[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F8AWM5YMSRPSZPBVT97EAA":3,"skill-same:01M6F8AWM5YMSRPSZPBVT97EAA":123},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":36,"publishedAt":57,"linkOnly":58,"markdownContent":59,"markdownBody":60,"frontMatter":61,"refName":44,"commitSha":73,"skillDirectory":74,"forksCount":75,"repositoryHtmlUrl":76,"repositoryHomepageUrl":6,"ownerHtmlUrl":77,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":78,"install":79,"resources":92},"01M6F8AWM5YMSRPSZPBVT97EAA","linkedin-content-generator",null,"AI-powered LinkedIn content suite: generate posts, carousels, newsletters, and 30-day calendars with niche-specific SEO rules and a feedback-based personal memory system.","boisenoise\u002Fskills-collections","boisenoise","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F193180?v=4","01M6CDBDQK6BDN55ZMA6B6PKBM","01M6CDBDVSJ3JPTBYN26FZ7TZK",12,"MIT","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002FSKILL.md",[17,22,25,28,33],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":29,"categoryName":30,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",{"categoryNo":34,"categoryName":35,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000036","内容创作者",[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56],"content","linkedin content generator","generator","linkedin content","linkedin","Media","community","main","social","creation","critical","memory system","niche","copywriting","posts","content-creation","carousel","content-calendar","feedback-based","memory","2026-11-10 10:12:30",false,"---\nname: linkedin-content-generator\ndescription: \"AI-powered LinkedIn content suite: generate posts, carousels, newsletters, and 30-day calendars with niche-specific SEO rules and a feedback-based personal memory system.\"\ncategory: marketing\nrisk: critical\nsource: community\nsource_repo: sarveshtalele\u002Flinkedin-content-skill\nsource_type: community\ndate_added: \"2026-06-04\"\nauthor: sarveshkishortalele\ntags: [linkedin, content-creation, social-media, marketing, newsletter, carousel, content-calendar, feedback-based, seo, copywriting]\ntools: [claude]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fsarveshtalele\u002Flinkedin-content-skill\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# LinkedIn Content Generator\n\n## Overview\n\nA full LinkedIn content-creation suite for Claude Code that turns a topic and niche into\npublish-ready posts, multi-slide carousels, long-form newsletter editions, and 30-day content\ncalendars — all wired through a personal feedback-based memory system so later prompts can reflect your feedback; improvement is not guaranteed.\n\nSeven coordinated commands cover the full content workflow:\n\n| Command | Purpose |\n|---|---|\n| `\u002Fgenerate-post` | Single ready-to-publish LinkedIn post |\n| `\u002Fgenerate-carousel` | Numbered slide content + caption |\n| `\u002Fgenerate-newsletter` | Long-form newsletter edition |\n| `\u002Fgenerate-calendar` | 30-day posting calendar with Markdown table |\n| `\u002Fshow-memory` | Display current preferences and feedback log |\n| `\u002Ffeedback` | Save what worked for future outputs |\n| `\u002Fclear-memory` | Reset memory to factory defaults |\n\nAll helper scripts are bundled inside `skills\u002Flinkedin-content-generator\u002Fscripts\u002F` and ship\nalongside this `SKILL.md`. They build richly engineered prompts, inject your saved\npreferences, and suggest editorial conventions before Claude generates output.\nA local `memory.md` file persists your style, tone, successful hooks, and top-performing\nformats across every session.\n\n## When to Use This Skill\n\n- Use when you need a ready-to-paste LinkedIn post with SEO-optimised hooks and hashtags.\n- Use when building a multi-slide carousel deck for LinkedIn Documents.\n- Use when writing a long-form LinkedIn Newsletter edition with structured sections.\n- Use when planning an entire month of content with format variety and pacing rules.\n- Use when you want content that adapts to your personal voice over time via saved feedback.\n- Use when working in any niche (AI, SaaS, Marketing, Finance, Healthcare, etc.) and need\n  platform-native formatting that avoids common LinkedIn algorithmic pitfalls.\n\n## Prerequisites\n\n**Python 3.8 or later** must be available in your shell path.\n\nThe skill is self-contained. Install it from the Agentic Awesome Skills library:\n\n```bash\n# Install via antigravity CLI (recommended)\nnpx antigravity-awesome-skills --skill linkedin-content-generator\n\n# Or copy manually into your Claude Code skills directory\ncp -r skills\u002Flinkedin-content-generator ~\u002F.claude\u002Fskills\u002F\n```\n\nAll six Python scripts and the default `memory.md` are bundled inside the\n`scripts\u002F` subdirectory of this skill. No additional cloning or downloads are required.\nNo API keys, external services, or network access are needed.\n\n## How It Works\n\n### Architecture\n\n```\nUser command (\u002Fgenerate-post ...)\n        │\n        ▼\nSKILL.md parses $ARGUMENTS\n        │\n        ▼\nPython script builds prompt\n  • Injects LinkedIn SEO rules\n  • Injects memory.md preferences\n        │\n        ▼\nClaude generates publish-ready output\n        │\n        ▼\n\u002Ffeedback saves what worked → memory.md\n        (loop — every future output improves)\n```\n\n### Step 1: Set Up Your Niche (One-Time)\n\nOpen `~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002Fmemory.md` and update the\n**Primary Niche** field:\n\n```markdown\n## Core Identity & Tone\n- **Primary Niche:** AI & Technology   ← change this\n```\n\nThis field is injected into every prompt. Without it, the skill defaults to\n`\"AI & Technology\"`.