/hermes:hermes skills                    # How to create Hermes skills\n/hermes:hermes cron                      # Cron job configuration\n\n# Honcho memory platform\n/honcho:honcho quickstart                # Get started with Honcho\n/honcho:honcho context                   # Context retrieval for LLMs\n/honcho:honcho sdk                       # SDK reference\n\n# Safe delete\n/safe-delete:safe-delete enable          # Enable trash-based deletion\n/safe-delete:safe-delete status          # Check current mode\n\n# Firecrawl web scraping\n/firecrawl:firecrawl scrape https://example.com  # Scrape a page\n/firecrawl:firecrawl search \"AI news\"            # Web search\n/firecrawl:firecrawl crawl https://docs.site.com # Crawl a site\n/firecrawl:firecrawl mcp                         # MCP server setup\n\n# Media stack management\n/servarr:servarr setup docker      # Full Docker stack\n/servarr:servarr integrate         # Wire up all apps\n/servarr:servarr profiles          # TRaSH quality profiles\n/servarr:servarr remote            # Laptop→NAS setup\n\n# Immich photo management\n/immich:immich setup                  # Docker Compose deployment\n/immich:immich backup                 # Database + filesystem backup\n/immich:immich library /mnt/photos    # External library setup\n/immich:immich upload /path/to/photos # CLI bulk upload\n```\n\n### Natural Language\n\nYou can also just describe what you want:\n\n```\n\"Create an Umbrel app for my Docker project\"\n\"Help me package this for umbrelOS\"\n\"How do I create a Claude Code agent?\"\n\"What are the best practices for hooks?\"\n\"Automate browser login with agent-browser\"\n\"How do I use snapshots for element selection?\"\n\"Add persistent memory to my LLM agent with Honcho\"\n\"How do I get user context from Honcho for my chatbot?\"\n\"Write a viral X/Twitter post about AI\"\n\"Set up a safe delete alias so I don't accidentally delete everything\"\n```\n\nThe skills auto-activate based on context.\n\n## Skill Details\n\n### umbrel-app\n\nFull lifecycle support for Umbrel app development:\n\n- **scaffold** - Generate complete app structure\n- **validate** - Check against 20+ requirements\n- **convert** - Transform Docker Compose to Umbrel format\n- **pr** - Generate submission-ready PR content\n- **debug** - Troubleshoot issues\n- **sync/diff** - Stay updated with upstream docs\n\n```bash\n/umbrel-app:umbrel scaffold my-app\n/umbrel-app:umbrel validate ./my-app\n```\n\n[Full documentation](./skills/umbrel-app/README.md)\n\n### claude-code-expert\n\nComprehensive Claude Code and Anthropic ecosystem knowledge:\n\n- **create agent/skill/hook/command** - Official patterns and guidance\n- **validate** - Check artifacts against official checklists\n- **patterns** - Browse available creation patterns\n- **features** - Learn about Claude Code capabilities\n- **sync/check** - Keep documentation up to date\n\n```bash\n/claude-code-expert:claude create agent\n/claude-code-expert:claude create skill\n/claude-code-expert:claude validate ./my-agent\n/claude-code-expert:claude features\n```\n\n[Full documentation](./skills/claude-code-expert/README.md)\n\n### agent-browser\n\nExpert on Vercel's browser automation CLI for AI agents:\n\n- **open** - Navigate to webpages\n- **snapshot** - Get accessibility tree with element refs\n- **click/fill/type** - Interact with elements by ref\n- **screenshot** - Capture viewport or full page\n- **session** - Manage isolated browser instances\n- **network** - Intercept and mock requests\n- **sync/diff** - Stay updated with upstream docs\n\n```bash\n/agent-browser:agent-browser open https://example.com\n/agent-browser:agent-browser snapshot -i\n/agent-browser:agent-browser click @e2\n/agent-browser:agent-browser screenshot page.png\n```\n\n[Full documentation](./skills/agent-browser/README.md)\n\n### chat-sdk\n\nExpert on Vercel's Chat SDK for building production-ready AI chatbots:\n\n- **setup** - Installation and project scaffolding\n- **providers** - Configure OpenAI, Anthropic, Google, and other LLM providers\n- **ui** - Build generative UI with artifacts\n- **streaming** - Implement streaming responses\n- **tools** - Define and use tools with LLMs\n- **sync/diff** - Stay updated with upstream