[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CVGYPCWT8GY64F50FN6NZT":3,"skill-same:01M7CVGYPCWT8GY64F50FN6NZT":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7CVGYPCWT8GY64F50FN6NZT","uncloud",null,"Use when managing an Uncloud cluster — deploying services, configuring Caddy ingress, adding static proxy routes for non-cluster devices, publishing ports, scaling, inspecting logs, or managing machines and volumes with the `uc` CLI.","Henrique1601\u002FSkiilsToIAs","Henrique1601","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92006691?v=4","01M7CRXVT0GVXVK80JT1GR687S","Henrique Bezerra Dos Santos","01M7CRXVTN5Y8TMWJ1MDSKCQ1T",0,"MIT","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Funcloud\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: uncloud\ndescription: Use when managing an Uncloud cluster — deploying services, configuring Caddy ingress, adding static proxy routes for non-cluster devices, publishing ports, scaling, inspecting logs, or managing machines and volumes with the `uc` CLI.\nmetadata:\n  origin: ECC\n---\n\n# Uncloud Cluster Management\n\nReference for the `uc` CLI — a decentralised self-hosting platform using Docker containers, WireGuard mesh networking, and Caddy reverse proxy.\n\n## When to Activate\n\nUse this skill when working with Uncloud clusters, especially when:\n- Bootstrapping or joining machines with `uc machine`\n- Deploying services from Compose files with `uc deploy`\n- Publishing HTTP, HTTPS, TCP, or UDP ports through Uncloud\n- Configuring Caddy ingress with `x-caddy`, `x-ports`, or `--caddyfile`\n- Routing external LAN devices through the cluster proxy\n- Inspecting logs, service state, volumes, DNS, or machine placement\n\n## How It Works\n\nUncloud runs Docker services across peer machines connected by a WireGuard mesh. Each machine is an equal cluster member; services communicate on the overlay network and Caddy runs globally to terminate public HTTP\u002FHTTPS traffic. Compose files can use Uncloud extensions for ingress, placement, and generated Caddy configuration, while the `uc` CLI handles image distribution, scheduling, scaling, logs, and cluster state.\n\n## Examples\n\n```bash\nuc machine init user@host --name machine-1\nuc service run --name web -p app.example.com:8080\u002Fhttps nginx:latest\nuc deploy\n```\n\n## Core Concepts\n\n- **No central control plane** — all machines are equal peers connected by WireGuard\n- **Caddy** runs as a global service on every machine; auto-obtains TLS from Let's Encrypt\n- **Overlay network** — services communicate via `10.210.0.0\u002F16` by default; DNS provided inside the mesh\n- **Caddyfile is autogenerated** — never edit it directly; use `x-caddy` \u002F `--caddyfile` instead\n\n---\n\n## CLI Quick Reference\n\n### Machines\n\n| Command | Purpose |\n|---------|---------|\n| `uc machine init user@host` | Bootstrap first machine \u002F new cluster |\n| `uc machine add user@host` | Join machine to existing cluster |\n| `uc machine ls` | List machines |\n| `uc machine update NAME --public-ip IP` | Update public IP for ingress |\n| `uc machine rm NAME` | Remove machine |\n\nKey `init` flags: `--name`, `--network 10.210.0.0\u002F16`, `--no-caddy`, `--no-dns`, `--public-ip auto\\|IP\\|none`\n\n### Services\n\n| Command | Purpose |\n|---------|---------|\n| `uc service ls` \u002F `uc ls` | List services |\n| `uc service run IMAGE` | Run a single container service |\n| `uc deploy` | Deploy from `compose.yaml` |\n| `uc deploy --no-build` | Deploy already-pushed images without rebuilding |\n| `uc deploy --recreate` | Force service recreation |\n| `uc scale SERVICE N` | Set replica count |\n| `uc service logs SERVICE` | View logs |\n| `uc service exec SERVICE` | Shell into container |\n| `uc service inspect SERVICE` | Detailed