[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74DZHSNME5A0YRHS85KZCQK":3,"skill-same:01M74DZHSNME5A0YRHS85KZCQK":54},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M74DZHSNME5A0YRHS85KZCQK","repomix-codebase-packer",null,"Packs a whole repo, local or remote, into a single LLM-optimized file, with Tree-sitter compression (~70% fewer tokens) and secret scanning. For auditing an entire repo or preparing subagent context.","CarlosCaPe\u002Foctorato","CarlosCaPe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F39838249?v=4","01M72WXX4ZRR8MBH1EP1QND2FQ","dataqbs","01M72WXX5NA7YCKRSJ54GW1GQ8",18,"MIT","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Frepomix-codebase-packer\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: repomix-codebase-packer\ndescription: \"Packs a whole repo, local or remote, into a single LLM-optimized file, with Tree-sitter compression (~70% fewer tokens) and secret scanning. For auditing an entire repo or preparing subagent context.\"\n---\n\n# Repomix — Codebase to Single AI-Friendly File\n\nPacks a repo into one structured file (XML \u002F Markdown \u002F JSON \u002F plain text) with metadata, directory tree, per-file token counts, and optional compression. Respects `.gitignore`, includes Secretlint to flag secrets before you paste into an LLM.\n\nRepo: https:\u002F\u002Fgithub.com\u002Fyamadashy\u002Frepomix · MIT · `npx repomix@latest`\n\n## When to use\n\n- Sending a whole arm\u002Frepo to Claude for architectural review, security audit, or refactor planning\n- Preparing context for an `Explore` or `general-purpose` subagent that needs cross-file awareness\n- Onboarding a new client repo — pack it once, ask Claude \"explain what this does\" against the pack\n- Generating documentation \u002F tests for a small-to-medium codebase\n- Auditing an external OSS dependency before adopting it (pack the remote with `--remote`)\n\n## When NOT to use\n\n- Repo > ~200K tokens even after compression — chunk by directory instead, or use progressive exploration\n- You only need one file — `Read` is cheaper than packing the whole repo\n- Sensitive client data — pack respects `.gitignore` but Secretlint is not a substitute for a security review; never paste a pack into a third-party LLM without confirming the arm's data classification\n\n## Install\n\n```bash\n# zero-install (recommended for ad-hoc)\nnpx repomix@latest\n\n# global\nnpm install -g repomix\n```\n\n## Core commands\n\n```bash\n# pack current directory → repomix-output.xml\nrepomix\n\n# Markdown output (easier to skim in a code review)\nrepomix --style markdown\n\n# Tree-sitter compression — drops bodies, keeps signatures (~70% fewer tokens)\nrepomix --compress\n\n# scope: include\u002Fexclude\nrepomix --include \"src\u002F**\u002F*.ts\" --ignore \"**\u002F*.test.ts,**\u002F*.spec.ts\"\n\n# pack a remote repo without cloning\nrepomix --remote yamadashy\u002Frepomix\nrepomix --remote https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato --remote-branch main\n\n# split output if it blows the context window\nrepomix --split-output 1mb\n\n# include git context for \"why\" questions\nrepomix --include-logs --include-diffs\n\n# token distribution by directory (find the heavy folders before packing)\nrepomix --token-count-tree 1000\n```\n\n## MCP server mode (registered in this brain)\n\nThis brain has repomix registered as an MCP server. Inside Claude Code you can call its tools directly without shelling out:\n\n```bash\n# registration command (already executed for this brain — for reference only)\nclaude mcp add repomix -- npx -y repomix --mcp\n```\n\nWhen the MCP is active, Claude can request `pack_codebase`, `pack_remote_repository`, and related tools as native tool calls — no temp file roundtrip.\n\n## Patterns for this brain\n\n**Arm code review.** Inside an arm repo: `repomix --compress --style markdown --ignore \"**\u002Fnode_modules\u002F**,**\u002F.next\u002F**,**\u002Fdist\u002F**\"` → paste into Claude with prompt \"act as Code Reviewer agent, audit this for security + maintainability\".\n\n**External OSS audit.** Before adopting a new dependency: `repomix --remote \u003Corg\u002Frepo> --compress` → ask Claude for license risk, maintainer activity, abandoned-fork detection. Pair with `bruno-postman-alternative` \u002F `tabularis-db-client` evaluations.\n\n**Subagent prep.