[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70P049DQDPD65HRZPA0XKHN":3,"skill-same:01M70P049DQDPD65HRZPA0XKHN":73},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M70P049DQDPD65HRZPA0XKHN","patterns",null,"Use when writing or reviewing NL artifacts and need to check for anti-patterns — vague quantifiers, prohibitions without alternatives, oversized skills, write-on-read-only agents, monolithic prompts, or linter-duplicating rules.","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fpatterns\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"for","prompts","monolithic","check","artifacts","Rules","use","oversized","alternatives","read-only","nl","write","read","anti-patterns","vague","when","writing","only","linter","2026-11-10 10:12:30",false,"---\nname: patterns\ndescription: \"Use when writing or reviewing NL artifacts and need to check for anti-patterns — vague quantifiers, prohibitions without alternatives, oversized skills, write-on-read-only agents, monolithic prompts, or linter-duplicating rules.\"\nversion: 0.1.0\n---\n\n# NL Programming Patterns\n\nBest practices and anti-patterns for writing Claude Code plugin components. Each pattern includes a rationale and a concrete example. Use this skill when authoring or reviewing skills, agents, commands, rules, or hooks.\n\n---\n\n## Patterns (Use These)\n\n### P1: Trigger-Optimized Descriptions (R04)\n\nWrite agent and skill descriptions with 3+ specific trigger phrases rather than a single generic one-liner. Claude uses description text to decide when to invoke an agent; richer vocabulary improves recall.\n\n**Good:**\n```yaml\ndescription: |\n  Lints NL artifacts for quality issues. Use this agent when scoring plugin\n  components, running static analysis on prompts, checking command completeness,\n  or auditing skill descriptions for vagueness.\n```\n\n**Bad:**\n```yaml\ndescription: \"Analyzes files\"\n```\n\nThe bad example won't trigger reliably — \"analyzes files\" matches too broadly and too vaguely.\n\n---\n\n### P2: Example-Driven Agents (R09)\n\nInclude 2+ `\u003Cexample>` blocks in agent descriptions with realistic Context, user turn, and assistant response. Examples anchor the agent's behavior and dramatically improve triggering consistency.\n\n**Minimum structure per example:**\n```\n\u003Cexample>\nContext: \u003Csituation that would trigger this agent>\nuser: \u003Cwhat the user or command says>\nassistant: \u003Cwhat this agent does in response>\n\u003C\u002Fexample>\n```\n\n**Diverse scenarios:** Cover at least one user-direct invocation and one command-as-orchestrator invocation if applicable.\n\n---\n\n### P3: Imperative + Rationale Rules (R03, R21)\n\nWrite rules as \"**Do X** because Y\" not \"Don't do Z\". The Pink Elephant effect: telling someone not to think of a pink elephant makes them think of it. Prohibitions without alternatives are hard to follow under inference load.\n\n**Good:**\n```markdown\n**Use `${CLAUDE_PLUGIN_ROOT}` for all intra-plugin file references.**\n\nBecause absolute paths break when the plugin is installed by different users\nor on different machines, portable path variables ensure the plugin works\neverywhere it is installed.\n```\n\n**Bad:**\n```markdown\nDon't hardcode absolute paths in hooks or scripts.\n```\n\n---\n\n### P4: Layered Prompts (R40)\n\nStructure complex command and agent bodies in this order:\n1. Role\u002Fpersona\n2. Context (what you know, what you've been given)\n3. Task (specific action)\n4. Constraints (limits, edge cases, what to avoid)\n5. Output format (exact structure)\n\nMixing these layers — especially burying the task in the middle of constraints — reduces response quality.\n\n---\n\n### P5: Graduated Model Selection (R10)\n\nMatch model tier to task complexity:\n\n| Model | Best for |\n|-------|---------|\n| `haiku` | Parsing, formatting, file discovery, classification, pattern matching |\n| `sonnet` | Analysis, reasoning, code review, multi-step judgment, scoring |\n| `opus` | Complex judgment requiring deep synthesis, orchestration of many agents |\n\nUsing opus for a file-glob scan wastes tokens with no quality improvement. Using haiku for nuanced quality scoring produces unreliable results.