info |\n| `uc service rm SERVICE` | Remove service (keeps named volumes) |\n| `uc ps` | All containers across cluster |\n\n### Images\n\n```bash\nuc image push myapp:latest                    # Push local image to all machines\nuc image push myapp:latest -m machine1,machine2  # Push to specific machines\nuc images                                     # List images in cluster\n```\n\n### Volumes\n\n```bash\nuc volume ls                  # All volumes\nuc volume ls -m machine1      # On specific machine\nuc volume create NAME -m MACHINE\nuc volume rm NAME\n```\n\n### Caddy\n\n```bash\nuc caddy config    # Show current generated Caddyfile (read-only)\nuc caddy deploy    # Deploy\u002Fupgrade Caddy across cluster\n```\n\n### DNS & Context\n\n```bash\nuc dns show        # Show reserved *.uncld.dev domain\nuc dns reserve     # Reserve a new domain\nuc ctx ls          # List cluster contexts\nuc ctx use prod    # Switch context\n```\n\n---\n\n## Port Publishing\n\n### HTTP\u002FHTTPS (via Caddy reverse proxy)\n\n```\n-p [hostname:]container_port[\u002Fprotocol]\n```\n\n| Example | Meaning |\n|---------|---------|\n| `-p 8080\u002Fhttps` | HTTPS with auto `service-name.cluster-domain` hostname |\n| `-p app.example.com:8080\u002Fhttps` | HTTPS with custom hostname |\n| `-p 8080\u002Fhttp` | HTTP only, no TLS |\n\n### TCP\u002FUDP (host-bound, bypasses Caddy)\n\n```\n-p [host_ip:]host_port:container_port[\u002Fprotocol]@host\n```\n\n| Example | Meaning |\n|---------|---------|\n| `-p 5432:5432@host` | TCP 5432 on all interfaces |\n| `-p 127.0.0.1:5432:5432@host` | TCP 5432 loopback only |\n| `-p 53:5353\u002Fudp@host` | UDP |\n\n---\n\n## Compose File Extensions\n\nUncloud adds these extensions on top of Docker Compose:\n\n### `x-ports` — publish ports with domains\n\n```yaml\nservices:\n  app:\n    image: app:latest\n    x-ports:\n      - example.com:8000\u002Fhttps\n      - www.example.com:8000\u002Fhttps\n      - api.example.com:9000\u002Fhttps\n```\n\n### `x-caddy` — custom Caddy config for service\n\n```yaml\nservices:\n  app:\n    image: app:latest\n    x-caddy: |\n      example.com {\n        redir https:\u002F\u002Fwww.example.com{uri} permanent\n      }\n      www.example.com {\n        reverse_proxy {{upstreams 8000}} {\n          import common_proxy\n        }\n        basic_auth \u002Fadmin\u002F* {\n          admin $2a$14$...\n        }\n      }\n```\n\nTemplate functions available inside `x-caddy`:\n- `{{upstreams [service] [port]}}` — healthy container IPs\n- `{{.Name}}` — service name\n- `{{.Upstreams}}` — map of all services → IPs\n\n### `x-machines` — placement constraints\n\n```yaml\nservices:\n  db:\n    image: postgres:18\n    x-machines: db-machine          # Single machine name\n  app:\n    image: app:latest\n    x-machines:\n      - machine-1\n      - machine-2\n```\n\n### Full multi-service example\n\n```yaml\nservices:\n  api:\n    build: .\u002Fapi\n    x-ports:\n      - api.example.com:3000\u002Fhttps\n    environment:\n      DATABASE_URL: postgres:\u002F\u002Fdb:5432\u002Fmydb\n\n  web:\n    build: .\u002Fweb\n    x-ports:\n      - example.com:8000\u002Fhttps\n      - www.example.com:8000\u002Fhttps\n    environment:\n      API_URL: http:\u002F\u002Fapi:3000\n\n  db:\n    image: postgres:18\n    environment:\n      POSTGRES_PASSWORD: ${DB_PASSWORD}\n    volumes:\n      - db-data:\u002Fvar\u002Flib\u002Fpostgresql\u002Fdata\n    x-machines: db-machine\n\nvolumes:\n  db-data:\n```\n\n---\n\n## Routing to External (Non-Cluster) Devices\n\nTo expose an external device (e.g. BMC, NAS, router UI) via Caddy without running a real container:\n\n**1. Create a Caddyfile snippet** (e.g. `~\u002Fdevice.caddyfile`):\n\n```caddyfile\nhttps:\u002F\u002Fdevice.example.com {\n    reverse_proxy https:\u002F\u002F192.168.1.x {\n        transport http {\n            tls_insecure_skip_verify   # needed for self-signed BMC certs\n        }\n    }\n    log\n}\n```\n\nFor plaintext upstream: `reverse_proxy http:\u002F\u002F192.168.1.x:port`\n\n**2. Register as a named service with no-op container:**\n\n```bash\nuc service run \\\n  --name device-bmc \\\n  --caddyfile ~\u002Fdevice.caddyfile \\\n  registry.k8s.io\u002Fpause:3.9\n```\n\n`pause` is a minimal no-op container — it does nothing, but gives Uncloud a service entry to attach the Caddyfile to.