[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FF5C64GFTHDV4SETJG3EN8":3,"skill-same:01M7FF5C64GFTHDV4SETJG3EN8":50},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7FF5C64GFTHDV4SETJG3EN8","keyword-extractor",null,"Extracts up to 50 highly relevant SEO keywords from text. Use when user wants to generate or extract keywords for given text.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fkeyword-extractor\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: keyword-extractor\ndescription: >\n  Extracts up to 50 highly relevant SEO keywords from text. Use when user wants to generate or extract keywords for given text.\nrisk: safe\nsource: original\ndate_added: \"2026-03-11\"\n---\n\n# Keyword Extractor\n\nExtracts **max 50 relevant keywords** from text and formats them in a strict machine-ready structure.\n\n---\n\n## QUICK START\n\nJump to any section:\n1. [CORE MANDATE](#core-mandate) – Output rules and formatting \n2. [WHEN TO USE](#when-to-use) – Trigger conditions for this skill \n3. [KEYWORD QUALITY RULES](#keyword-quality-rules) – Priorities and forbidden keywords \n4. [WORKFLOW](#workflow) – Step-by-step generation and processing \n5. [FAILURE HANDLING](#failure-handling) – Short text or edge cases \n\n---\n\n# CORE MANDATE\n\nReturn **exactly one comma-separated line** of keywords, following these rules:\n- max 50 keywords  \n- ordered by relevance  \n- all lowercase  \n- no duplicates or near-duplicates  \n- mix of single words and 2–4 word phrases  \n- no numbering, bullets, explanations, or trailing period\n\n---\n\n## When to Use\nUse this skill when the user wants to generate or extract **SEO-friendly keywords or tags** from text including:\n- Extracting keywords or tags for any given text or paragraph  \n- Creating **comma-separated keywords or tags** suitable for SEO, search, or metadata  \n- Generating topic-specific keywords or tags based on the content’s main subjects and concepts  \n\nThis skill should be triggered for **all text-based keyword extraction requests**, regardless of phrasing, as long as the goal is SEO, tagging, or metadata generation.\n\nDo NOT trigger this skill for:  \n- Summaries or paraphrasing requests  \n- Text analysis without keyword generation\n\n---\n\n# KEYWORD QUALITY RULES\n\nPrefer noun phrases over verbs or adjectives.\nPrefer keywords useful for:\n- SEO and search\n- tagging\n- metadata\n\nPrioritize:\n- domain terminology\n- meaningful nouns\n- search phrases\n- entities\n- technical concepts\n\nAvoid weak keywords like:\n- things and various topics\n- general concepts\n- important ideas\n- methods\n\n**IMPORTANT: Each keyword must strictly represent a phrase that a user would type into a search engine**\n\n---\n\n# WORKFLOW\n\n## Step 1 — Analyze\n\nIdentify:\n- main subject\n- key topics\n- domain terminology\n- entities\n- concepts\n\nIgnore filler words.\n\n---\n\n## Step 2 — Generate Keywords\n\nGenerate up to 50 strictly SEO-friendly keywords directly from the text.\n\nInclude:\n- core topics\n- domain terminology\n- related concepts\n- common search queries\n\nAllowed formats:\n- single words\n- 2 word phrases\n- 3 word phrases\n- 4 word phrases\n\nExample:\n```machine learning, neural networks, deep learning models, ai algorithms, data science tools```\n\nAvoid vague keywords, filler phrases, adjectives without nouns like:\n```important methods, different ideas, various techniques, things```\n\nKeywords must not exceed 4 words.\n\n---\n\n## Step 3 — Rank\n\nOrder keywords by SEO importance using these signals:\n1. main topic of the text\n2. high-value domain terminology\n3. technologies, tools, or entities mentioned\n4. common search queries related to the topic\n5. supporting contextual topics\n\nMost important keywords should always appear first.\n\n---\n\n## Step 4 — Normalize\n\nEnsure:\n- lowercase, comma separated, no duplicates\n- ≤50 keywords\n- Remove near-duplicate keywords that represent the same concept.\n- Keep only the most common search phrase.\n- If two keywords represent the same concept, keep only the more common search phrase.\n\n---\n\n## Step 5 — Validate\n\nBefore returning output ensure:\n- keyword_count \u003C= 50\n- no duplicates and near-duplicates\n- all lowercase and comma separated\n- no trailing period\n- each keyword is a clear searchable topic\n- keywords do not exceed 4 words\n\nIf any rule fails regenerate the list.\n\n---\n\n# FAILURE HANDLING\n\nIf text is very short, infer likely topics and still generate keywords. Never exceed 50 keywords.\n\n---\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","# Keyword Extractor\n\nExtracts **max 50 relevant keywords** from text and formats them in a strict machine-ready structure.