\n\n---\n\n### P6: Scoped Skills (R05, R07)\n\nKeep each skill under 500 lines with a clearly bounded scope. Include a \"Scope Note\" section at the bottom stating what the skill covers and what it does NOT cover, with cross-references to related skills (`plugin:skill` format).\n\nBenefits:\n- Prevents context bloat when multiple skills are loaded simultaneously\n- Makes skills easier to update without cascading effects\n- Enables precise skill selection in agent frontmatter\n\n---\n\n### P7: Least-Privilege Tools (R11)\n\nOnly list tools in `allowed-tools` (commands) or `tools` (agents) that the body actually uses. Declaring unused tools is misleading and may grant unintended capabilities.\n\n**Good:**\n```yaml\ntools: [\"Glob\", \"Read\"]\n```\n(for a scanner that only discovers and reads files)\n\n**Bad:**\n```yaml\ntools: [\"Glob\", \"Read\", \"Write\", \"Edit\", \"Bash\", \"WebSearch\"]\n```\n(for the same scanner)\n\n---\n\n### P8: Explicit Output Formats (R12, R16, R41)\n\nEvery command and agent body should define the exact output structure. Don't leave format to inference — specify section names, table columns, score display format, and summary location.\n\n**Example output format spec in a command body:**\n```\nReport format:\n## Summary\nTotal artifacts: N | Pass (≥70): N | Fail (\u003C70): N\n\n## Results\n| File | Type | Score | Top Issues |\n|------|------|-------|------------|\n| path\u002Fto\u002Ffile.md | agent | 87 | ... |\n\n## Details\nOne subsection per file with full penalty breakdown.\n```\n\n---\n\n### P9: Error Path Coverage (R17)\n\nHandle the three failure modes explicitly in every command and agent:\n1. **Empty input** — no files found, no argument provided\n2. **Missing files** — referenced file doesn't exist\n3. **Malformed data** — YAML parse errors, invalid JSON, truncated content\n\nEach failure mode should produce a clear, actionable error message — not a silent no-op or a generic \"something went wrong.\"\n\n---\n\n## Anti-Patterns (Avoid These)\n\n### A1: Vague Quantifiers (R01)\n\nWords like \"appropriate\", \"relevant\", \"as needed\", \"sufficient\", \"adequate\", \"reasonable\" without measurable criteria are lint targets. They make rules and instructions unenforceable.\n\n**Penalty:** -2 per occurrence in NLPM scoring, capped at -20.\n\n**Fix:** Replace with specific criteria.\n- \"appropriate length\" → \"under 500 lines\"\n- \"relevant tools\" → \"only tools called in the body\"\n- \"as needed\" → \"when the input path is a directory\"\n\n---\n\n### A2: Prohibitions Without Alternatives (R03)\n\n\"Don't use X\" without explaining what to use instead violates P3 and leaves the reader with no actionable path.\n\n**Fix:** Always pair a prohibition with an alternative:\n- \"Don't hardcode paths\" → \"Use `${CLAUDE_PLUGIN_ROOT}` instead of absolute paths, because...\"\n- \"Don't use passive voice\" → \"Use imperative verbs (Use, Run, Check, Return) because they reduce ambiguity\"\n\n---\n\n### A3: Oversized Skills (R05)\n\nSkills over 500 lines become context bloat. When multiple oversized skills are loaded together, the effective context for the actual task shrinks.\n\n**Fix:** Split by responsibility. If a skill covers both \"what the schema looks like\" and \"how to evaluate quality,\" those are two skills: `conventions` and `scoring`.\n\n---\n\n### A4: Write\u002FEdit on Read-Only Agents (R11)\n\nAudit, review, and analysis agents should never declare `Write` or `Edit` in their tools list. Read-only agents that can modify files create unexpected side effects.\n\n**Principle:** Agents with names like `linter`, `scanner`, `reviewer`, `auditor`, `inspector` should be read-only. Modification is a separate agent responsibility.\n\n---\n\n### A5: Monolithic Prompts (R13, R40)\n\nA single unstructured block of instructions — no headings, no sections, no numbered steps — is hard to follow for complex tasks and produces inconsistent output.\n\n**Fix:** Use markdown headings and numbered steps. Group related instructions. Put the output format spec at the end, not the beginning.\n\n---\n\n### A6: Rules Duplicating Linters (R24)\n\nIf eslint, ruff, clippy, or another static analysis tool already catches a code-level issue, a Claude rule that re-states it is redundant noise. Rules should cover intent, architecture, and NL artifact quality — things linters can't check.