\n\n### Step 2: Generate Content\n\nRun any of the seven commands described in the **Commands Reference** section below.\nClaude reads the script output and produces the final content directly in the chat.\n\n### Step 3: Save What Works\n\nAfter each output, save successful patterns with `\u002Ffeedback`:\n\n```\n\u002Ffeedback the storytelling hook in this post got 3x more comments than usual\n```\n\nThe feedback is appended to `memory.md` and automatically injected into all future\ngeneration prompts.\n\n## Commands Reference\n\n### `\u002Fgenerate-post` — Single LinkedIn Post\n\nGenerates a scroll-stopping, SEO-optimised LinkedIn text post.\n\n**Usage:**\n```\n\u002Fgenerate-post \u003Ctopic> [in \u003Cniche>] [tone: controversial|storytelling|educational|motivational|professional]\n```\n\n**Parameters:**\n\n| Parameter | Default | Options |\n|---|---|---|\n| `topic` | required | any subject |\n| `niche` | `\"AI & Technology\"` | any industry |\n| `tone` | `professional` | `professional` · `storytelling` · `controversial` · `educational` · `motivational` |\n| `style` | `list-based` | `list-based` · `text-only` · `storytelling` · `data-driven` · `contrarian` |\n\n**Examples:**\n\n```\n\u002Fgenerate-post why most developers fail at time management in Software Engineering tone: storytelling\n```\n\n```\n\u002Fgenerate-post the real cost of technical debt in SaaS tone: controversial\n```\n\n```\n\u002Fgenerate-post 5 things I wish I knew before my first startup in Entrepreneurship tone: educational style: list-based\n```\n\n**Output structure:**\n1. Scroll-stopping hook (2 lines, triggers \"see more\")\n2. Context \u002F problem setup (2–3 short sentences)\n3. Core value (numbered list or bullets, max 7 items)\n4. Key takeaway (1–2 punchy sentences)\n5. Specific call to action\n6. 3–5 hashtags (broad + niche + community mix)\n\n---\n\n### `\u002Fgenerate-carousel` — LinkedIn Carousel\n\nGenerates numbered slide content plus a ready-to-use LinkedIn caption.\n\n**Usage:**\n```\n\u002Fgenerate-carousel \u003Ctopic> [in \u003Cniche>] [\u003Cn> slides] [style: how-to|listicle|myth-busting|framework|story-arc]\n```\n\n**Parameters:**\n\n| Parameter | Default | Options |\n|---|---|---|\n| `topic` | required | any subject |\n| `niche` | `\"AI & Technology\"` | any industry |\n| `slides` | `7` | `3`–`12` |\n| `style` | `listicle` | `how-to` · `listicle` · `myth-busting` · `framework` · `story-arc` |\n\n**Style guide:**\n\n| Style | Structure |\n|---|---|\n| `how-to` | Slide 1 = problem → slides 2–N = steps → last = result \u002F CTA |\n| `listicle` | Each slide = one item with bold title + 1–2 sentence explanation |\n| `myth-busting` | Each slide = `MYTH: [belief]` → `TRUTH: [reality]` |\n| `framework` | Introduce a proprietary framework; each slide = one component |\n| `story-arc` | Slide 1 = before → middle = journey → last = after + CTA |\n\n**Examples:**\n\n```\n\u002Fgenerate-carousel 10 prompt engineering mistakes 8 slides style: myth-busting\n```\n\n```\n\u002Fgenerate-carousel building a second brain in Knowledge Management 7 slides style: how-to\n```\n\n```\n\u002Fgenerate-carousel the PARA method for productivity in Personal Development style: framework\n```\n\n**Output:** Slides numbered `1` through `N`, followed by a LinkedIn caption with hook,\nteaser context, \"Swipe →\" prompt, and hashtags.\n\n---\n\n### `\u002Fgenerate-newsletter` — LinkedIn Newsletter Edition\n\nGenerates a complete long-form newsletter edition structured for the LinkedIn Newsletter\neditor.\n\n**Usage:**\n```\n\u002Fgenerate-newsletter \u003Ctopic> [in \u003Cniche>] [length: short|medium|long] [title: \"\u003Cseries title>\"]\n```\n\n**Parameters:**\n\n| Parameter | Default | Options |\n|---|---|---|\n| `topic` | required | any subject |\n| `niche` | `\"AI & Technology\"` | any industry |\n| `length` | `medium` | `short` (~700 w) · `medium` (~1,200 w) · `long` (~2,000 w) |\n| `title` | auto-generated | optional series name |\n\n**Examples:**\n\n```\n\u002Fgenerate-newsletter how AI is reshaping hiring in HR & Recruiting length: medium\n```\n\n```\n\u002Fgenerate-newsletter the state of developer tools in 2026 in DevTools length: long title: \"Build Layer Weekly\"\n```\n\n**Output structure:**\n1. SEO-optimised H1 headline\n2. Opening hook (personal anecdote, statistic, or bold claim)\n3. Body sections with H2 subheadings\n4. Key takeaways (3–5 bullets)\n5. One specific action step for this week\n6. Engagement question to spark comments\n\n---\n\n### `\u002Fgenerate-calendar` — 30-Day Content Calendar\n\nGenerates a Markdown table calendar with monthly theme, SEO keywords, and format breakdown.\n\n**Usage:**\n```\n\u002Fgenerate-calendar [niche: \u003Cniche>] [days: \u003Cn>] [frequency: \u003Cfreq>] [goal: awareness|engagement|leads|authority|growth]\n```\n\n**Parameters:**\n\n| Parameter | Default | Options |\n|---|---|---|\n| `niche` | required | any industry |\n| `days` | `30` | any positive integer |\n| `frequency` | `\"3 times a week\"` | any posting cadence |\n| `goal` | `growth` | `awareness` · `engagement` · `leads` · `authority` · `growth` |\n\n**Goal guide:**\n\n| Goal | Strategy |\n|---|---|\n| `awareness` | Shareable, relatable, trending; heavy on carousels and contrarian takes |\n| `engagement` | Opinion posts, polls, questions, storytelling to maximise comments |\n| `leads` | Educational value posts + authority-building + clear DM CTAs |\n| `authority` | Deep insights, data-backed posts, thought leadership, newsletters |\n| `growth` | Mix viral formats (carousels, lists, contrarian) with high-value education |\n\n**Examples:**\n\n```\n\u002Fgenerate-calendar niche: Fintech days: 30 frequency: daily goal: authority\n```\n\n```\n\u002Fgenerate-calendar niche: Marketing Agencies days: 14 frequency: 5 times a week goal: leads\n```\n\n**Output:** Markdown table (`# | Day | Format | Topic \u002F Angle | Hook | CTA`) + monthly theme +\ntop 5 SEO keywords + format breakdown summary.