\n\n**3. Verify:**\n\n```bash\nuc caddy config   # device.example.com block should appear\n```\n\n> `--caddyfile` cannot be combined with non-`@host` published ports.\n\n**DNS tip:** A wildcard record (`*.yourdomain.com → cluster-public-ip`) means any new subdomain works immediately — no DNS change needed per service.\n\n---\n\n## Service DNS (Internal)\n\nServices inside the cluster resolve each other by name:\n\n| DNS name | Resolves to |\n|----------|------------|\n| `service-name` | Any healthy container |\n| `service-name.internal` | Same |\n| `rr.service-name.internal` | Round-robin |\n| `nearest.service-name.internal` | Machine-local first |\n\n---\n\n## Scaling & Global Services\n\n```bash\nuc scale web 5    # 5 replicas (spread across machines)\nuc scale web 1    # Scale down\n```\n\n```yaml\nservices:\n  caddy:\n    deploy:\n      mode: global   # One container on every machine\n```\n\n---\n\n## Image Tag Templates (in compose.yaml)\n\n```yaml\nimage: myapp:{{gitdate \"20060102\"}}.{{gitsha 7}}\nimage: myapp:{{gitsha 7}}.${GITHUB_RUN_ID:-local}\n```\n\n| Function | Output |\n|----------|--------|\n| `{{gitsha N}}` | First N chars of commit SHA |\n| `{{gitdate \"format\"}}` | Git commit date in Go format |\n| `{{date \"format\"}}` | Current date |\n\n---\n\n## Common Workflows\n\n**Deploy from source:**\n```bash\nuc deploy                          # Build + push + deploy\nuc build --push && uc deploy --no-build   # Separate steps\n```\n\n**Inspect a service:**\n```bash\nuc inspect web\nuc logs -f web\nuc logs --since 1h web\nuc exec web                        # Opens shell\nuc exec web \u002Fbin\u002Fsh -c \"env\"       # Run specific command\n```\n\n**Zero-downtime deploys** happen automatically; Uncloud waits for health checks before terminating old containers.\n\n**Force recreate:**\n```bash\nuc deploy --recreate\n```\n\n---\n\n## Common Mistakes\n\n| Mistake | Fix |\n|---------|-----|\n| Editing the Caddyfile directly | Use `x-caddy` in compose or `--caddyfile` on `uc service run` |\n| Proxying an HTTPS upstream with self-signed cert | Add `transport http { tls_insecure_skip_verify }` |\n| `uc caddy config` shows no user-defined blocks | Caddy admin socket unreachable — check `uc inspect caddy` and `uc logs caddy` |\n| Service can't reach external LAN IP from container | Verify Caddy container's host can route to target network |\n| Volumes lost after `uc service rm` | Named volumes persist; only anonymous volumes are auto-removed |\n","# Uncloud Cluster Management\n\nReference for the `uc` CLI — a decentralised self-hosting platform using Docker containers, WireGuard mesh networking, and Caddy reverse proxy.\n\n## When to Activate\n\nUse this skill when working with Uncloud clusters, especially when:\n- Bootstrapping or joining machines with `uc machine`\n- Deploying services from Compose files with `uc deploy`\n- Publishing HTTP, HTTPS, TCP, or UDP ports through Uncloud\n- Configuring Caddy ingress with `x-caddy`, `x-ports`, or `--caddyfile`\n- Routing external LAN devices through the cluster proxy\n- Inspecting logs, service state, volumes, DNS, or machine placement\n\n## How It Works\n\nUncloud runs Docker services across peer machines connected by a WireGuard mesh. Each machine is an equal cluster member; services communicate on the overlay network and Caddy runs globally to terminate public HTTP\u002FHTTPS traffic. Compose files can use Uncloud extensions for ingress, placement, and generated Caddy configuration, while the `uc` CLI handles image distribution, scheduling, scaling, logs, and cluster state.