[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78DSNGMN2Q50YZB00Y7BBVT":3,"skill-same:01M78DSNGMN2Q50YZB00Y7BBVT":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M78DSNGMN2Q50YZB00Y7BBVT","folder-specific-claude-and-agents-md",null,"Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when the user asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.","Solizardking\u002Fskillhub-main","Solizardking","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108096810?v=4","01M786KDB10AYV042N0F9BD5B5","Clawd","01M786NYYXSZK1D05WM8JQPC48",0,"MIT","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fskill-authoring\u002Ffolder-specific-claude-and-agents-md\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: folder-specific-claude-and-agents-md\ndescription: Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when the user asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.\nuser-invocable: true\n---\n\n# Folder CLAUDE.md Creation\n\nGenerate a focused `CLAUDE.md` inside a target folder, plus an `AGENTS.md` symlink pointing at it. The file gives any future agent (Claude Code, Codex, etc.) the folder-specific context the global `CLAUDE.md` doesn't cover.\n\nBackground reference: `library\u002Fclaude-code\u002Fclaude-and-agents-md.md`.\n\n## Process\n\n### Step 1: Confirm the target folder + sanity-check it deserves a file\nAsk the user which folder. Use absolute path under `~\u002Fpath\u002Fto\u002Fproject\u002F`.\n\n**Only create a file if the folder has context needed across multiple sessions** — active evolving work, specific conventions, ongoing decisions. A folder of static reference files does NOT need one (agents can read on demand). If unsure, ask the user.\n\n### Step 2: Read every file in the folder IN FULL\n- Use `ls -la` first to enumerate files and subfolders.\n- Read every markdown, config, and key source file.\n- For large tldraw\u002FVite subprojects: read `package.json`, `src\u002FApp.tsx`, one representative module file, and the folder's own `module-details.md`-style files.\n- Do NOT skim. Do NOT skip. The user's later edits depend on you having full context.\n\n### Step 3: Draft a bullet list of candidate content\nBefore writing the file, give the user a bullet list grouped by section — let them react first. Candidate sections (skip any that don't apply):\n\n- **Product \u002F Purpose** — what this folder\u002Fproject is, current state, key metrics\n- **Avatar \u002F Audience** — who it's for (if applicable)\n- **Essential Files** — one-line role for each important file, including cross-folder references (use `@path\u002Ffile.md` import syntax)\n- **Constraints (MUST NOT)** — explicit hard negatives. Highest-ROI content in the file.\n- **Conventions** — the user's lingo, status emojis (✅ 🟡), naming patterns, \"usually do\" patterns\n- **Locked Decisions** — things agreed + dated, must not re-litigate\n- **Context** — history, authority, credibility that frames the work\n- **How to work with the user** — collaboration style for this specific folder\n- **Marketing Angles \u002F Positioning** — if public-facing\n- **Top Insights** — 3-5 most glaring signals from research (if research exists)\n\n### Step 4: Iterate with the user\n- Keep answers short. The user will edit directly in the IDE.\n- When they edit the file, RE-READ it and flag: contradictions, typos, missing rules, wrong categorization.\n- Do not revert their edits unless asked.\n\n### Step 5: Write the file\n- Path: `\u003Cfolder>\u002FCLAUDE.md`\n- Start with a one-line header explaining the file's purpose.\n- **Subdir file marker:** if this is a subdirectory file (parent folder already has its own CLAUDE.md), open with `Apply root CLAUDE.md first, then this file.`\n- Use `##` section headers matching the sections the user approved.\n- Bullets over prose. Short bullets.\n- **Cross-folder references:** use `@relative\u002Fpath\u002Ffile.md` import syntax, not prose mentions.\n- **Heavy reference docs:** annotate with `**Read when:**` triggers (e.g. \"Read when: writing offer copy\"). Prevents loading every session.\n\n### Step 6: Create the AGENTS.md symlink\n```\ncd \u003Cfolder> && ln -s CLAUDE.md AGENTS.md\n```\nVerify with `ls -la CLAUDE.md AGENTS.md`.\n\n### Step 7: Commit only when asked\nDo NOT stage or push unless the user says to. When they do: `git add -A`, commit with a `Day N:` style message, push.\n\n## Rules\n\n- **Never invent content.** Every bullet must trace back to something you read in the folder or something the user said. No generic boilerplate.\n- **Brevity wins.** The user edits aggressively to make things shorter. Start tight.\n- **Folder-scoped only.