\n\n---\n\n### `\u002Fshow-memory` — Display Preferences\n\nDisplays current memory contents: niche, tone, style, and all saved feedback entries.\n\n**Usage:**\n```\n\u002Fshow-memory\n```\n\n**Output:** Full `memory.md` content with entry count, primary niche, and tone summary.\n\n---\n\n### `\u002Ffeedback` — Save Successful Patterns\n\nAppends a labelled feedback entry to `memory.md`. Future outputs automatically incorporate\nsaved patterns.\n\n**Usage:**\n```\n\u002Ffeedback \u003Cwhat worked well>\n```\n\n**Examples:**\n\n```\n\u002Ffeedback the contrarian hook \"everyone is wrong about X\" drove 400% more impressions\n```\n\n```\n\u002Ffeedback myth-busting carousels in the DevOps niche get 3x more saves than listicles\n```\n\n```\n\u002Ffeedback storytelling tone with a personal failure story outperforms data-driven in my audience\n```\n\n---\n\n### `\u002Fclear-memory` — Reset Memory\n\nResets `memory.md` to factory defaults. The CLI requires `clear --confirm`; review and back up the file before resetting.\n\n**Usage:**\n```\n\u002Fclear-memory\n```\n\n## Editorial Conventions (Prompt Suggestions)\n\nThe skill injects these rules into every prompt via the bundled `scripts\u002Futils.py`. They are editable suggestions, not verified LinkedIn ranking rules or code-enforced output constraints.\n\n### Hook Engineering\n- Line 1 must be scroll-stopping (bold claim, surprising stat, provocative question, or\n  personal story opener).\n- Line 2 must create a pattern interrupt that forces \"see more\".\n- Forbidden openers: `\"In today's...\"`, `\"I am excited to...\"`, `\"Happy to share...\"`,\n  `\"Thrilled to announce...\"`.\n\n### Readability Rules\n- Maximum 2 sentences per paragraph.\n- Aggressive line breaks — white space wins on LinkedIn.\n- Bold used sparingly, only for critical points.\n- Target reading level: Grade 8 or below.\n\n### Hashtag Strategy\n- 1 broad hashtag (`#AI`, `#Marketing`, `#Leadership`).\n- 2 niche hashtags (`#AIAgents`, `#ContentMarketing`, `#StartupLife`).\n- 1–2 community hashtags (`#LinkedInTips`, `#PersonalBranding`).\n- Hard limit: **never more than 5** total.\n\n## Best Practices\n\n- ✅ Set `Primary Niche` in `memory.md` before generating any content.\n- ✅ Run `\u002Ffeedback` after any post that performs well — the memory compounds over time.\n- ✅ Use `\u002Fgenerate-calendar` first when planning a content sprint; it provides topics\n  for `\u002Fgenerate-post` and `\u002Fgenerate-carousel` runs.\n- ✅ Mix carousel styles across a calendar period: listicle, myth-busting, and\n  story-arc perform differently and prevent audience fatigue.\n- ✅ Test the `controversial` tone on topics where you have a genuine, defensible stance;\n  avoid it for topics where nuance is more valuable than edge.\n- ❌ Do not skip the `\u002Ffeedback` loop — without it, every output starts from generic\n  LinkedIn best practices rather than your specific audience data.\n- ❌ Do not post more than 5 hashtags; this is an editorial preference; no penalty threshold is established here.\n- ❌ Do not use the `data-driven` style without real statistics to cite; fabricated\n  numbers destroy credibility faster than any other LinkedIn mistake.\n- ❌ Do not generate a 30-day calendar without specifying `goal`; the default `growth`\n  goal mixes formats broadly and may not match a specific campaign objective.\n\n## Limitations\n\n- This skill does not publish to LinkedIn directly. All output is copy-paste ready but\n  requires manual posting via the LinkedIn web or mobile app.\n- The memory system is file-based and local. It is not shared across machines or team\n  members without manually syncing `memory.md`.\n- The skill does not verify real-time LinkedIn algorithm changes. SEO rules are based on\n  documented best practices as of mid-2025 and may need manual updates as the platform\n  evolves.\n- Calendar output does not auto-schedule posts or integrate with scheduling tools\n  (Buffer, Hootsuite, etc.). It produces a Markdown table for manual import.\n- The `slides` parameter is clamped to the range `3–12`. Carousels outside this range\n  will silently be adjusted to the nearest boundary.\n- `memory.md` grows unbounded as feedback accumulates. Very large memory files (500+\n  entries) may exceed prompt context limits and cause truncation. Periodically archive\n  old entries using `\u002Fclear-memory` and re-seed with your top learnings.\n- Does not work in sandboxed environments where `python3` is unavailable or `Bash` tool\n  calls are blocked.\n\n## Security & Safety Notes\n\nThis skill uses the `Bash` allowed-tool to run Python scripts bundled at\n`~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002F`. Generators read memory and print prompts; they do not generate media or call an AI themselves. Slash command names are conventions, not installed command definitions. All scripts are read-only except `memory_manager.py`, which writes only to `memory.md` inside that\nsame bundled `scripts\u002F` directory.\n\n- No network requests are made by any script.\n- No credentials, tokens, or secrets are read, written, or logged.\n- No files outside `~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002F` are modified.\n- The `clear` command in `memory_manager.py` overwrites only the bundled `memory.md`;\n  it does not delete any other files.\n- All `--feedback` and `--id` arguments passed to `memory_manager.py` are written\n  verbatim to `memory.md`. Do not pass shell metacharacters or sensitive data as\n  feedback strings.