\n\n## Examples\n\n```bash\nuc machine init user@host --name machine-1\nuc service run --name web -p app.example.com:8080\u002Fhttps nginx:latest\nuc deploy\n```\n\n## Core Concepts\n\n- **No central control plane** — all machines are equal peers connected by WireGuard\n- **Caddy** runs as a global service on every machine; auto-obtains TLS from Let's Encrypt\n- **Overlay network** — services communicate via `10.210.0.0\u002F16` by default; DNS provided inside the mesh\n- **Caddyfile is autogenerated** — never edit it directly; use `x-caddy` \u002F `--caddyfile` instead\n\n---\n\n## CLI Quick Reference\n\n### Machines\n\n| Command | Purpose |\n|---------|---------|\n| `uc machine init user@host` | Bootstrap first machine \u002F new cluster |\n| `uc machine add user@host` | Join machine to existing cluster |\n| `uc machine ls` | List machines |\n| `uc machine update NAME --public-ip IP` | Update public IP for ingress |\n| `uc machine rm NAME` | Remove machine |\n\nKey `init` flags: `--name`, `--network 10.210.0.0\u002F16`, `--no-caddy`, `--no-dns`, `--public-ip auto\\|IP\\|none`\n\n### Services\n\n| Command | Purpose |\n|---------|---------|\n| `uc service ls` \u002F `uc ls` | List services |\n| `uc service run IMAGE` | Run a single container service |\n| `uc deploy` | Deploy from `compose.yaml` |\n| `uc deploy --no-build` | Deploy already-pushed images without rebuilding |\n| `uc deploy --recreate` | Force service recreation |\n| `uc scale SERVICE N` | Set replica count |\n| `uc service logs SERVICE` | View logs |\n| `uc service exec SERVICE` | Shell into container |\n| `uc service inspect SERVICE` | Detailed info |\n| `uc service rm SERVICE` | Remove service (keeps named volumes) |\n| `uc ps` | All containers across cluster |\n\n### Images\n\n```bash\nuc image push myapp:latest                    # Push local image to all machines\nuc image push myapp:latest -m machine1,machine2  # Push to specific machines\nuc images                                     # List images in cluster\n```\n\n### Volumes\n\n```bash\nuc volume ls                  # All volumes\nuc volume ls -m machine1      # On specific machine\nuc volume create NAME -m MACHINE\nuc volume rm NAME\n```\n\n### Caddy\n\n```bash\nuc caddy config    # Show current generated Caddyfile (read-only)\nuc caddy deploy    # Deploy\u002Fupgrade Caddy across cluster\n```\n\n### DNS & Context\n\n```bash\nuc dns show        # Show reserved *.uncld.dev domain\nuc dns reserve     # Reserve a new domain\nuc ctx ls          # List cluster contexts\nuc ctx use prod    # Switch context\n```\n\n---\n\n## Port Publishing\n\n### HTTP\u002FHTTPS (via Caddy reverse proxy)\n\n```\n-p [hostname:]container_port[\u002Fprotocol]\n```\n\n| Example | Meaning |\n|---------|---------|\n| `-p 8080\u002Fhttps` | HTTPS with auto `service-name.cluster-domain` hostname |\n| `-p app.example.com:8080\u002Fhttps` | HTTPS with custom hostname |\n| `-p 8080\u002Fhttp` | HTTP only, no TLS |\n\n### TCP\u002FUDP (host-bound, bypasses Caddy)\n\n```\n-p [host_ip:]host_port:container_port[\u002Fprotocol]@host\n```\n\n| Example | Meaning |\n|---------|---------|\n| `-p 5432:5432@host` | TCP 5432 on all interfaces |\n| `-p 127.0.0.1:5432:5432@host` | TCP 5432 loopback only |\n| `-p 53:5353\u002Fudp@host` | UDP |\n\n---\n\n## Compose File Extensions\n\nUncloud adds these extensions on top of Docker Compose:\n\n### `x-ports` — publish ports with domains\n\n```yaml\nservices:\n  app:\n    image: app:latest\n    x-ports:\n      - example.com:8000\u002Fhttps\n      - www.example.com:8000\u002Fhttps\n      - api.example.com:9000\u002Fhttps\n```\n\n### `x-caddy` — custom Caddy config for service\n\n```yaml\nservices:\n  app:\n    image: app:latest\n    x-caddy: |\n      example.com {\n        redir https:\u002F\u002Fwww.example.com{uri} permanent\n      }\n      www.example.com {\n        reverse_proxy {{upstreams 8000}} {\n          import common_proxy\n        }\n        basic_auth \u002Fadmin\u002F* {\n          admin $2a$14$...