docs\n\n[Full documentation](./skills/chat-sdk/README.md)\n\n### ai-sdk\n\nExpert on Vercel's AI SDK - TypeScript toolkit for building AI applications:\n\n- **providers** - Unified API across 100+ LLMs\n- **streaming** - Streaming text, audio, and image generation\n- **tool calling** - Structured tool definitions and execution\n- **agents** - Build autonomous agents with memory\n- **rags** - Retrieval augmented generation patterns\n- **sync/diff** - Stay updated with upstream docs\n\n[Full documentation](./skills/ai-sdk/README.md)\n\n### agent-skills\n\nExpert at the Agent Skills open format specification:\n\n- **create** - Create new SKILL.md files following the spec\n- **validate** - Validate skills against the specification\n- **spec** - Understand the Agent Skills format\n- **best-practices** - Authoring guidelines and patterns\n- **integrate** - Add skills to your agent\n- **sync/diff** - Stay updated with upstream docs\n\n```bash\n/skills-ref validate ./skills/my-skill\n```\n\n[Full documentation](./skills/agent-skills/README.md)\n\n### hermes\n\nExpert at understanding and configuring Hermes Agent:\n\n- **memory** - Dual-store memory, Honcho profiles, instruction capture\n- **skills** - How skills are created, triggered, and structured\n- **cron** - Schedule formats, delivery targets, scheduler architecture\n- **tools** - Built-in tool categories and capabilities\n- **config** - Configuration files and environment variables\n- **conventions** - Communication style and user preferences\n\n```bash\n/hermes:hermes memory\n/hermes:hermes skills\n/hermes:hermes cron\n```\n\n[Full documentation](./skills/hermes/README.md)\n\n### honcho\n\nExpert on Honcho — AI-native memory and context platform for LLM applications:\n\n- **quickstart** - Setup and first API calls\n- **architecture** - Core data model (workspaces, peers, sessions)\n- **context** - Retrieve context for LLM injection\n- **peers** - Working with peer representations\n- **dreaming** - Autonomous memory consolidation\n- **sdk** - Python and TypeScript SDK reference\n- **api** - Full REST API reference\n- **integrate** - Guides for Claude Code, MCP, LangGraph, Discord, Telegram, and more\n- **sync/diff** - Stay updated with upstream docs\n\n```bash\n/honcho:honcho quickstart\n/honcho:honcho context\n/honcho:honcho sdk\n/honcho:honcho integrate discord\n```\n\n[Full documentation](./skills/honcho/README.md)\n\n### safe-delete\n\nPrevents catastrophic file deletion by intercepting dangerous rm commands:\n\n- **enable** - Activate trash-based deletion (aliases rm to trash-cli)\n- **block** - Block patterns like `rm -rf /` or `rm -rf /*`\n- **whitelist** - Allow specific directories to be deleted\n- **status** - Show current protection state\n- **restore** - Recover files from trash\n\n```bash\n/safe-delete:safe-delete enable\n/safe-delete:safe-delete status\n```\n\n[Full documentation](./skills/safe-delete/README.md)\n\n### x-engagement\n\nCrafts high-engagement X (Twitter) content using strategic frameworks:\n\n- **hook** - Write viral-worthy opening hooks\n- **authority** - Build authority through strategic content\n- **conversation** - Hijack trending conversations\n- **thread** - Write viral threads\n- **draft** - Generate engagement-optimized posts\n\n```bash\n/x-engagement:x-engagement hook \"AI agents\"\n/x-engagement:x-engagement thread \"Why most AI projects fail\"\n```\n\n[Full documentation](./skills/x-engagement/README.md)\n\n### firecrawl\n\nExpert on Firecrawl web scraping, crawling, and data extraction API:\n\n- **scrape** - Extract markdown/HTML/JSON from a single URL\n- **search** - Query-based web discovery with content extraction\n- **crawl** - Recursively gather content from entire sites\n- **map** - Discover all URLs on a website\n- **interact** - Browser automation (clicks, forms, navigation)\n- **extract** - LLM-powered structured data extraction\n- **sdk** - Node, Python, Go, Rust SDK reference\n- **mcp** - MCP server setup for Claude/Cursor\n- **sync/diff** - Stay updated with upstream docs\n\n```bash\n/firecrawl:firecrawl scrape https://example.com\n/firecrawl:firecrawl search \"AI news\"\n/firecrawl:firecrawl crawl https://docs.example.com\n```\n\n[Full