\n\nAll Bash commands in this skill are local Python invocations with no elevated privileges\nrequired:\n\n```bash\n# SKILL_SCRIPTS resolves to ~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\nSKILL_SCRIPTS=\"${HOME}\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\"\npython3 \"${SKILL_SCRIPTS}\u002Fgenerate_post.py\" --topic \"...\" --niche \"...\" --tone professional --style list-based\npython3 \"${SKILL_SCRIPTS}\u002Fmemory_manager.py\" add --id \"...\" --feedback \"...\" --tags \"...\"\npython3 \"${SKILL_SCRIPTS}\u002Fmemory_manager.py\" read\npython3 \"${SKILL_SCRIPTS}\u002Fmemory_manager.py\" clear --confirm\n```\n\n\n\n## Common Pitfalls\n\n- **Problem:** Script exits with `ModuleNotFoundError` or `No module named 'utils'`.\n  **Solution:** Each script uses `sys.path.insert(0, SCRIPT_DIR)` to locate `utils.py`\n  relative to itself, so they work from any directory when their script path resolves correctly. Use\n  `python3 \"${HOME}\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002Fgenerate_post.py\" ...`.\n\n- **Problem:** Memory is not being applied to generated content.\n  **Solution:** Check that `memory.md` exists at\n  `~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002Fmemory.md`. Run `\u002Fshow-memory`\n  to confirm. If missing, run any generator command once — it reports no memory; use the memory manager add operation to initialize intentionally.\n\n- **Problem:** Calendar output is missing days or the table is malformed.\n  **Solution:** Verify the `--days` value is a positive integer and `--frequency` is\n  quoted if it contains spaces (e.g., `\"3 times a week\"`). The script passes these\n  values directly into the prompt string.\n\n- **Problem:** Carousel slides exceed the requested count.\n  **Solution:** The `slides` value is clamped locally to `[3, 12]`. If Claude\n  generates more slides than requested, it is following the style guide structure\n  (cover + content + CTA). Specify an exact count and style to get precise control.\n\n- **Problem:** Generated post sounds generic despite feedback being saved.\n  **Solution:** Memory entries are injected as context, not as hard rules. Use specific,\n  actionable feedback: `\"opening with a personal failure story outperforms stats for my\n  audience\"` is more useful than `\"storytelling was good\"`.\n\n- **Problem:** `python3` not found on Windows.\n  **Solution:** Install Python 3.8+ from python.org and ensure it is on PATH, or run via\n  `py \"%USERPROFILE%\\.claude\\skills\\linkedin-content-generator\\scripts\\generate_post.py\" ...`. On Windows without WSL, the `Bash` tool invocation\n  may need adjustment in the SKILL.md `allowed-tools` context.\n\n## Related Skills\n\n- `@content-creator` — Broader brand voice analysis, SEO optimisation, and\n  cross-platform content frameworks. Use when building a full content marketing system\n  beyond LinkedIn alone.\n- `@content-strategy` — Topic cluster planning, editorial roadmap, and content mix\n  strategy. Use before running `\u002Fgenerate-calendar` when you need to define pillar topics\n  first.\n- `@content-marketer` — Campaign-level content planning across channels. Complements\n  this skill when LinkedIn is one channel in a broader multi-platform launch.\n- `@linkedin-automation` — Programmatic LinkedIn post publishing via the Composio\u002FRube\n  MCP. Use alongside this skill when you want to automate the publishing step after\n  generating content here.\n- `@linkedin-profile-optimizer` — LinkedIn profile and personal brand optimisation.\n  Use before running this skill to align generated content voice with your profile's\n  headline, summary, and featured section.\n\n## Additional Resources\n\n- [LinkedIn Algorithm Guide (Official)](https:\u002F\u002Fwww.linkedin.com\u002Fhelp\u002Flinkedin\u002Fanswer\u002Fa522537)\n- [LinkedIn Newsletter Best Practices](https:\u002F\u002Fwww.linkedin.com\u002Fhelp\u002Flinkedin\u002Fanswer\u002Fa544800)\n- [Source Repository — linkedin-content-skill](https:\u002F\u002Fgithub.com\u002Fsarveshtalele\u002Flinkedin-content-skill)\n","# LinkedIn Content Generator\n\n## Overview\n\nA full LinkedIn content-creation suite for Claude Code that turns a topic and niche into\npublish-ready posts, multi-slide carousels, long-form newsletter editions, and 30-day content\ncalendars — all wired through a personal feedback-based memory system so later prompts can reflect your feedback; improvement is not guaranteed.\n\nSeven coordinated commands cover the full content workflow:\n\n| Command | Purpose |\n|---|---|\n| `\u002Fgenerate-post` | Single ready-to-publish LinkedIn post |\n| `\u002Fgenerate-carousel` | Numbered slide content + caption |\n| `\u002Fgenerate-newsletter` | Long-form newsletter edition |\n| `\u002Fgenerate-calendar` | 30-day posting calendar with Markdown table |\n| `\u002Fshow-memory` | Display current preferences and feedback log |\n| `\u002Ffeedback` | Save what worked for future outputs |\n| `\u002Fclear-memory` | Reset memory to factory defaults |\n\nAll helper scripts are bundled inside `skills\u002Flinkedin-content-generator\u002Fscripts\u002F` and ship\nalongside this `SKILL.md`. They build richly engineered prompts, inject your saved\npreferences, and suggest editorial conventions before Claude generates output.\nA local `memory.md` file persists your style, tone, successful hooks, and top-performing\nformats across every session.\n\n## When to Use This Skill\n\n- Use when you need a ready-to-paste LinkedIn post with SEO-optimised hooks and hashtags.\n- Use when building a multi-slide carousel deck for LinkedIn Documents.\n- Use when writing a long-form LinkedIn Newsletter edition with structured sections.\n- Use when planning an entire month of content with format variety and pacing rules.