\n\n**Fix:** Reference the tool instead: \"Run `ruff check` before committing — it enforces all formatting rules.\"\n\n---\n\n### A7: Agents Without Examples (R09)\n\nAn agent description with no `\u003Cexample>` blocks has unreliable triggering. Without examples, Claude must infer invocation criteria from the description alone, which degrades with ambiguous wording.\n\n**NLPM penalty:** -15 for zero examples on an agent.\n\n---\n\n### A8: Opus for Mechanical Tasks (R10)\n\nFile discovery, JSON parsing, pattern matching, line counting — these are haiku tasks. Using opus for them is a 10-30x token cost increase with no quality benefit.\n\n**Decision rule:** If the task has a deterministic correct answer that doesn't require judgment, use haiku. If it requires nuanced evaluation, use sonnet. Reserve opus for tasks where sonnet demonstrably fails.\n\n---\n\n### A9: Hardcoded Paths (R30)\n\nAbsolute paths in hooks, scripts, or plugin configs break when:\n- A different user installs the plugin\n- The project is moved\n- CI\u002FCD runs in a container\n\n**Fix:** Use `${CLAUDE_PLUGIN_ROOT}` for paths within a plugin. Use relative paths where the base is well-defined.\n\n---\n\n## Scope Note\n\nThis skill covers NL programming patterns and anti-patterns for Claude Code artifacts. It does NOT cover:\n- Exact schema fields and syntax → see `nlpm:conventions`\n- Scoring rubric with penalty tables → see `nlpm:scoring`\n- General software engineering patterns outside Claude Code\n","# NL Programming Patterns\n\nBest practices and anti-patterns for writing Claude Code plugin components. Each pattern includes a rationale and a concrete example. Use this skill when authoring or reviewing skills, agents, commands, rules, or hooks.\n\n---\n\n## Patterns (Use These)\n\n### P1: Trigger-Optimized Descriptions (R04)\n\nWrite agent and skill descriptions with 3+ specific trigger phrases rather than a single generic one-liner. Claude uses description text to decide when to invoke an agent; richer vocabulary improves recall.\n\n**Good:**\n```yaml\ndescription: |\n  Lints NL artifacts for quality issues. Use this agent when scoring plugin\n  components, running static analysis on prompts, checking command completeness,\n  or auditing skill descriptions for vagueness.\n```\n\n**Bad:**\n```yaml\ndescription: \"Analyzes files\"\n```\n\nThe bad example won't trigger reliably — \"analyzes files\" matches too broadly and too vaguely.\n\n---\n\n### P2: Example-Driven Agents (R09)\n\nInclude 2+ `\u003Cexample>` blocks in agent descriptions with realistic Context, user turn, and assistant response. Examples anchor the agent's behavior and dramatically improve triggering consistency.\n\n**Minimum structure per example:**\n```\n\u003Cexample>\nContext: \u003Csituation that would trigger this agent>\nuser: \u003Cwhat the user or command says>\nassistant: \u003Cwhat this agent does in response>\n\u003C\u002Fexample>\n```\n\n**Diverse scenarios:** Cover at least one user-direct invocation and one command-as-orchestrator invocation if applicable.\n\n---\n\n### P3: Imperative + Rationale Rules (R03, R21)\n\nWrite rules as \"**Do X** because Y\" not \"Don't do Z\". The Pink Elephant effect: telling someone not to think of a pink elephant makes them think of it. Prohibitions without alternatives are hard to follow under inference load.\n\n**Good:**\n```markdown\n**Use `${CLAUDE_PLUGIN_ROOT}` for all intra-plugin file references.**\n\nBecause absolute paths break when the plugin is installed by different users\nor on different machines, portable path variables ensure the plugin works\neverywhere it is installed.\n```\n\n**Bad:**\n```markdown\nDon't hardcode absolute paths in hooks or scripts.\n```\n\n---\n\n### P4: Layered Prompts (R40)\n\nStructure complex command and agent bodies in this order:\n1. Role\u002Fpersona\n2. Context (what you know, what you've been given)\n3. Task (specific action)\n4. Constraints (limits, edge cases, what to avoid)\n5. Output format (exact structure)\n\nMixing these layers — especially burying the task in the middle of constraints — reduces response quality.