documentation](./skills/firecrawl/README.md)\n\n### servarr\n\nDeploy and manage the complete media automation stack:\n\n- **setup** - Docker Compose for full stack (9 services)\n- **configure** - App-specific configuration guides\n- **api** - API usage with curl examples for all apps\n- **integrate** - Wire up Prowlarr → *arr apps → qBittorrent → Plex\n- **profiles** - TRaSH quality profiles via Recyclarr\n- **status** - Health check all running instances\n- **troubleshoot** - Diagnose common issues\n- **add** - Add movies/shows/artists via API\n- **request** - Overseerr request workflow\n- **remote** - Laptop→NAS management patterns\n\n```bash\n/servarr:servarr setup docker\n/servarr:servarr integrate\n/servarr:servarr add movie \"Inception\"\n/servarr:servarr remote\n```\n\n[Full documentation](./skills/servarr/README.md)\n\n### immich\n\nDeploy and manage Immich, a self-hosted photo and video management solution:\n\n- **setup** - Docker Compose deployment guide\n- **configure** - Environment variables and settings\n- **backup** - Database and filesystem backup/restore\n- **library** - External library setup for existing photo directories\n- **upload** - CLI bulk upload with album creation\n- **api** - REST API usage with curl examples\n- **ml** - Machine learning configuration (CLIP, faces, OCR)\n- **mobile** - Mobile app setup and backup\n\n```bash\n/immich:immich setup\n/immich:immich backup\n/immich:immich upload /path/to/photos\n/immich:immich library /mnt/nas/photos\n```\n\n[Full documentation](./skills/immich/README.md)\n\n### glinet\n\nConfigure and manage GL.iNet routers (firmware v4.x):\n\n- **setup** - First time setup and internet configuration\n- **vpn** - WireGuard, OpenVPN, Tailscale client/server\n- **adguard** - Built-in AdGuard Home ad blocking\n- **gateway** - Drop-in gateway for existing networks\n- **dns** - Encrypted DNS (DoH, DoT, DNSCrypt)\n- **multiwan** - Failover and load balancing\n- **firewall** - Port forwarding, DMZ, access control\n- **storage** - USB/Samba/WebDAV/DLNA\n\n```bash\n/glinet:glinet setup\n/glinet:glinet vpn wireguard\n/glinet:glinet adguard\n/glinet:glinet gateway\n```\n\n[Full documentation](./skills/glinet/README.md)\n\n### umami\n\nDeploy and manage Umami, a privacy-focused open-source web analytics platform:\n\n- **setup** — Docker Compose, source, and cloud installation\n- **api** — `@umami/api-client` TypeScript client for all endpoints\n- **track** — Client-side and server-side event tracking\n- **stats** — Website statistics, metrics, and active users\n- **reports** — Attribution, funnel, retention, journey, revenue, UTM\n- **realtime** — Live visitor data\n- **teams** — Team and user management\n\n```bash\n/umami:umami setup\n/umami:umami api getWebsites\n/umami:umami track purchase\n/umami:umami stats \u003cwebsiteId\u003e\n/umami:umami reports funnel\n```\n\n[Full documentation](./skills/umami/README.md)\n\n## Adding New Skills\n\n1. Create a new directory under `skills/`:\n\n   ```\n   skills/\n   └── my-new-skill/\n       ├── .claude-plugin/\n       │   └── plugin.json\n       ├── commands/\n       ├── skills/\n       ├── sync.json           # Required for CI automation\n       └── README.md\n   ```\n\n2. Create `sync.json` for automated updates:\n\n   ```json\n   {\n     \"name\": \"my-new-skill\",\n     \"version\": \"1.0.0\",\n     \"description\": \"What it does\",\n     \"sources\": [\n       {\n         \"url\": \"https://example.com/docs.md\",\n         \"target\": \"skills/my-skill/docs/readme-upstream.md\",\n         \"freshness_days\": 14\n       }\n     ],\n     \"cache_dir\": \".cache\"\n   }\n   ```\n\n3. Add entry to `.claude-plugin/marketplace.json`:\n\n   ```json\n   {\n     \"name\": \"my-new-skill\",\n     \"source\": \"./skills/my-new-skill\",\n     \"description\": \"What it does\",\n     \"version\": \"1.0.0\"\n   }\n   ```\n\n4. Add skill to CI sync array in `.github/workflows/sync-docs.yml` if it has upstream docs\n5. Commit and push\n\n## CI Automation\n\nThe repository includes automated workflows for keeping skill documentation up to date.\n\n### Scheduled Sync\n\nRuns bi-weekly (1st and 15th of each month) to check for upstream documentation changes. Only syncs skills with actual upstream documentation sources.