\n- Use when you want content that adapts to your personal voice over time via saved feedback.\n- Use when working in any niche (AI, SaaS, Marketing, Finance, Healthcare, etc.) and need\n  platform-native formatting that avoids common LinkedIn algorithmic pitfalls.\n\n## Prerequisites\n\n**Python 3.8 or later** must be available in your shell path.\n\nThe skill is self-contained. Install it from the Agentic Awesome Skills library:\n\n```bash\n# Install via antigravity CLI (recommended)\nnpx antigravity-awesome-skills --skill linkedin-content-generator\n\n# Or copy manually into your Claude Code skills directory\ncp -r skills\u002Flinkedin-content-generator ~\u002F.claude\u002Fskills\u002F\n```\n\nAll six Python scripts and the default `memory.md` are bundled inside the\n`scripts\u002F` subdirectory of this skill. No additional cloning or downloads are required.\nNo API keys, external services, or network access are needed.\n\n## How It Works\n\n### Architecture\n\n```\nUser command (\u002Fgenerate-post ...)\n        │\n        ▼\nSKILL.md parses $ARGUMENTS\n        │\n        ▼\nPython script builds prompt\n  • Injects LinkedIn SEO rules\n  • Injects memory.md preferences\n        │\n        ▼\nClaude generates publish-ready output\n        │\n        ▼\n\u002Ffeedback saves what worked → memory.md\n        (loop — every future output improves)\n```\n\n### Step 1: Set Up Your Niche (One-Time)\n\nOpen `~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002Fmemory.md` and update the\n**Primary Niche** field:\n\n```markdown\n## Core Identity & Tone\n- **Primary Niche:** AI & Technology   ← change this\n```\n\nThis field is injected into every prompt. Without it, the skill defaults to\n`\"AI & Technology\"`.\n\n### Step 2: Generate Content\n\nRun any of the seven commands described in the **Commands Reference** section below.\nClaude reads the script output and produces the final content directly in the chat.\n\n### Step 3: Save What Works\n\nAfter each output, save successful patterns with `\u002Ffeedback`:\n\n```\n\u002Ffeedback the storytelling hook in this post got 3x more comments than usual\n```\n\nThe feedback is appended to `memory.md` and automatically injected into all future\ngeneration prompts.\n\n## Commands Reference\n\n### `\u002Fgenerate-post` — Single LinkedIn Post\n\nGenerates a scroll-stopping, SEO-optimised LinkedIn text post.\n\n**Usage:**\n```\n\u002Fgenerate-post \u003Ctopic> [in \u003Cniche>] [tone: controversial|storytelling|educational|motivational|professional]\n```\n\n**Parameters:**\n\n| Parameter | Default | Options |\n|---|---|---|\n| `topic` | required | any subject |\n| `niche` | `\"AI & Technology\"` | any industry |\n| `tone` | `professional` | `professional` · `storytelling` · `controversial` · `educational` · `motivational` |\n| `style` | `list-based` | `list-based` · `text-only` · `storytelling` · `data-driven` · `contrarian` |\n\n**Examples:**\n\n```\n\u002Fgenerate-post why most developers fail at time management in Software Engineering tone: storytelling\n```\n\n```\n\u002Fgenerate-post the real cost of technical debt in SaaS tone: controversial\n```\n\n```\n\u002Fgenerate-post 5 things I wish I knew before my first startup in Entrepreneurship tone: educational style: list-based\n```\n\n**Output structure:**\n1. Scroll-stopping hook (2 lines, triggers \"see more\")\n2. Context \u002F problem setup (2–3 short sentences)\n3. Core value (numbered list or bullets, max 7 items)\n4. Key takeaway (1–2 punchy sentences)\n5. Specific call to action\n6. 3–5 hashtags (broad + niche + community mix)\n\n---\n\n### `\u002Fgenerate-carousel` — LinkedIn Carousel\n\nGenerates numbered slide content plus a ready-to-use LinkedIn caption.\n\n**Usage:**\n```\n\u002Fgenerate-carousel \u003Ctopic> [in \u003Cniche>] [\u003Cn> slides] [style: how-to|listicle|myth-busting|framework|story-arc]\n```\n\n**Parameters:**\n\n| Parameter | Default | Options |\n|---|---|---|\n| `topic` | required | any subject |\n| `niche` | `\"AI & Technology\"` | any industry |\n| `slides` | `7` | `3`–`12` |\n| `style` | `listicle` | `how-to` · `listicle` · `myth-busting` · `framework` · `story-arc` |\n\n**Style guide:**\n\n| Style | Structure |\n|---|---|\n| `how-to` | Slide 1 = problem → slides 2–N = steps → last = result \u002F CTA |\n| `listicle` | Each slide = one item with bold title + 1–2 sentence explanation |\n| `myth-busting` | Each slide = `MYTH: [belief]` → `TRUTH: [reality]` |\n| `framework` | Introduce a proprietary framework; each slide = one component |\n| `story-arc` | Slide 1 = before → middle = journey → last = after + CTA |\n\n**Examples:**\n\n```\n\u002Fgenerate-carousel 10 prompt engineering mistakes 8 slides style: myth-busting\n```\n\n```\n\u002Fgenerate-carousel building a second brain in Knowledge Management 7 slides style: how-to\n```\n\n```\n\u002Fgenerate-carousel the PARA method for productivity in Personal Development style: framework\n```\n\n**Output:** Slides numbered `1` through `N`, followed by a LinkedIn caption with hook,\nteaser context, \"Swipe →\" prompt, and hashtags.\n\n---\n\n### `\u002Fgenerate-newsletter` — LinkedIn Newsletter Edition\n\nGenerates a complete long-form newsletter edition structured for the LinkedIn Newsletter\neditor.