[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CVAC6GZY0GSWPS6STM6WXT":3,"skill-same:01M7CVAC6GZY0GSWPS6STM6WXT":59},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CVAC6GZY0GSWPS6STM6WXT","deploy-to-vercel",null,"Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".","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\u002Fdeploy-to-vercel\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deploy-to-vercel\ndescription: Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".\nmetadata:\n  author: vercel\n  version: \"4.0.0\"\n---\n\n# Deploy to Vercel\n\nDeploy any project to Vercel. **Always deploy as preview** (not production) unless the user explicitly asks for production.\n\nThe goal is to get the user into the best long-term setup: their project linked to Vercel with git-push deploys. Every method below tries to move the user closer to that state.\n\n## Step 1: Gather Project State\n\nRun all four checks before deciding which method to use:\n\n```bash\n# 1. Check for a git remote\ngit remote get-url origin 2>\u002Fdev\u002Fnull\n\n# 2. Check if locally linked to a Vercel project (either file means linked)\ncat .vercel\u002Fproject.json 2>\u002Fdev\u002Fnull || cat .vercel\u002Frepo.json 2>\u002Fdev\u002Fnull\n\n# 3. Check if the Vercel CLI is installed and authenticated\nvercel whoami 2>\u002Fdev\u002Fnull\n\n# 4. List available teams (if authenticated)\nvercel teams list --format json 2>\u002Fdev\u002Fnull\n```\n\n### Team selection\n\nIf the user belongs to multiple teams, present all available team slugs as a bulleted list and ask which one to deploy to. Once the user picks a team, proceed immediately to the next step — do not ask for additional confirmation.\n\nPass the team slug via `--scope` on all subsequent CLI commands (`vercel deploy`, `vercel link`, `vercel inspect`, etc.):\n\n```bash\nvercel deploy [path] -y --no-wait --scope \u003Cteam-slug>\n```\n\nIf the project is already linked (`.vercel\u002Fproject.json` or `.vercel\u002Frepo.json` exists), the `orgId` in those files determines the team — no need to ask again. If there is only one team (or just a personal account), skip the prompt and use it directly.\n\n**About the `.vercel\u002F` directory:** A linked project has either:\n- `.vercel\u002Fproject.json` — created by `vercel link` (single project linking). Contains `projectId` and `orgId`.\n- `.vercel\u002Frepo.json` — created by `vercel link --repo` (repo-based linking). Contains `orgId`, `remoteName`, and a `projects` array mapping directories to Vercel project IDs.\n\nEither file means the project is linked. Check for both.\n\n**Do NOT** use `vercel project inspect`, `vercel ls`, or `vercel link` to detect state in an unlinked directory — without a `.vercel\u002F` config, they will interactively prompt (or with `--yes`, silently link as a side-effect). Only `vercel whoami` is safe to run anywhere.\n\n## Step 2: Choose a Deploy Method\n\n### Linked (`.vercel\u002F` exists) + has git remote → Git Push\n\nThis is the ideal state. The project is linked and has git integration.\n\n1. **Ask the user before pushing.** Never push without explicit approval:\n   ```\n   This project is connected to Vercel via git. I can commit and push to\n   trigger a deployment. Want me to proceed?\n   ```\n\n2. **Commit and push:**\n   ```bash\n   git add .\n   git commit -m \"deploy: \u003Cdescription of changes>\"\n   git push\n   ```\n   Vercel automatically builds from the push. Non-production branches get preview deployments; the production branch (usually `main`) gets a production deployment.\n\n3. **Retrieve the preview URL.** If the CLI is authenticated:\n   ```bash\n   sleep 5\n   vercel ls --format json\n   ```\n   The JSON output has a `deployments` array. Find the latest entry — its `url` field is the preview URL.\n\n   If the CLI is not authenticated, tell the user to check the Vercel dashboard or the commit status checks on their git provider for the preview URL.\n\n---\n\n### Linked (`.vercel\u002F` exists) + no git remote → `vercel deploy`\n\nThe project is linked but there's no git repo. Deploy directly with the CLI.