** Don't duplicate the global `CLAUDE.md` (personality, dates, ports, etc.). Only include what's specific to this folder.\n- **No file trees, no directory dumps, no stack details the code already shows.** Anything an agent can derive from `ls` or `grep` rots fast and wastes tokens. Pin decisions, rules, and context — not structure.\n- **Constraints vs Conventions.** Hard \"MUST NOT\" rules go in Constraints (explicit negatives). \"Usually do X\" patterns go in Conventions. Splitting these improves adherence.\n- **No absolute ALWAYS\u002FNEVER without explicit exceptions.** Edge cases make absolute rules get ignored. \"Never commit secrets EXCEPT `.env.example`\" beats \"never commit secrets.\"\n- **Never summarize or auto-shorten the file.** Context collapse degrades it. Grow deliberately, prune manually. If the user asks to trim, do it by hand.\n- **Maintenance loop.** When the user corrects the agent on something this file should have prevented, add the rule to the file immediately. Don't wait.\n- **No emojis unless the user uses them** (status markers ✅ 🟡 are the exception — they're already conventions).\n- **Symlink, not copy.** `AGENTS.md` must be a symlink so edits stay in sync.\n- **Flag gaps honestly.** If the user's edits introduce contradictions (e.g. \"sell X\" in one section and \"never sell X\" in another), call it out before they ask.\n","# Folder CLAUDE.md Creation\n\nGenerate a focused `CLAUDE.md` inside a target folder, plus an `AGENTS.md` symlink pointing at it. The file gives any future agent (Claude Code, Codex, etc.) the folder-specific context the global `CLAUDE.md` doesn't cover.\n\nBackground reference: `library\u002Fclaude-code\u002Fclaude-and-agents-md.md`.\n\n## Process\n\n### Step 1: Confirm the target folder + sanity-check it deserves a file\nAsk the user which folder. Use absolute path under `~\u002Fpath\u002Fto\u002Fproject\u002F`.\n\n**Only create a file if the folder has context needed across multiple sessions** — active evolving work, specific conventions, ongoing decisions. A folder of static reference files does NOT need one (agents can read on demand). If unsure, ask the user.\n\n### Step 2: Read every file in the folder IN FULL\n- Use `ls -la` first to enumerate files and subfolders.\n- Read every markdown, config, and key source file.\n- For large tldraw\u002FVite subprojects: read `package.json`, `src\u002FApp.tsx`, one representative module file, and the folder's own `module-details.md`-style files.\n- Do NOT skim. Do NOT skip. The user's later edits depend on you having full context.\n\n### Step 3: Draft a bullet list of candidate content\nBefore writing the file, give the user a bullet list grouped by section — let them react first. Candidate sections (skip any that don't apply):\n\n- **Product \u002F Purpose** — what this folder\u002Fproject is, current state, key metrics\n- **Avatar \u002F Audience** — who it's for (if applicable)\n- **Essential Files** — one-line role for each important file, including cross-folder references (use `@path\u002Ffile.md` import syntax)\n- **Constraints (MUST NOT)** — explicit hard negatives. Highest-ROI content in the file.\n- **Conventions** — the user's lingo, status emojis (✅ 🟡), naming patterns, \"usually do\" patterns\n- **Locked Decisions** — things agreed + dated, must not re-litigate\n- **Context** — history, authority, credibility that frames the work\n- **How to work with the user** — collaboration style for this specific folder\n- **Marketing Angles \u002F Positioning** — if public-facing\n- **Top Insights** — 3-5 most glaring signals from research (if research exists)\n\n### Step 4: Iterate with the user\n- Keep answers short. The user will edit directly in the IDE.\n- When they edit the file, RE-READ it and flag: contradictions, typos, missing rules, wrong categorization.\n- Do not revert their edits unless asked.\n\n### Step 5: Write the file\n- Path: `\u003Cfolder>\u002FCLAUDE.md`\n- Start with a one-line header explaining the file's purpose.\n- **Subdir file marker:** if this is a subdirectory file (parent folder already has its own CLAUDE.md), open with `Apply root CLAUDE.md first, then this file.`\n- Use `##` section headers matching the sections the user approved.\n- Bullets over prose. Short bullets.\n- **Cross-folder references:** use `@relative\u002Fpath\u002Ffile.md` import syntax, not prose mentions.\n- **Heavy reference docs:** annotate with `**Read when:**` triggers (e.g. \"Read when: writing offer copy\"). Prevents loading every session.\n\n### Step 6: Create the AGENTS.md symlink\n```\ncd \u003Cfolder> && ln -s CLAUDE.md AGENTS.md\n```\nVerify with `ls -la CLAUDE.md AGENTS.md`.\n\n### Step 7: Commit only when asked\nDo NOT stage or push unless the user says to. When they do: `git add -A`, commit with a `Day N:` style message, push.