\n\n**Usage:**\n```\n\u002Fgenerate-newsletter \u003Ctopic> [in \u003Cniche>] [length: short|medium|long] [title: \"\u003Cseries title>\"]\n```\n\n**Parameters:**\n\n| Parameter | Default | Options |\n|---|---|---|\n| `topic` | required | any subject |\n| `niche` | `\"AI & Technology\"` | any industry |\n| `length` | `medium` | `short` (~700 w) · `medium` (~1,200 w) · `long` (~2,000 w) |\n| `title` | auto-generated | optional series name |\n\n**Examples:**\n\n```\n\u002Fgenerate-newsletter how AI is reshaping hiring in HR & Recruiting length: medium\n```\n\n```\n\u002Fgenerate-newsletter the state of developer tools in 2026 in DevTools length: long title: \"Build Layer Weekly\"\n```\n\n**Output structure:**\n1. SEO-optimised H1 headline\n2. Opening hook (personal anecdote, statistic, or bold claim)\n3. Body sections with H2 subheadings\n4. Key takeaways (3–5 bullets)\n5. One specific action step for this week\n6. Engagement question to spark comments\n\n---\n\n### `\u002Fgenerate-calendar` — 30-Day Content Calendar\n\nGenerates a Markdown table calendar with monthly theme, SEO keywords, and format breakdown.\n\n**Usage:**\n```\n\u002Fgenerate-calendar [niche: \u003Cniche>] [days: \u003Cn>] [frequency: \u003Cfreq>] [goal: awareness|engagement|leads|authority|growth]\n```\n\n**Parameters:**\n\n| Parameter | Default | Options |\n|---|---|---|\n| `niche` | required | any industry |\n| `days` | `30` | any positive integer |\n| `frequency` | `\"3 times a week\"` | any posting cadence |\n| `goal` | `growth` | `awareness` · `engagement` · `leads` · `authority` · `growth` |\n\n**Goal guide:**\n\n| Goal | Strategy |\n|---|---|\n| `awareness` | Shareable, relatable, trending; heavy on carousels and contrarian takes |\n| `engagement` | Opinion posts, polls, questions, storytelling to maximise comments |\n| `leads` | Educational value posts + authority-building + clear DM CTAs |\n| `authority` | Deep insights, data-backed posts, thought leadership, newsletters |\n| `growth` | Mix viral formats (carousels, lists, contrarian) with high-value education |\n\n**Examples:**\n\n```\n\u002Fgenerate-calendar niche: Fintech days: 30 frequency: daily goal: authority\n```\n\n```\n\u002Fgenerate-calendar niche: Marketing Agencies days: 14 frequency: 5 times a week goal: leads\n```\n\n**Output:** Markdown table (`# | Day | Format | Topic \u002F Angle | Hook | CTA`) + monthly theme +\ntop 5 SEO keywords + format breakdown summary.\n\n---\n\n### `\u002Fshow-memory` — Display Preferences\n\nDisplays current memory contents: niche, tone, style, and all saved feedback entries.\n\n**Usage:**\n```\n\u002Fshow-memory\n```\n\n**Output:** Full `memory.md` content with entry count, primary niche, and tone summary.\n\n---\n\n### `\u002Ffeedback` — Save Successful Patterns\n\nAppends a labelled feedback entry to `memory.md`. Future outputs automatically incorporate\nsaved patterns.\n\n**Usage:**\n```\n\u002Ffeedback \u003Cwhat worked well>\n```\n\n**Examples:**\n\n```\n\u002Ffeedback the contrarian hook \"everyone is wrong about X\" drove 400% more impressions\n```\n\n```\n\u002Ffeedback myth-busting carousels in the DevOps niche get 3x more saves than listicles\n```\n\n```\n\u002Ffeedback storytelling tone with a personal failure story outperforms data-driven in my audience\n```\n\n---\n\n### `\u002Fclear-memory` — Reset Memory\n\nResets `memory.md` to factory defaults. The CLI requires `clear --confirm`; review and back up the file before resetting.\n\n**Usage:**\n```\n\u002Fclear-memory\n```\n\n## Editorial Conventions (Prompt Suggestions)\n\nThe skill injects these rules into every prompt via the bundled `scripts\u002Futils.py`. They are editable suggestions, not verified LinkedIn ranking rules or code-enforced output constraints.\n\n### Hook Engineering\n- Line 1 must be scroll-stopping (bold claim, surprising stat, provocative question, or\n  personal story opener).\n- Line 2 must create a pattern interrupt that forces \"see more\".\n- Forbidden openers: `\"In today's...\"`, `\"I am excited to...\"`, `\"Happy to share...\"`,\n  `\"Thrilled to announce...\"`.\n\n### Readability Rules\n- Maximum 2 sentences per paragraph.\n- Aggressive line breaks — white space wins on LinkedIn.\n- Bold used sparingly, only for critical points.\n- Target reading level: Grade 8 or below.\n\n### Hashtag Strategy\n- 1 broad hashtag (`#AI`, `#Marketing`, `#Leadership`).\n- 2 niche hashtags (`#AIAgents`, `#ContentMarketing`, `#StartupLife`).\n- 1–2 community hashtags (`#LinkedInTips`, `#PersonalBranding`).\n- Hard limit: **never more than 5** total.\n\n## Best Practices\n\n- ✅ Set `Primary Niche` in `memory.md` before generating any content.\n- ✅ Run `\u002Ffeedback` after any post that performs well — the memory compounds over time.\n- ✅ Use `\u002Fgenerate-calendar` first when planning a content sprint; it provides topics\n  for `\u002Fgenerate-post` and `\u002Fgenerate-carousel` runs.\n- ✅ Mix carousel styles across a calendar period: listicle, myth-busting, and\n  story-arc perform differently and prevent audience fatigue.\n- ✅ Test the `controversial` tone on topics where you have a genuine, defensible stance;\n  avoid it for topics where nuance is more valuable than edge.\n- ❌ Do not skip the `\u002Ffeedback` loop — without it, every output starts from generic\n  LinkedIn best practices rather than your specific audience data.\n- ❌ Do not post more than 5 hashtags; this is an editorial preference; no penalty threshold is established here.\n- ❌ Do not use the `data-driven` style without real statistics to cite; fabricated\n  numbers destroy credibility faster than any other LinkedIn mistake.\n- ❌ Do not generate a 30-day calendar without specifying `goal`; the default `growth`\n  goal mixes formats broadly and may not match a specific campaign objective.\n\n## Limitations\n\n- This skill does not publish to LinkedIn directly. All output is copy-paste ready but\n  requires manual posting via the LinkedIn web or mobile app.\n- The memory system is file-based and local. It is not shared across machines or team\n  members without manually syncing `memory.md`.