** When dispatching an `Explore` or `general-purpose` agent for whole-repo questions, pack first and hand it the file path — saves the agent N tool calls and keeps token cost predictable.\n\n**Pre-paste safety.** Always skim the Secretlint warnings printed by repomix before pasting into ANY external LLM. The brain rule \"never echo back user-provided secrets\" applies to whole-repo dumps.\n\n## Companion skills\n\n- `progressive-code-exploration` — when the repo is too big to pack, use index-first instead\n- `token-efficient-prompting` — once packed, ask compact questions\n- `security-threat-model` — feed the pack into a structured threat-model pass\n- `code-review` — natural downstream skill after `repomix --compress`\n- `agent-browser` — for live web targets repomix can't reach (it's repo-only)\n\n## Caveats\n\n- `--compress` uses Tree-sitter; works best on Python, TS\u002FJS, Go, Rust, Java. For exotic languages output may degrade to raw chunks.\n- Secretlint catches common patterns (AWS keys, GH tokens, Stripe) but is not exhaustive. Never assume a pack is safe to share publicly.\n- Remote packing clones to a temp dir; large monorepos can take minutes. Prefer `--include` to scope down.\n","# Repomix — Codebase to Single AI-Friendly File\n\nPacks a repo into one structured file (XML \u002F Markdown \u002F JSON \u002F plain text) with metadata, directory tree, per-file token counts, and optional compression. Respects `.gitignore`, includes Secretlint to flag secrets before you paste into an LLM.\n\nRepo: https:\u002F\u002Fgithub.com\u002Fyamadashy\u002Frepomix · MIT · `npx repomix@latest`\n\n## When to use\n\n- Sending a whole arm\u002Frepo to Claude for architectural review, security audit, or refactor planning\n- Preparing context for an `Explore` or `general-purpose` subagent that needs cross-file awareness\n- Onboarding a new client repo — pack it once, ask Claude \"explain what this does\" against the pack\n- Generating documentation \u002F tests for a small-to-medium codebase\n- Auditing an external OSS dependency before adopting it (pack the remote with `--remote`)\n\n## When NOT to use\n\n- Repo > ~200K tokens even after compression — chunk by directory instead, or use progressive exploration\n- You only need one file — `Read` is cheaper than packing the whole repo\n- Sensitive client data — pack respects `.gitignore` but Secretlint is not a substitute for a security review; never paste a pack into a third-party LLM without confirming the arm's data classification\n\n## Install\n\n```bash\n# zero-install (recommended for ad-hoc)\nnpx repomix@latest\n\n# global\nnpm install -g repomix\n```\n\n## Core commands\n\n```bash\n# pack current directory → repomix-output.xml\nrepomix\n\n# Markdown output (easier to skim in a code review)\nrepomix --style markdown\n\n# Tree-sitter compression — drops bodies, keeps signatures (~70% fewer tokens)\nrepomix --compress\n\n# scope: include\u002Fexclude\nrepomix --include \"src\u002F**\u002F*.ts\" --ignore \"**\u002F*.test.ts,**\u002F*.spec.ts\"\n\n# pack a remote repo without cloning\nrepomix --remote yamadashy\u002Frepomix\nrepomix --remote https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato --remote-branch main\n\n# split output if it blows the context window\nrepomix --split-output 1mb\n\n# include git context for \"why\" questions\nrepomix --include-logs --include-diffs\n\n# token distribution by directory (find the heavy folders before packing)\nrepomix --token-count-tree 1000\n```\n\n## MCP server mode (registered in this brain)\n\nThis brain has repomix registered as an MCP server. Inside Claude Code you can call its tools directly without shelling out:\n\n```bash\n# registration command (already executed for this brain — for reference only)\nclaude mcp add repomix -- npx -y repomix --mcp\n```\n\nWhen the MCP is active, Claude can request `pack_codebase`, `pack_remote_repository`, and related tools as native tool calls — no temp file roundtrip.\n\n## Patterns for this brain\n\n**Arm code review.** Inside an arm repo: `repomix --compress --style markdown --ignore \"**\u002Fnode_modules\u002F**,**\u002F.next\u002F**,**\u002Fdist\u002F**\"` → paste into Claude with prompt \"act as Code Reviewer agent, audit this for security + maintainability\".\n\n**External OSS audit.