\n\n## Rules\n\n- **Never invent content.** Every bullet must trace back to something you read in the folder or something the user said. No generic boilerplate.\n- **Brevity wins.** The user edits aggressively to make things shorter. Start tight.\n- **Folder-scoped only.** Don't duplicate the global `CLAUDE.md` (personality, dates, ports, etc.). Only include what's specific to this folder.\n- **No file trees, no directory dumps, no stack details the code already shows.** Anything an agent can derive from `ls` or `grep` rots fast and wastes tokens. Pin decisions, rules, and context — not structure.\n- **Constraints vs Conventions.** Hard \"MUST NOT\" rules go in Constraints (explicit negatives). \"Usually do X\" patterns go in Conventions. Splitting these improves adherence.\n- **No absolute ALWAYS\u002FNEVER without explicit exceptions.** Edge cases make absolute rules get ignored. \"Never commit secrets EXCEPT `.env.example`\" beats \"never commit secrets.\"\n- **Never summarize or auto-shorten the file.** Context collapse degrades it. Grow deliberately, prune manually. If the user asks to trim, do it by hand.\n- **Maintenance loop.** When the user corrects the agent on something this file should have prevented, add the rule to the file immediately. Don't wait.\n- **No emojis unless the user uses them** (status markers ✅ 🟡 are the exception — they're already conventions).\n- **Symlink, not copy.** `AGENTS.md` must be a symlink so edits stay in sync.\n- **Flag gaps honestly.** If the user's edits introduce contradictions (e.g. \"sell X\" in one section and \"never sell X\" in another), call it out before they ask.\n",{"name":5,"description":7,"user-invocable":24},true,"main","be3de0244dc1a57e323d8160787ebb40fb64930e","skills\u002Fskill-authoring\u002Ffolder-specific-claude-and-agents-md","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002FSolizardking","https:\u002F\u002Fmusebook.trade","Got a mile high and never came down","2026-10-08 23:20:13",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":24},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Solizardking\u002Fskillhub-main --skill folder-specific-claude-and-agents-md",{"tool":40,"command":41},"bunx","bunx skills add Solizardking\u002Fskillhub-main --skill folder-specific-claude-and-agents-md",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Solizardking\u002Fskillhub-main --skill folder-specific-claude-and-agents-md","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fskill-authoring\u002Ffolder-specific-claude-and-agents-md\u002FSKILL.md",[],[48,55,62,69,76,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M78E0TGCAMNPS207BA3G07S7","zkrouter","Self-hosted OpenAI-compatible LLM router — smart tier-based routing, ZK-stamped routing decisions, mode overrides, free OpenRouter at install via the Birth bot. Save 60-80% on inference costs by routing to the cheapest capable model across 12+ OpenRouter models.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzkrouter\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M78E0R1Z8BDT6EDTHY17MTNB","zk","For custom ZK Solana programs and privacy-preserving applications to prevent double spending. Guide to integrate rent-free nullifier PDAs for double-spend prevention.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M78E0P3ZTZ1YWF8MD5MM23QE","zk-omni-messaging","Zero-knowledge omnichain messaging between Robinhood Chain and Solana using CheshireZkOmniMessenger (msgType 4) with nullifier anti-replay and the zk-omni-relayer service.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk-omni-messaging\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M78E0JXZ2PNB1896VXAGDBWD","zerion-wallet-data","Use when the user asks to check a wallet's portfolio, token balances, DeFi positions, PnL, transaction history, or NFTs. Provides interpreted on-chain data across 40+ EVM chains and Solana via x402 pay-per-request or API key — no raw RPC decoding needed.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzerion-wallet-data\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M78E0G14FH9GRRTQYMKD5E59","youtube-clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M78E0C2ZYA99CFFDNB7ZMK5S","yield-optimization","Multi-chain yield optimization via yield.xyz (StakeKit). Discover 2,988+ yield opportunities across 75+ blockchains, build deposit\u002Fwithdrawal transactions with shell scripts, and sign them with a MoonPay wallet. Use when the user wants to earn yield, find the best lending or staking rate, enter\u002Fexit a position, or check portfolio balances.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyield-optimization\u002FSKILL.md",[],[]]