\n- The skill does not verify real-time LinkedIn algorithm changes. SEO rules are based on\n  documented best practices as of mid-2025 and may need manual updates as the platform\n  evolves.\n- Calendar output does not auto-schedule posts or integrate with scheduling tools\n  (Buffer, Hootsuite, etc.). It produces a Markdown table for manual import.\n- The `slides` parameter is clamped to the range `3–12`. Carousels outside this range\n  will silently be adjusted to the nearest boundary.\n- `memory.md` grows unbounded as feedback accumulates. Very large memory files (500+\n  entries) may exceed prompt context limits and cause truncation. Periodically archive\n  old entries using `\u002Fclear-memory` and re-seed with your top learnings.\n- Does not work in sandboxed environments where `python3` is unavailable or `Bash` tool\n  calls are blocked.\n\n## Security & Safety Notes\n\nThis skill uses the `Bash` allowed-tool to run Python scripts bundled at\n`~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002F`. Generators read memory and print prompts; they do not generate media or call an AI themselves. Slash command names are conventions, not installed command definitions. All scripts are read-only except `memory_manager.py`, which writes only to `memory.md` inside that\nsame bundled `scripts\u002F` directory.\n\n- No network requests are made by any script.\n- No credentials, tokens, or secrets are read, written, or logged.\n- No files outside `~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002F` are modified.\n- The `clear` command in `memory_manager.py` overwrites only the bundled `memory.md`;\n  it does not delete any other files.\n- All `--feedback` and `--id` arguments passed to `memory_manager.py` are written\n  verbatim to `memory.md`. Do not pass shell metacharacters or sensitive data as\n  feedback strings.\n\nAll Bash commands in this skill are local Python invocations with no elevated privileges\nrequired:\n\n```bash\n# SKILL_SCRIPTS resolves to ~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\nSKILL_SCRIPTS=\"${HOME}\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\"\npython3 \"${SKILL_SCRIPTS}\u002Fgenerate_post.py\" --topic \"...\" --niche \"...\" --tone professional --style list-based\npython3 \"${SKILL_SCRIPTS}\u002Fmemory_manager.py\" add --id \"...\" --feedback \"...\" --tags \"...\"\npython3 \"${SKILL_SCRIPTS}\u002Fmemory_manager.py\" read\npython3 \"${SKILL_SCRIPTS}\u002Fmemory_manager.py\" clear --confirm\n```\n\n\n\n## Common Pitfalls\n\n- **Problem:** Script exits with `ModuleNotFoundError` or `No module named 'utils'`.\n  **Solution:** Each script uses `sys.path.insert(0, SCRIPT_DIR)` to locate `utils.py`\n  relative to itself, so they work from any directory when their script path resolves correctly. Use\n  `python3 \"${HOME}\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002Fgenerate_post.py\" ...`.\n\n- **Problem:** Memory is not being applied to generated content.\n  **Solution:** Check that `memory.md` exists at\n  `~\u002F.claude\u002Fskills\u002Flinkedin-content-generator\u002Fscripts\u002Fmemory.md`. Run `\u002Fshow-memory`\n  to confirm. If missing, run any generator command once — it reports no memory; use the memory manager add operation to initialize intentionally.\n\n- **Problem:** Calendar output is missing days or the table is malformed.\n  **Solution:** Verify the `--days` value is a positive integer and `--frequency` is\n  quoted if it contains spaces (e.g., `\"3 times a week\"`). The script passes these\n  values directly into the prompt string.\n\n- **Problem:** Carousel slides exceed the requested count.\n  **Solution:** The `slides` value is clamped locally to `[3, 12]`. If Claude\n  generates more slides than requested, it is following the style guide structure\n  (cover + content + CTA). Specify an exact count and style to get precise control.\n\n- **Problem:** Generated post sounds generic despite feedback being saved.\n  **Solution:** Memory entries are injected as context, not as hard rules. Use specific,\n  actionable feedback: `\"opening with a personal failure story outperforms stats for my\n  audience\"` is more useful than `\"storytelling was good\"`.\n\n- **Problem:** `python3` not found on Windows.\n  **Solution:** Install Python 3.8+ from python.org and ensure it is on PATH, or run via\n  `py \"%USERPROFILE%\\.claude\\skills\\linkedin-content-generator\\scripts\\generate_post.py\" ...`. On Windows without WSL, the `Bash` tool invocation\n  may need adjustment in the SKILL.md `allowed-tools` context.\n\n## Related Skills\n\n- `@content-creator` — Broader brand voice analysis, SEO optimisation, and\n  cross-platform content frameworks. Use when building a full content marketing system\n  beyond LinkedIn alone.\n- `@content-strategy` — Topic cluster planning, editorial roadmap, and content mix\n  strategy. Use before running `\u002Fgenerate-calendar` when you need to define pillar topics\n  first.\n- `@content-marketer` — Campaign-level content planning across channels. Complements\n  this skill when LinkedIn is one channel in a broader multi-platform launch.\n- `@linkedin-automation` — Programmatic LinkedIn post publishing via the Composio\u002FRube\n  MCP. Use alongside this skill when you want to automate the publishing step after\n  generating content here.\n- `@linkedin-profile-optimizer` — LinkedIn profile and personal brand optimisation.\n  Use before running this skill to align generated content voice with your profile's\n  headline, summary, and featured section.