\n\n---\n\n### P5: Graduated Model Selection (R10)\n\nMatch model tier to task complexity:\n\n| Model | Best for |\n|-------|---------|\n| `haiku` | Parsing, formatting, file discovery, classification, pattern matching |\n| `sonnet` | Analysis, reasoning, code review, multi-step judgment, scoring |\n| `opus` | Complex judgment requiring deep synthesis, orchestration of many agents |\n\nUsing opus for a file-glob scan wastes tokens with no quality improvement. Using haiku for nuanced quality scoring produces unreliable results.\n\n---\n\n### P6: Scoped Skills (R05, R07)\n\nKeep each skill under 500 lines with a clearly bounded scope. Include a \"Scope Note\" section at the bottom stating what the skill covers and what it does NOT cover, with cross-references to related skills (`plugin:skill` format).\n\nBenefits:\n- Prevents context bloat when multiple skills are loaded simultaneously\n- Makes skills easier to update without cascading effects\n- Enables precise skill selection in agent frontmatter\n\n---\n\n### P7: Least-Privilege Tools (R11)\n\nOnly list tools in `allowed-tools` (commands) or `tools` (agents) that the body actually uses. Declaring unused tools is misleading and may grant unintended capabilities.\n\n**Good:**\n```yaml\ntools: [\"Glob\", \"Read\"]\n```\n(for a scanner that only discovers and reads files)\n\n**Bad:**\n```yaml\ntools: [\"Glob\", \"Read\", \"Write\", \"Edit\", \"Bash\", \"WebSearch\"]\n```\n(for the same scanner)\n\n---\n\n### P8: Explicit Output Formats (R12, R16, R41)\n\nEvery command and agent body should define the exact output structure. Don't leave format to inference — specify section names, table columns, score display format, and summary location.\n\n**Example output format spec in a command body:**\n```\nReport format:\n## Summary\nTotal artifacts: N | Pass (≥70): N | Fail (\u003C70): N\n\n## Results\n| File | Type | Score | Top Issues |\n|------|------|-------|------------|\n| path\u002Fto\u002Ffile.md | agent | 87 | ... |\n\n## Details\nOne subsection per file with full penalty breakdown.\n```\n\n---\n\n### P9: Error Path Coverage (R17)\n\nHandle the three failure modes explicitly in every command and agent:\n1. **Empty input** — no files found, no argument provided\n2. **Missing files** — referenced file doesn't exist\n3. **Malformed data** — YAML parse errors, invalid JSON, truncated content\n\nEach failure mode should produce a clear, actionable error message — not a silent no-op or a generic \"something went wrong.\"\n\n---\n\n## Anti-Patterns (Avoid These)\n\n### A1: Vague Quantifiers (R01)\n\nWords like \"appropriate\", \"relevant\", \"as needed\", \"sufficient\", \"adequate\", \"reasonable\" without measurable criteria are lint targets. They make rules and instructions unenforceable.\n\n**Penalty:** -2 per occurrence in NLPM scoring, capped at -20.\n\n**Fix:** Replace with specific criteria.\n- \"appropriate length\" → \"under 500 lines\"\n- \"relevant tools\" → \"only tools called in the body\"\n- \"as needed\" → \"when the input path is a directory\"\n\n---\n\n### A2: Prohibitions Without Alternatives (R03)\n\n\"Don't use X\" without explaining what to use instead violates P3 and leaves the reader with no actionable path.\n\n**Fix:** Always pair a prohibition with an alternative:\n- \"Don't hardcode paths\" → \"Use `${CLAUDE_PLUGIN_ROOT}` instead of absolute paths, because...\"\n- \"Don't use passive voice\" → \"Use imperative verbs (Use, Run, Check, Return) because they reduce ambiguity\"\n\n---\n\n### A3: Oversized Skills (R05)\n\nSkills over 500 lines become context bloat. When multiple oversized skills are loaded together, the effective context for the actual task shrinks.\n\n**Fix:** Split by responsibility. If a skill covers both \"what the schema looks like\" and \"how to evaluate quality,\" those are two skills: `conventions` and `scoring`.\n\n---\n\n### A4: Write\u002FEdit on Read-Only Agents (R11)\n\nAudit, review, and analysis agents should never declare `Write` or `Edit` in their tools list. Read-only agents that can modify files create unexpected side effects.\n\n**Principle:** Agents with names like `linter`, `scanner`, `reviewer`, `auditor`, `inspector` should be read-only. Modification is a separate agent responsibility.