\n\n```bash\nvercel deploy [path] -y --no-wait\n```\n\nUse `--no-wait` so the CLI returns immediately with the deployment URL instead of blocking until the build finishes (builds can take a while). Then check on the deployment status with:\n\n```bash\nvercel inspect \u003Cdeployment-url>\n```\n\nFor production deploys (only if user explicitly asks):\n```bash\nvercel deploy [path] --prod -y --no-wait\n```\n\n---\n\n### Not linked + CLI is authenticated → Link first, then deploy\n\nThe CLI is working but the project isn't linked yet. This is the opportunity to get the user into the best state.\n\n1. **Ask the user which team to deploy to.** Present the team slugs from Step 1 as a bulleted list. If there's only one team (or just a personal account), skip this step.\n\n2. **Once a team is selected, proceed directly to linking.** Tell the user what will happen but do not ask for separate confirmation:\n   ```\n   Linking this project to \u003Cteam name> on Vercel. This will create a Vercel\n   project to deploy to and enable automatic deployments on future git pushes.\n   ```\n\n3. **If a git remote exists**, use repo-based linking with the selected team scope:\n   ```bash\n   vercel link --repo --scope \u003Cteam-slug>\n   ```\n   This reads the git remote URL and matches it to existing Vercel projects that deploy from that repo. It creates `.vercel\u002Frepo.json`. This is much more reliable than `vercel link` (without `--repo`), which tries to match by directory name and often fails when the local folder and Vercel project are named differently.\n\n   **If there is no git remote**, fall back to standard linking:\n   ```bash\n   vercel link --scope \u003Cteam-slug>\n   ```\n   This prompts the user to select or create a project. It creates `.vercel\u002Fproject.json`.\n\n4. **Then deploy using the best available method:**\n   - If a git remote exists → commit and push (see git push method above)\n   - If no git remote → `vercel deploy [path] -y --no-wait --scope \u003Cteam-slug>`, then `vercel inspect \u003Curl>` to check status\n\n---\n\n### Not linked + CLI not authenticated → Install, auth, link, deploy\n\nThe Vercel CLI isn't set up at all.\n\n1. **Install the CLI (if not already installed):**\n   ```bash\n   npm install -g vercel\n   ```\n\n2. **Authenticate:**\n   ```bash\n   vercel login\n   ```\n   The user completes auth in their browser. If running in a non-interactive environment where login is not possible, skip to the **no-auth fallback** below.\n\n3. **Ask which team to deploy to** — present team slugs from `vercel teams list --format json` as a bulleted list. If only one team \u002F personal account, skip. Once selected, proceed immediately.\n\n4. **Link the project** with the selected team scope (use `--repo` if a git remote exists, plain `vercel link` otherwise):\n   ```bash\n   vercel link --repo --scope \u003Cteam-slug>   # if git remote exists\n   vercel link --scope \u003Cteam-slug>          # if no git remote\n   ```\n\n5. **Deploy** using the best available method (git push if remote exists, otherwise `vercel deploy -y --no-wait --scope \u003Cteam-slug>`, then `vercel inspect \u003Curl>` to check status).\n\n---\n\n### No-Auth Fallback — `vercel deploy --temporary`\n\n**When to use:** The CLI has no credentials and `vercel login` isn't possible (sandboxes, agents, non-interactive environments). Do **not** ask the user to approve a CLI login or device code first — try this.\n\n```bash\nnpx vercel@latest deploy [path] --temporary -y\n```\n\nNo account is needed. The CLI builds locally, deploys to a temporary production URL, and prints a **claim URL** plus how long until the deployment expires. Rerunning the command in the same directory redeploys the same temporary project until it expires.\n\nTemporary deployments don't work in CI or in a directory already linked to a Vercel project. See https:\u002F\u002Fvercel.com\u002Fdocs\u002Fdeployments\u002Fdeploy-without-logging-in.\n\n**Tell the user:** \"Your deployment is ready at [url]. It expires in [time] unless you claim it at [claimUrl]. Don't share the claim link.\"\n\n**Escalated network access (Codex):** Only escalate the deploy command if sandboxing blocks the network call (`sandbox_permissions=require_escalated`).\n\n---\n\n## Agent-Specific Notes\n\n### Claude Code \u002F terminal-based agents\n\nYou have full shell access. Follow the decision flow above using the CLI directly.