** Before adopting a new dependency: `repomix --remote \u003Corg\u002Frepo> --compress` → ask Claude for license risk, maintainer activity, abandoned-fork detection. Pair with `bruno-postman-alternative` \u002F `tabularis-db-client` evaluations.\n\n**Subagent prep.** When dispatching an `Explore` or `general-purpose` agent for whole-repo questions, pack first and hand it the file path — saves the agent N tool calls and keeps token cost predictable.\n\n**Pre-paste safety.** Always skim the Secretlint warnings printed by repomix before pasting into ANY external LLM. The brain rule \"never echo back user-provided secrets\" applies to whole-repo dumps.\n\n## Companion skills\n\n- `progressive-code-exploration` — when the repo is too big to pack, use index-first instead\n- `token-efficient-prompting` — once packed, ask compact questions\n- `security-threat-model` — feed the pack into a structured threat-model pass\n- `code-review` — natural downstream skill after `repomix --compress`\n- `agent-browser` — for live web targets repomix can't reach (it's repo-only)\n\n## Caveats\n\n- `--compress` uses Tree-sitter; works best on Python, TS\u002FJS, Go, Rust, Java. For exotic languages output may degrade to raw chunks.\n- Secretlint catches common patterns (AWS keys, GH tokens, Stripe) but is not exhaustive. Never assume a pack is safe to share publicly.\n- Remote packing clones to a temp dir; large monorepos can take minutes. Prefer `--include` to scope down.\n",{"name":5,"description":7},"master","b4414608cd5a3f87d1525b518f1c6add8363540d","skills\u002Frepomix-codebase-packer",6,"https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato","https:\u002F\u002Fwww.dataqbs.com\u002Foctorato","https:\u002F\u002Fgithub.com\u002FCarlosCaPe","www.dataqbs.com"," AI-powered data engineering\r\n& consulting\r\n\r\nWe build data platforms that turn complexity into clarity — from cloud architecture and ETL pipelines to AI-driven","2026-11-14 00:21:00",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add CarlosCaPe\u002Foctorato --skill repomix-codebase-packer",{"tool":40,"command":41},"bunx","bunx skills add CarlosCaPe\u002Foctorato --skill repomix-codebase-packer",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CarlosCaPe\u002Foctorato --skill repomix-codebase-packer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Frepomix-codebase-packer\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"skill.json","REFERENCE","参考文档",321,"https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Frepomix-codebase-packer\u002Fskill.json",[55,64,72,79,87,95],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":60,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M74EVAA4A4B4AKR5TT732GP4","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M74EV4WMRDKP2NQS4YWR8PXH","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwrangler\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwrangler\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M74EV05MHTXKEXD4B2QJEYTF","workspace-skill-discovery","Discover and include ALL skills across the workspace — not just global ones. Use at the start of every session or when the user asks about available skills. Ensures project-level skills (under .claude\u002Fskills\u002F or skills\u002F in any repo) are never missed.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkspace-skill-discovery\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M74ETV78525B4VP2F28Z6NRD","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkers-best-practices\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkers-best-practices\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M74ETR75NF67WGVEN7288ACV","winui-app","Create, build and design WinUI 3 desktop apps with C# and the Windows App SDK following Microsoft's official guidance and CommunityToolkit. Covers XAML, navigation, theming, accessibility and deployment.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwinui-app\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwinui-app\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M74ETJFRNPPNSQZ36C6HD6CW","windows-brain-script-portability","Scripts in ~\u002F.claude\u002Fscripts\u002F that run on a Windows brain: use the python3.cmd shim and not bare python3, and reconfigure stdout to UTF-8 if you print symbols. Use it when writing a brain script or triaging a Windows-only crash.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwindows-brain-script-portability\u002FSKILL.md",[],[]]