\n\n---\n\n### A5: Monolithic Prompts (R13, R40)\n\nA single unstructured block of instructions — no headings, no sections, no numbered steps — is hard to follow for complex tasks and produces inconsistent output.\n\n**Fix:** Use markdown headings and numbered steps. Group related instructions. Put the output format spec at the end, not the beginning.\n\n---\n\n### A6: Rules Duplicating Linters (R24)\n\nIf eslint, ruff, clippy, or another static analysis tool already catches a code-level issue, a Claude rule that re-states it is redundant noise. Rules should cover intent, architecture, and NL artifact quality — things linters can't check.\n\n**Fix:** Reference the tool instead: \"Run `ruff check` before committing — it enforces all formatting rules.\"\n\n---\n\n### A7: Agents Without Examples (R09)\n\nAn agent description with no `\u003Cexample>` blocks has unreliable triggering. Without examples, Claude must infer invocation criteria from the description alone, which degrades with ambiguous wording.\n\n**NLPM penalty:** -15 for zero examples on an agent.\n\n---\n\n### A8: Opus for Mechanical Tasks (R10)\n\nFile discovery, JSON parsing, pattern matching, line counting — these are haiku tasks. Using opus for them is a 10-30x token cost increase with no quality benefit.\n\n**Decision rule:** If the task has a deterministic correct answer that doesn't require judgment, use haiku. If it requires nuanced evaluation, use sonnet. Reserve opus for tasks where sonnet demonstrably fails.\n\n---\n\n### A9: Hardcoded Paths (R30)\n\nAbsolute paths in hooks, scripts, or plugin configs break when:\n- A different user installs the plugin\n- The project is moved\n- CI\u002FCD runs in a container\n\n**Fix:** Use `${CLAUDE_PLUGIN_ROOT}` for paths within a plugin. Use relative paths where the base is well-defined.\n\n---\n\n## Scope Note\n\nThis skill covers NL programming patterns and anti-patterns for Claude Code artifacts. It does NOT cover:\n- Exact schema fields and syntax → see `nlpm:conventions`\n- Scoring rubric with penalty tables → see `nlpm:scoring`\n- General software engineering patterns outside Claude Code\n",{"name":5,"version":48,"description":7},"0.1.0","main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fpatterns",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill patterns",{"tool":65,"command":66},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill patterns",{"tool":68,"command":69},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fpatterns\u002FSKILL.md",true,[],[74,83,91,99,107,115],{"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":15,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":82},"01M73H7XKBHE1ETQDZT94MF9HH","seedance-prompt-en","Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":82},"01M73GRE9998Q1DZWC71N41JWG","onepage-pdf","Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file\u002Freport\u002Fproposal into a \"single-page PDF\", \"long PDF\", \"不分页 PDF\", \"单页 PDF\", \"长图式 PDF\", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":82},"01M73GQG1KZDADVPV3MHAT1J5A","native-feel-cross-platform-desktop","Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include \"cross-platform desktop\", \"Electron alternative\", \"Tauri vs native\", \"WebView wrapper\", \"near-native performance\", \"Raycast architecture\", \"WebKit\u002FWebView2 quirks\", \"WKWebView\", \"system tray app\", \"global hotkey app\", \"launcher app\". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":82},"01M73G87PDNSMKG2FHWCYER6N8","gstack","Router for the gstack skill suite. (gstack)","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":82},"01M73G3EAQWKCM8DB8D0N0QSVG","fireworks-tech-graph","Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent\u002Fmemory, or concept map - and export as SVG+PNG. Trigger on: \"画图\" \"帮我画\" \"生成图\" \"做个图\" \"架构图\" \"流程图\" \"可视化一下\" \"出图\" \"generate diagram\" \"draw diagram\" \"visualize\" or any system\u002Fflow description the user wants illustrated.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":82},"01M73G086AXAH9DW1H5G5N3CPB","dbs-video-extract","接收抖音、小红书、微信视频号等短视频链接或分享文案，查询作品／账号数据并提取语音文字稿，按作者和标题归档为 Markdown。用户希望完整解析短视频、取得数据或文字稿时使用；运行前检查 TikHub 与轻抖使用凭证，缺少时用新手能理解的方式引导购买和安全配置。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fdbs-video-extract\u002FSKILL.md",[],[]]