\n        }\n      }\n```\n\nTemplate functions available inside `x-caddy`:\n- `{{upstreams [service] [port]}}` — healthy container IPs\n- `{{.Name}}` — service name\n- `{{.Upstreams}}` — map of all services → IPs\n\n### `x-machines` — placement constraints\n\n```yaml\nservices:\n  db:\n    image: postgres:18\n    x-machines: db-machine          # Single machine name\n  app:\n    image: app:latest\n    x-machines:\n      - machine-1\n      - machine-2\n```\n\n### Full multi-service example\n\n```yaml\nservices:\n  api:\n    build: .\u002Fapi\n    x-ports:\n      - api.example.com:3000\u002Fhttps\n    environment:\n      DATABASE_URL: postgres:\u002F\u002Fdb:5432\u002Fmydb\n\n  web:\n    build: .\u002Fweb\n    x-ports:\n      - example.com:8000\u002Fhttps\n      - www.example.com:8000\u002Fhttps\n    environment:\n      API_URL: http:\u002F\u002Fapi:3000\n\n  db:\n    image: postgres:18\n    environment:\n      POSTGRES_PASSWORD: ${DB_PASSWORD}\n    volumes:\n      - db-data:\u002Fvar\u002Flib\u002Fpostgresql\u002Fdata\n    x-machines: db-machine\n\nvolumes:\n  db-data:\n```\n\n---\n\n## Routing to External (Non-Cluster) Devices\n\nTo expose an external device (e.g. BMC, NAS, router UI) via Caddy without running a real container:\n\n**1. Create a Caddyfile snippet** (e.g. `~\u002Fdevice.caddyfile`):\n\n```caddyfile\nhttps:\u002F\u002Fdevice.example.com {\n    reverse_proxy https:\u002F\u002F192.168.1.x {\n        transport http {\n            tls_insecure_skip_verify   # needed for self-signed BMC certs\n        }\n    }\n    log\n}\n```\n\nFor plaintext upstream: `reverse_proxy http:\u002F\u002F192.168.1.x:port`\n\n**2. Register as a named service with no-op container:**\n\n```bash\nuc service run \\\n  --name device-bmc \\\n  --caddyfile ~\u002Fdevice.caddyfile \\\n  registry.k8s.io\u002Fpause:3.9\n```\n\n`pause` is a minimal no-op container — it does nothing, but gives Uncloud a service entry to attach the Caddyfile to.\n\n**3. Verify:**\n\n```bash\nuc caddy config   # device.example.com block should appear\n```\n\n> `--caddyfile` cannot be combined with non-`@host` published ports.\n\n**DNS tip:** A wildcard record (`*.yourdomain.com → cluster-public-ip`) means any new subdomain works immediately — no DNS change needed per service.\n\n---\n\n## Service DNS (Internal)\n\nServices inside the cluster resolve each other by name:\n\n| DNS name | Resolves to |\n|----------|------------|\n| `service-name` | Any healthy container |\n| `service-name.internal` | Same |\n| `rr.service-name.internal` | Round-robin |\n| `nearest.service-name.internal` | Machine-local first |\n\n---\n\n## Scaling & Global Services\n\n```bash\nuc scale web 5    # 5 replicas (spread across machines)\nuc scale web 1    # Scale down\n```\n\n```yaml\nservices:\n  caddy:\n    deploy:\n      mode: global   # One container on every machine\n```\n\n---\n\n## Image Tag Templates (in compose.yaml)\n\n```yaml\nimage: myapp:{{gitdate \"20060102\"}}.{{gitsha 7}}\nimage: myapp:{{gitsha 7}}.