\n\n**Manual trigger**: Actions \u003e Sync Skill Documentation \u003e Run workflow\n\nOptions:\n- `force`: Force sync even without detected changes\n- `dry_run`: Check for changes without creating PR\n\n**Skills with CI sync enabled:**\n- umbrel-app, claude-code-expert, agent-browser, chat-sdk, ai-sdk, agent-skills, hermes, honcho, firecrawl, servarr, obsidian, adguard, immich, glinet, umami\n\n### Automated Releases (release-please)\n\nThis repository uses [release-please](https://github.com/googleapis/release-please) to automate versioning and releases based on [Conventional Commits](https://www.conventionalcommits.org/).\n\n**How it works:**\n\n1. Push commits using conventional format: `feat(skill-name): description`\n2. Release-please detects changes and creates a release PR\n3. The PR updates versions and CHANGELOG automatically\n4. When merged, creates a GitHub release with tag (e.g., `umbrel-app-v1.3.0`)\n\n**Commit types:**\n\n| Prefix | Version Bump | Changelog Section |\n|--------|--------------|-------------------|\n| `feat` | Minor (1.x.0) | Features |\n| `fix` | Patch (1.0.x) | Bug Fixes |\n| `docs` | Patch (1.0.x) | Documentation |\n| `chore` | None | Hidden |\n\n**Configuration files:**\n\n- `release-please-config.json` - Release settings and package definitions\n- `.release-please-manifest.json` - Current versions for each skill\n\n### Configuration\n\nSet custom schedule via repository variable:\n\n```\nSYNC_SCHEDULE: \"0 6 1,15 * *\"  # Cron format\n```\n\n## Structure\n\n```\nskills/\n├── .claude-plugin/\n│   └── marketplace.json          # Marketplace manifest\n├── .github/\n│   ├── scripts/\n│   │   └── sync-skill.sh         # Generic sync script\n│   └── workflows/\n│       ├── sync-docs.yml         # Scheduled sync workflow\n│       └── release-on-merge.yml  # Auto-release on PR merge\n├── skills/\n│   ├── umbrel-app/               # Umbrel app development\n│   ├── claude-code-expert/       # Claude Code knowledge base\n│   ├── agent-browser/            # Browser automation for AI agents\n│   ├── chat-sdk/                 # Vercel Chat SDK\n│   ├── ai-sdk/                   # Vercel AI SDK\n│   ├── agent-skills/             # Agent Skills specification\n│   ├── hermes/                   # Hermes Agent self-knowledge\n│   ├── honcho/                   # Honcho AI-native memory platform\n│   ├── safe-delete/              # Safe file deletion\n│   ├── x-engagement/             # X/Twitter engagement\n│   ├── gh-issue-tracker/         # Error tracking via GitHub Issues\n│   ├── firecrawl/                # Firecrawl web scraping API\n│   ├── servarr/                  # Media stack (*arr suite + Plex)\n│   ├── obsidian/                 # Obsidian vault management\n│   ├── adguard/                  # AdGuard Home DNS filtering\n│   ├── immich/                   # Immich photo/video management\n│   ├── glinet/                   # GL.iNet router management\n│   └── umami/                    # Umami web analytics\n└── README.md\n```\n\n## Agent Skills Compatibility\n\nAll skills in this repository follow the [Agent Skills](https://agentskills.io) open format specification:\n\n| Requirement | Status |\n|-------------|--------|\n| Valid `name` field (lowercase, hyphens) | ✓ |\n| Name matches directory | ✓ |\n| Descriptive `description` with triggers | ✓ |\n| SKILL.md under 500 lines | ✓ |\n| Progressive disclosure pattern | ✓ |\n| References in docs/ folder | ✓ |\n\n### Specification Compliance\n\n- **SKILL.md format**: YAML frontmatter + Markdown body\n- **Progressive disclosure**: Metadata → Instructions → References (docs/)\n- **Directory structure**: `skills/\u003cname\u003e/skills/\u003cname\u003e/SKILL.md`\n- **Token efficiency**: Main skills ~100 lines, detailed docs loaded on-demand\n\n### Validate with skills-ref\n\n```bash\npip install skills-ref\nskills-ref validate ./skills/umbrel-app/skills/umbrel-app\n```\n\nFor more information, see [agentskills.io](https://agentskills.io) or the [agent-skills skill](./skills/agent-skills).\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzot24%2Fskills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzot24%2Fskills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzot24%2Fskills/lists"}