\n\n---\n\n## QUICK START\n\nJump to any section:\n1. [CORE MANDATE](#core-mandate) – Output rules and formatting \n2. [WHEN TO USE](#when-to-use) – Trigger conditions for this skill \n3. [KEYWORD QUALITY RULES](#keyword-quality-rules) – Priorities and forbidden keywords \n4. [WORKFLOW](#workflow) – Step-by-step generation and processing \n5. [FAILURE HANDLING](#failure-handling) – Short text or edge cases \n\n---\n\n# CORE MANDATE\n\nReturn **exactly one comma-separated line** of keywords, following these rules:\n- max 50 keywords  \n- ordered by relevance  \n- all lowercase  \n- no duplicates or near-duplicates  \n- mix of single words and 2–4 word phrases  \n- no numbering, bullets, explanations, or trailing period\n\n---\n\n## When to Use\nUse this skill when the user wants to generate or extract **SEO-friendly keywords or tags** from text including:\n- Extracting keywords or tags for any given text or paragraph  \n- Creating **comma-separated keywords or tags** suitable for SEO, search, or metadata  \n- Generating topic-specific keywords or tags based on the content’s main subjects and concepts  \n\nThis skill should be triggered for **all text-based keyword extraction requests**, regardless of phrasing, as long as the goal is SEO, tagging, or metadata generation.\n\nDo NOT trigger this skill for:  \n- Summaries or paraphrasing requests  \n- Text analysis without keyword generation\n\n---\n\n# KEYWORD QUALITY RULES\n\nPrefer noun phrases over verbs or adjectives.\nPrefer keywords useful for:\n- SEO and search\n- tagging\n- metadata\n\nPrioritize:\n- domain terminology\n- meaningful nouns\n- search phrases\n- entities\n- technical concepts\n\nAvoid weak keywords like:\n- things and various topics\n- general concepts\n- important ideas\n- methods\n\n**IMPORTANT: Each keyword must strictly represent a phrase that a user would type into a search engine**\n\n---\n\n# WORKFLOW\n\n## Step 1 — Analyze\n\nIdentify:\n- main subject\n- key topics\n- domain terminology\n- entities\n- concepts\n\nIgnore filler words.\n\n---\n\n## Step 2 — Generate Keywords\n\nGenerate up to 50 strictly SEO-friendly keywords directly from the text.\n\nInclude:\n- core topics\n- domain terminology\n- related concepts\n- common search queries\n\nAllowed formats:\n- single words\n- 2 word phrases\n- 3 word phrases\n- 4 word phrases\n\nExample:\n```machine learning, neural networks, deep learning models, ai algorithms, data science tools```\n\nAvoid vague keywords, filler phrases, adjectives without nouns like:\n```important methods, different ideas, various techniques, things```\n\nKeywords must not exceed 4 words.\n\n---\n\n## Step 3 — Rank\n\nOrder keywords by SEO importance using these signals:\n1. main topic of the text\n2. high-value domain terminology\n3. technologies, tools, or entities mentioned\n4. common search queries related to the topic\n5. supporting contextual topics\n\nMost important keywords should always appear first.\n\n---\n\n## Step 4 — Normalize\n\nEnsure:\n- lowercase, comma separated, no duplicates\n- ≤50 keywords\n- Remove near-duplicate keywords that represent the same concept.\n- Keep only the most common search phrase.\n- If two keywords represent the same concept, keep only the more common search phrase.\n\n---\n\n## Step 5 — Validate\n\nBefore returning output ensure:\n- keyword_count \u003C= 50\n- no duplicates and near-duplicates\n- all lowercase and comma separated\n- no trailing period\n- each keyword is a clear searchable topic\n- keywords do not exceed 4 words\n\nIf any rule fails regenerate the list.\n\n---\n\n# FAILURE HANDLING\n\nIf text is very short, infer likely topics and still generate keywords. Never exceed 50 keywords.\n\n---\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":24,"source":25,"date_added":26,"description":27},"safe","original","2026-03-11","Extracts up to 50 highly relevant SEO keywords from text. Use when user wants to generate or extract keywords for given text.\n","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","07-后端与架构\u002Fkeyword-extractor",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill keyword-extractor",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill keyword-extractor",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill keyword-extractor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fkeyword-extractor\u002FSKILL.md",true,[],[51,58,63,70,77,84],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":59,"name":53,"nameZh":6,"description":54,"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},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\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":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\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},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]