\n\n### Sandboxed environments (claude.ai, Codex)\n\nCheck whether the CLI is logged in with `vercel whoami`. If it is, follow Step 2, including team selection. If it isn't, use the **no-auth fallback**.\n\n---\n\n## Output\n\nAlways show the user the deployment URL.\n\n- **Git push:** Use `vercel ls --format json` to find the preview URL. If the CLI isn't authenticated, tell the user to check the Vercel dashboard or commit status checks.\n- **CLI deploy:** Show the URL returned by `vercel deploy --no-wait`. Use `vercel inspect \u003Curl>` to check build status and report it to the user.\n- **No-auth fallback:** Show the deployment URL, the claim URL, and the expiry the CLI printed.\n\n**Do not** curl or fetch the deployed URL to verify it works. Just return the link.\n\n---\n\n## Troubleshooting\n\n### Network Egress Error (claude.ai)\n\nIf deployment fails due to network restrictions on claude.ai, tell the user:\n\n```\nDeployment failed due to network restrictions. To fix this:\n\n1. Go to https:\u002F\u002Fclaude.ai\u002Fsettings\u002Fcapabilities\n2. Add *.vercel.com and registry.npmjs.org to the allowed domains\n3. Try deploying again\n```\n\n### Escalated Network Access (Codex \u002F sandboxed environments)\n\nIf deployment fails due to network issues (timeouts, DNS errors, connection resets) in a sandboxed environment, rerun with escalated permissions (`sandbox_permissions=require_escalated`). Do not escalate the initial CLI availability check — only escalate the actual deploy command.\n\nExample guidance to the user:\n```\nThe deploy needs escalated network access to deploy to Vercel. I can rerun\nthe command with escalated permissions — want me to proceed?\n```\n\n### CLI Auth Failure\n\nIf `vercel login` or `vercel deploy` fails with authentication errors, use the no-auth fallback: `vercel deploy --temporary -y`.\n","# Deploy to Vercel\n\nDeploy any project to Vercel. **Always deploy as preview** (not production) unless the user explicitly asks for production.\n\nThe goal is to get the user into the best long-term setup: their project linked to Vercel with git-push deploys. Every method below tries to move the user closer to that state.\n\n## Step 1: Gather Project State\n\nRun all four checks before deciding which method to use:\n\n```bash\n# 1. Check for a git remote\ngit remote get-url origin 2>\u002Fdev\u002Fnull\n\n# 2. Check if locally linked to a Vercel project (either file means linked)\ncat .vercel\u002Fproject.json 2>\u002Fdev\u002Fnull || cat .vercel\u002Frepo.json 2>\u002Fdev\u002Fnull\n\n# 3. Check if the Vercel CLI is installed and authenticated\nvercel whoami 2>\u002Fdev\u002Fnull\n\n# 4. List available teams (if authenticated)\nvercel teams list --format json 2>\u002Fdev\u002Fnull\n```\n\n### Team selection\n\nIf the user belongs to multiple teams, present all available team slugs as a bulleted list and ask which one to deploy to. Once the user picks a team, proceed immediately to the next step — do not ask for additional confirmation.\n\nPass the team slug via `--scope` on all subsequent CLI commands (`vercel deploy`, `vercel link`, `vercel inspect`, etc.):\n\n```bash\nvercel deploy [path] -y --no-wait --scope \u003Cteam-slug>\n```\n\nIf the project is already linked (`.vercel\u002Fproject.json` or `.vercel\u002Frepo.json` exists), the `orgId` in those files determines the team — no need to ask again. If there is only one team (or just a personal account), skip the prompt and use it directly.\n\n**About the `.vercel\u002F` directory:** A linked project has either:\n- `.vercel\u002Fproject.json` — created by `vercel link` (single project linking). Contains `projectId` and `orgId`.\n- `.vercel\u002Frepo.json` — created by `vercel link --repo` (repo-based linking). Contains `orgId`, `remoteName`, and a `projects` array mapping directories to Vercel project IDs.\n\nEither file means the project is linked. Check for both.\n\n**Do NOT** use `vercel project inspect`, `vercel ls`, or `vercel link` to detect state in an unlinked directory — without a `.vercel\u002F` config, they will interactively prompt (or with `--yes`, silently link as a side-effect). Only `vercel whoami` is safe to run anywhere.\n\n## Step 2: Choose a Deploy Method\n\n### Linked (`.vercel\u002F` exists) + has git remote → Git Push\n\nThis is the ideal state. The project is linked and has git integration.