${GITHUB_RUN_ID:-local}\n```\n\n| Function | Output |\n|----------|--------|\n| `{{gitsha N}}` | First N chars of commit SHA |\n| `{{gitdate \"format\"}}` | Git commit date in Go format |\n| `{{date \"format\"}}` | Current date |\n\n---\n\n## Common Workflows\n\n**Deploy from source:**\n```bash\nuc deploy                          # Build + push + deploy\nuc build --push && uc deploy --no-build   # Separate steps\n```\n\n**Inspect a service:**\n```bash\nuc inspect web\nuc logs -f web\nuc logs --since 1h web\nuc exec web                        # Opens shell\nuc exec web \u002Fbin\u002Fsh -c \"env\"       # Run specific command\n```\n\n**Zero-downtime deploys** happen automatically; Uncloud waits for health checks before terminating old containers.\n\n**Force recreate:**\n```bash\nuc deploy --recreate\n```\n\n---\n\n## Common Mistakes\n\n| Mistake | Fix |\n|---------|-----|\n| Editing the Caddyfile directly | Use `x-caddy` in compose or `--caddyfile` on `uc service run` |\n| Proxying an HTTPS upstream with self-signed cert | Add `transport http { tls_insecure_skip_verify }` |\n| `uc caddy config` shows no user-defined blocks | Caddy admin socket unreachable — check `uc inspect caddy` and `uc logs caddy` |\n| Service can't reach external LAN IP from container | Verify Caddy container's host can route to target network |\n| Volumes lost after `uc service rm` | Named volumes persist; only anonymous volumes are auto-removed |\n",{"name":5,"metadata":24,"description":7},{"origin":25},"ECC","main","a73152352c0612252131e5cf84e91312a6cf17dc","devops-cloud\u002Funcloud","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs","https:\u002F\u002Fgithub.com\u002FHenrique1601","https:\u002F\u002Fbezerraportifolio.netlify.app\u002F","Full Stack Developer | React, Next.js, TypeScript, Node.js & IA | Construindo produtos digitais e soluções SaaS","2026-11-15 02:56:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Henrique1601\u002FSkiilsToIAs --skill uncloud",{"tool":40,"command":41},"bunx","bunx skills add Henrique1601\u002FSkiilsToIAs --skill uncloud",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Henrique1601\u002FSkiilsToIAs --skill uncloud","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Funcloud\u002FSKILL.md",true,[],[49,56,63,71,78,85],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7E2ANBW9V6AVX5JXNCEAWF8","rag-architect-agent","Agente Arquiteto de RAG, Embeddings & Busca Vetorial. Especialista em design e implementação de pipelines de Retrieval-Augmented Generation de alta fidelidade: chunking semântico, modelagem pgvector no PostgreSQL (Neon\u002FSupabase), busca híbrida (cosseno + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fcustom-agents\u002Frag-architect-agent\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7E29KKF8R02ZRGYE2MJM67G","rag-architecture-patterns","Padrões arquiteturais e implementação de pipelines RAG (Retrieval-Augmented Generation) de alta fidelidade para qualquer projeto ou sistema. Cobre chunking semântico, embeddings, busca híbrida (pgvector + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Frag-architecture-patterns\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CWRA8E3BJ7CPY8N8EG28J1","skill-repair","Use this to fix and re-install agent skills that have failed installation.\nThis skill provides the necessary context and permissions to surgically update\nthe `manifest.json` after a fix has been applied.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fskill-repair\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CWR66FZP8FA47WVZ4Z2EXC","security-scan","Scan your Claude Code configuration (.claude\u002F directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-scan\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CWR0QPY58QPTR1P759TFNG","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-review\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CWQXCE40XWT4FZ3VWZFGDP","security-bounty-hunter","Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-bounty-hunter\u002FSKILL.md",[],[]]