[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ESTPTFZ3R4D2P4WGDDW6VP":3,"skill-same:01M7ESTPTFZ3R4D2P4WGDDW6VP":46},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7ESTPTFZ3R4D2P4WGDDW6VP","skills-social",null,"Regenerate a shareable JSON catalog of the user's skills — one entry per skill in ~\u002Fdotfiles\u002Fskills with a category, a short tagline, a trigger phrase and its slash invocation, ready to render as a social-media card. Use when the user wants to refresh, update, regenerate, share, or export their skills list, asks for the skills social media JSON or skills catalog JSON, or wants a shareable overview of the skills they have built.","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\u002F04-安全渗透\u002Fskills-social\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skills-social\ndescription: >\n  Regenerate a shareable JSON catalog of the user's skills — one entry per skill in\n  ~\u002Fdotfiles\u002Fskills with a category, a short tagline, a trigger phrase and its slash\n  invocation, ready to render as a social-media card. Use when the user wants to refresh,\n  update, regenerate, share, or export their skills list, asks for the skills social media\n  JSON or skills catalog JSON, or wants a shareable overview of the skills they have built.\n---\n\n# Skills Social JSON\n\nRead every skill in the skills folder and write a catalog JSON built for sharing: one\nentry per skill, each with a fixed category, a one-line tagline, the moment you would\nreach for it, and its slash invocation. Never edit a `SKILL.md` — this skill writes\nexactly one file.\n\n## Inputs\n\nDefaults; each is overridable by invocation args.\n\n- **Skills root**: the directory containing this skill — `~\u002Fdotfiles\u002Fskills`\n- **Source of truth**: `\u003Croot>\u002F*\u002FSKILL.md`. Enumerate those directories, never the\n  symlinks in `~\u002F.claude\u002Fskills` or `~\u002F.cursor\u002Fskills-cursor` — those go stale when a\n  skill is renamed\n- **Output**: `\u003Croot>\u002Fskills-social.json`\n- **Author**: `git config user.name` — never hardcode\n\n## Phase 1 — Collect the skills\n\n1. List every `\u003Croot>\u002F*\u002FSKILL.md`. Each one is an entry, including `skills-social` itself.\n2. Read the `name` and `description` frontmatter of each. `name` must equal the directory\n   name — report a mismatch rather than silently trusting either.\n3. Note any skill carrying `disable-model-invocation: true`; its `trigger` says when the\n   user runs it, not when it fires automatically.\n\n## Phase 2 — Categorize\n\nAssign exactly one category from this fixed vocabulary, so the rendered image can\ncolor-code consistently. Do not invent a new value — widen an existing category instead.\n\n| category | covers | current members |\n| --- | --- | --- |\n| `git-workflow` | branches, commits, PRs | `reviewable-commits`, `stacked-pr-splitter`, `branch-test-plan` |\n| `code-quality` | how code gets written and changed | `branch-comment-cleanup`, `minimal-code-changes` |\n| `web-audit` | shipping a page or site | `a11y-page-audit`, `prod-page-audit` |\n| `tooling` | environment, docs, config plumbing | `context7-mcp`, `env-example-sync` |\n| `meta` | skills and dotfiles about themselves | `skills-audit`, `skill-best-practices-sync`, `shell-aliases-social`, `skills-social` |\n\n## Phase 3 — Write the taglines\n\nRewrite each frontmatter description into image copy. The frontmatter is trigger bait for\nthe model — never copy it verbatim.\n\n- `description`: one sentence, at most 80 characters, present tense, stating the outcome\n  (\"Turns a branch diff into a manual QA plan\"). No \"Use when…\", no \"This skill\".\n- `trigger`: at most six words naming the moment (\"before opening a PR\"). Lowercase, no\n  trailing period.\n- `invocation`: `\u002F\u003Cname>`.\n\n## Phase 4 — Write the JSON\n\n```json\n{\n  \"meta\": {\n    \"author\": \"\u003Cfrom git config user.name>\",\n    \"source\": \"~\u002Fdotfiles\u002Fskills\",\n    \"generated\": \"YYYY-MM-DD\",\n    \"count\": 13\n  },\n  \"entries\": [\n    {\n      \"name\": \"branch-test-plan\",\n      \"category\": \"git-workflow\",\n      \"description\": \"Turns a branch diff into a manual QA plan with regression checks\",\n      \"trigger\": \"before opening a PR\",\n      \"invocation\": \"\u002Fbranch-test-plan\"\n    }\n  ]\n}\n```\n\nSort `entries` by category in the vocabulary order above, then by `name`, so regenerating\nproduces a stable diff. Two-space indent, trailing newline.\n\n## Phase 5 — Verify\n\n1. Valid JSON: `python3 -c \"import json;json.load(open('skills-social.json'))\"`.\n2. `meta.count` equals the number of `entries` equals the number of `*\u002FSKILL.md`\n   directories under the root.\n3. Every `category` is in the fixed vocabulary, and no `description` exceeds 80\n   characters.\n4. No private paths, hostnames, project IDs or credentials leaked out of any `SKILL.md` —\n   the output is committed to a public repo.\n\n## Report\n\nCompare against the previous version of the file and print:\n\n```\n## Skills social — \u003Cdate>\n\n### Added\n- \u003Cskill — category assigned>\n\n### Removed\n- \u003Cskill — no longer in the folder>\n\n### Updated\n- \u003Cskill — what changed: category, tagline, or trigger>\n\n### Still needs human attention\n- \u003Cname\u002Fdirectory mismatches, skills that resisted a one-line tagline>\n```\n\n## Notes & edge cases\n\n- **A skill fits no category**: widen the closest category's scope rather than adding a\n  value; add one only when three or more skills would share it, and say so in the report.\n- **Stale symlinks**: `~\u002F.claude\u002Fskills` can hold dangling links to renamed skills — never\n  enumerate from there.\n- **Self-inclusion**: `skills-social` appears in its own output.\n- **Image generation**: out of scope. The JSON is the deliverable, mirroring\n  `zsh\u002Fshell-aliases-social.json` and the image rendered from it.