\n\n1. **Ask the user before pushing.** Never push without explicit approval:\n   ```\n   This project is connected to Vercel via git. I can commit and push to\n   trigger a deployment. Want me to proceed?\n   ```\n\n2. **Commit and push:**\n   ```bash\n   git add .\n   git commit -m \"deploy: \u003Cdescription of changes>\"\n   git push\n   ```\n   Vercel automatically builds from the push. Non-production branches get preview deployments; the production branch (usually `main`) gets a production deployment.\n\n3. **Retrieve the preview URL.** If the CLI is authenticated:\n   ```bash\n   sleep 5\n   vercel ls --format json\n   ```\n   The JSON output has a `deployments` array. Find the latest entry — its `url` field is the preview URL.\n\n   If the CLI is not authenticated, tell the user to check the Vercel dashboard or the commit status checks on their git provider for the preview URL.\n\n---\n\n### Linked (`.vercel\u002F` exists) + no git remote → `vercel deploy`\n\nThe project is linked but there's no git repo. Deploy directly with the CLI.\n\n```bash\nvercel deploy [path] -y --no-wait\n```\n\nUse `--no-wait` so the CLI returns immediately with the deployment URL instead of blocking until the build finishes (builds can take a while). Then check on the deployment status with:\n\n```bash\nvercel inspect \u003Cdeployment-url>\n```\n\nFor production deploys (only if user explicitly asks):\n```bash\nvercel deploy [path] --prod -y --no-wait\n```\n\n---\n\n### Not linked + CLI is authenticated → Link first, then deploy\n\nThe CLI is working but the project isn't linked yet. This is the opportunity to get the user into the best state.\n\n1. **Ask the user which team to deploy to.** Present the team slugs from Step 1 as a bulleted list. If there's only one team (or just a personal account), skip this step.\n\n2. **Once a team is selected, proceed directly to linking.** Tell the user what will happen but do not ask for separate confirmation:\n   ```\n   Linking this project to \u003Cteam name> on Vercel. This will create a Vercel\n   project to deploy to and enable automatic deployments on future git pushes.\n   ```\n\n3. **If a git remote exists**, use repo-based linking with the selected team scope:\n   ```bash\n   vercel link --repo --scope \u003Cteam-slug>\n   ```\n   This reads the git remote URL and matches it to existing Vercel projects that deploy from that repo. It creates `.vercel\u002Frepo.json`. This is much more reliable than `vercel link` (without `--repo`), which tries to match by directory name and often fails when the local folder and Vercel project are named differently.\n\n   **If there is no git remote**, fall back to standard linking:\n   ```bash\n   vercel link --scope \u003Cteam-slug>\n   ```\n   This prompts the user to select or create a project. It creates `.vercel\u002Fproject.json`.\n\n4. **Then deploy using the best available method:**\n   - If a git remote exists → commit and push (see git push method above)\n   - If no git remote → `vercel deploy [path] -y --no-wait --scope \u003Cteam-slug>`, then `vercel inspect \u003Curl>` to check status\n\n---\n\n### Not linked + CLI not authenticated → Install, auth, link, deploy\n\nThe Vercel CLI isn't set up at all.\n\n1. **Install the CLI (if not already installed):**\n   ```bash\n   npm install -g vercel\n   ```\n\n2. **Authenticate:**\n   ```bash\n   vercel login\n   ```\n   The user completes auth in their browser. If running in a non-interactive environment where login is not possible, skip to the **no-auth fallback** below.\n\n3. **Ask which team to deploy to** — present team slugs from `vercel teams list --format json` as a bulleted list. If only one team \u002F personal account, skip. Once selected, proceed immediately.\n\n4. **Link the project** with the selected team scope (use `--repo` if a git remote exists, plain `vercel link` otherwise):\n   ```bash\n   vercel link --repo --scope \u003Cteam-slug>   # if git remote exists\n   vercel link --scope \u003Cteam-slug>          # if no git remote\n   ```\n\n5. **Deploy** using the best available method (git push if remote exists, otherwise `vercel deploy -y --no-wait --scope \u003Cteam-slug>`, then `vercel inspect \u003Curl>` to check status).\n\n---\n\n### No-Auth Fallback — `vercel deploy --temporary`\n\n**When to use:** The CLI has no credentials and `vercel login` isn't possible (sandboxes, agents, non-interactive environments). Do **not** ask the user to approve a CLI login or device code first — try this.\n\n```bash\nnpx vercel@latest deploy [path] --temporary -y\n```\n\nNo account is needed. The CLI builds locally, deploys to a temporary production URL, and prints a **claim URL** plus how long until the deployment expires. Rerunning the command in the same directory redeploys the same temporary project until it expires.\n\nTemporary deployments don't work in CI or in a directory already linked to a Vercel project. See https:\u002F\u002Fvercel.com\u002Fdocs\u002Fdeployments\u002Fdeploy-without-logging-in.\n\n**Tell the user:** \"Your deployment is ready at [url]. It expires in [time] unless you claim it at [claimUrl]. Don't share the claim link.\"\n\n**Escalated network access (Codex):** Only escalate the deploy command if sandboxing blocks the network call (`sandbox_permissions=require_escalated`).\n\n---\n\n## Agent-Specific Notes\n\n### Claude Code \u002F terminal-based agents\n\nYou have full shell access. Follow the decision flow above using the CLI directly.\n\n### Sandboxed environments (claude.ai, Codex)\n\nCheck whether the CLI is logged in with `vercel whoami`. If it is, follow Step 2, including team selection. If it isn't, use the **no-auth fallback**.\n\n---\n\n## Output\n\nAlways show the user the deployment URL.\n\n- **Git push:** Use `vercel ls --format json` to find the preview URL. If the CLI isn't authenticated, tell the user to check the Vercel dashboard or commit status checks.\n- **CLI deploy:** Show the URL returned by `vercel deploy --no-wait`. Use `vercel inspect \u003Curl>` to check build status and report it to the user.\n- **No-auth fallback:** Show the deployment URL, the claim URL, and the expiry the CLI printed.\n\n**Do not** curl or fetch the deployed URL to verify it works. Just return the link.\n\n---\n\n## Troubleshooting\n\n### Network Egress Error (claude.ai)\n\nIf deployment fails due to network restrictions on claude.ai, tell the user:\n\n```\nDeployment failed due to network restrictions. To fix this:\n\n1. Go to https:\u002F\u002Fclaude.ai\u002Fsettings\u002Fcapabilities\n2. Add *.vercel.com and registry.npmjs.org to the allowed domains\n3. Try deploying again\n```\n\n### Escalated Network Access (Codex \u002F sandboxed environments)\n\nIf deployment fails due to network issues (timeouts, DNS errors, connection resets) in a sandboxed environment, rerun with escalated permissions (`sandbox_permissions=require_escalated`). Do not escalate the initial CLI availability check — only escalate the actual deploy command.\n\nExample guidance to the user:\n```\nThe deploy needs escalated network access to deploy to Vercel. I can rerun\nthe command with escalated permissions — want me to proceed?\n```\n\n### CLI Auth Failure\n\nIf `vercel login` or `vercel deploy` fails with authentication errors, use the no-auth fallback: `vercel deploy --temporary -y`.\n",{"name":5,"metadata":24,"description":7},{"author":25,"version":26},"vercel","4.0.0","main","a73152352c0612252131e5cf84e91312a6cf17dc","devops-cloud\u002Fdeploy-to-vercel","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":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Henrique1601\u002FSkiilsToIAs --skill deploy-to-vercel",{"tool":41,"command":42},"bunx","bunx skills add Henrique1601\u002FSkiilsToIAs --skill deploy-to-vercel",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Henrique1601\u002FSkiilsToIAs --skill deploy-to-vercel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fdeploy-to-vercel\u002FSKILL.md",true,[49,55],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"resources\u002Fdeploy-codex.sh","SCRIPT","脚本",8855,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fdeploy-to-vercel\u002Fresources\u002Fdeploy-codex.sh",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"resources\u002Fdeploy.sh",8841,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fdeploy-to-vercel\u002Fresources\u002Fdeploy.sh",[60,67,74,82,89,96],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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",[],[]]