\n","# Skills Social JSON\n\nRead every skill in the skills folder and write a catalog JSON built for sharing: one\nentry per skill, each with a fixed category, a one-line tagline, the moment you would\nreach for it, and its slash invocation. Never edit a `SKILL.md` — this skill writes\nexactly one file.\n\n## Inputs\n\nDefaults; each is overridable by invocation args.\n\n- **Skills root**: the directory containing this skill — `~\u002Fdotfiles\u002Fskills`\n- **Source of truth**: `\u003Croot>\u002F*\u002FSKILL.md`. Enumerate those directories, never the\n  symlinks in `~\u002F.claude\u002Fskills` or `~\u002F.cursor\u002Fskills-cursor` — those go stale when a\n  skill is renamed\n- **Output**: `\u003Croot>\u002Fskills-social.json`\n- **Author**: `git config user.name` — never hardcode\n\n## Phase 1 — Collect the skills\n\n1. List every `\u003Croot>\u002F*\u002FSKILL.md`. Each one is an entry, including `skills-social` itself.\n2. Read the `name` and `description` frontmatter of each. `name` must equal the directory\n   name — report a mismatch rather than silently trusting either.\n3. Note any skill carrying `disable-model-invocation: true`; its `trigger` says when the\n   user runs it, not when it fires automatically.\n\n## Phase 2 — Categorize\n\nAssign exactly one category from this fixed vocabulary, so the rendered image can\ncolor-code consistently. Do not invent a new value — widen an existing category instead.\n\n| category | covers | current members |\n| --- | --- | --- |\n| `git-workflow` | branches, commits, PRs | `reviewable-commits`, `stacked-pr-splitter`, `branch-test-plan` |\n| `code-quality` | how code gets written and changed | `branch-comment-cleanup`, `minimal-code-changes` |\n| `web-audit` | shipping a page or site | `a11y-page-audit`, `prod-page-audit` |\n| `tooling` | environment, docs, config plumbing | `context7-mcp`, `env-example-sync` |\n| `meta` | skills and dotfiles about themselves | `skills-audit`, `skill-best-practices-sync`, `shell-aliases-social`, `skills-social` |\n\n## Phase 3 — Write the taglines\n\nRewrite each frontmatter description into image copy. The frontmatter is trigger bait for\nthe model — never copy it verbatim.\n\n- `description`: one sentence, at most 80 characters, present tense, stating the outcome\n  (\"Turns a branch diff into a manual QA plan\"). No \"Use when…\", no \"This skill\".\n- `trigger`: at most six words naming the moment (\"before opening a PR\"). Lowercase, no\n  trailing period.\n- `invocation`: `\u002F\u003Cname>`.\n\n## Phase 4 — Write the JSON\n\n```json\n{\n  \"meta\": {\n    \"author\": \"\u003Cfrom git config user.name>\",\n    \"source\": \"~\u002Fdotfiles\u002Fskills\",\n    \"generated\": \"YYYY-MM-DD\",\n    \"count\": 13\n  },\n  \"entries\": [\n    {\n      \"name\": \"branch-test-plan\",\n      \"category\": \"git-workflow\",\n      \"description\": \"Turns a branch diff into a manual QA plan with regression checks\",\n      \"trigger\": \"before opening a PR\",\n      \"invocation\": \"\u002Fbranch-test-plan\"\n    }\n  ]\n}\n```\n\nSort `entries` by category in the vocabulary order above, then by `name`, so regenerating\nproduces a stable diff. Two-space indent, trailing newline.\n\n## Phase 5 — Verify\n\n1. Valid JSON: `python3 -c \"import json;json.load(open('skills-social.json'))\"`.\n2. `meta.count` equals the number of `entries` equals the number of `*\u002FSKILL.md`\n   directories under the root.\n3. Every `category` is in the fixed vocabulary, and no `description` exceeds 80\n   characters.\n4. No private paths, hostnames, project IDs or credentials leaked out of any `SKILL.md` —\n   the output is committed to a public repo.\n\n## Report\n\nCompare against the previous version of the file and print:\n\n```\n## Skills social — \u003Cdate>\n\n### Added\n- \u003Cskill — category assigned>\n\n### Removed\n- \u003Cskill — no longer in the folder>\n\n### Updated\n- \u003Cskill — what changed: category, tagline, or trigger>\n\n### Still needs human attention\n- \u003Cname\u002Fdirectory mismatches, skills that resisted a one-line tagline>\n```\n\n## Notes & edge cases\n\n- **A skill fits no category**: widen the closest category's scope rather than adding a\n  value; add one only when three or more skills would share it, and say so in the report.\n- **Stale symlinks**: `~\u002F.claude\u002Fskills` can hold dangling links to renamed skills — never\n  enumerate from there.\n- **Self-inclusion**: `skills-social` appears in its own output.\n- **Image generation**: out of scope. The JSON is the deliverable, mirroring\n  `zsh\u002Fshell-aliases-social.json` and the image rendered from it.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fskills-social",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":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill skills-social",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill skills-social",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill skills-social","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fskills-social\u002FSKILL.md",true,[],[47,55,60,67,74,81],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"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",[],[],"2026-11-16 10:05:34",{"skillNo":56,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":54},"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":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":54},"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":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":54},"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":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":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":54},"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":54},"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",[],[]]