\n\n## Additional Resources\n\n- [LinkedIn Algorithm Guide (Official)](https:\u002F\u002Fwww.linkedin.com\u002Fhelp\u002Flinkedin\u002Fanswer\u002Fa522537)\n- [LinkedIn Newsletter Best Practices](https:\u002F\u002Fwww.linkedin.com\u002Fhelp\u002Flinkedin\u002Fanswer\u002Fa544800)\n- [Source Repository — linkedin-content-skill](https:\u002F\u002Fgithub.com\u002Fsarveshtalele\u002Flinkedin-content-skill)\n",{"name":5,"risk":47,"tags":62,"tools":67,"author":69,"source":43,"license":14,"category":64,"date_added":70,"description":7,"source_repo":71,"source_type":43,"license_source":72},[41,52,63,64,65,53,54,55,66,50],"social-media","marketing","newsletter","seo",[68],"claude","sarveshkishortalele","2026-06-04","sarveshtalele\u002Flinkedin-content-skill","https:\u002F\u002Fgithub.com\u002Fsarveshtalele\u002Flinkedin-content-skill\u002Fblob\u002Fmain\u002FLICENSE","7bf2279c8a65758319526a721d5c4b75683aec9c","skills\u002Fantigravity-linkedin-content-generator",3,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections","https:\u002F\u002Fgithub.com\u002Fboisenoise","2026-11-11 14:20:43",{"source":8,"skillName":5,"commands":80,"prompt":90,"zipAvailable":91},[81,84,87],{"tool":82,"command":83},"npx","npx skills add boisenoise\u002Fskills-collections --skill linkedin-content-generator",{"tool":85,"command":86},"bunx","bunx skills add boisenoise\u002Fskills-collections --skill linkedin-content-generator",{"tool":88,"command":89},"pnpm","pnpm dlx skills add boisenoise\u002Fskills-collections --skill linkedin-content-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002FSKILL.md",true,[93,99,103,107,111,115,119],{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Fgenerate_calendar.py","SCRIPT","脚本",3325,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002Fscripts\u002Fgenerate_calendar.py",{"path":100,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fgenerate_carousel.py",2371,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002Fscripts\u002Fgenerate_carousel.py",{"path":104,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fgenerate_newsletter.py",2177,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002Fscripts\u002Fgenerate_newsletter.py",{"path":108,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002Fgenerate_post.py",2883,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002Fscripts\u002Fgenerate_post.py",{"path":112,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Fmemory_manager.py",4615,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002Fscripts\u002Fmemory_manager.py",{"path":116,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Fmemory.md",1512,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002Fscripts\u002Fmemory.md",{"path":120,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":121,"sourceHtmlUrl":122},"scripts\u002Futils.py",4059,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-linkedin-content-generator\u002Fscripts\u002Futils.py",[124,153,177,201,218,240],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":128,"licenseFileUrl":129,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":57},"01M6WNH92BHVFXHGPDZCPJ0AG0","web-access","Use Treg for public web or platform data only when existing search, browser and connected tools cannot cover the task, with explicit cost and data boundaries.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FSKILL.md",[],[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,47,148,149,150,151,152],"web","access","web access","official","development","browser","search","data","Tools","read","fetch","only","youtube","free tools","platform","free","cover","normal","when","2026",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":128,"licenseFileUrl":157,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":57},"01M6WNF9XAYAB2CZDDJBAKNM93","treg","Use the Treg CLI or MCP catalog to discover, price and call authorized external tools with team-scoped credentials and a user-approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FSKILL.md",[160],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[155,162,163,164,136,137,165,141,166,167,168,169,170,171,172,47,173,174,175,176,152],"MCP","cli","github","license","Budget","credentials","team","catalog","use","call","discover","external tools","with","scoped","blob",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":128,"licenseFileUrl":181,"sourceHtmlUrl":182,"categories":183,"keywords":187,"publishedAt":57},"01M6WN93MEAZ4E41DYAHJRPHQT","recruit","Turn a job description into an evidence-linked candidate shortlist through Treg, with job-related ranking and optional authorized business contact enrichment.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FSKILL.md",[184],{"categoryNo":185,"categoryName":186,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000038","人力资源",[179,164,136,165,188,189,190,191,192,193,47,194,195,196,174,197,198,199,200,176,155,152],"https","email","enrichment","business","evidence","phone","ranking","post","job description","for","person","candidate","reason",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":128,"licenseFileUrl":205,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":57},"01M6WN8R5RXSMHM9B4D9FAFX42","rea-growth","Analyze a company’s public growth and content through Treg, distinguish observations from hypotheses, and produce an evidence-linked playbook within an approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FSKILL.md",[],[209,210,211,164,136,165,212,37,188,213,166,64,214,215,192,47,216,217,176,155,152],"growth","rea","rea growth","produce","playbook","analyze","public","observations","company",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":128,"licenseFileUrl":222,"sourceHtmlUrl":223,"categories":224,"keywords":225,"publishedAt":57},"01M6WN2EVE3RQRGWAKBT4S7YT2","make-ugc","Create original AI UGC-style product videos through Treg: research hooks, approve a licensed presenter and voice, generate clips, add captions and report costs.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FSKILL.md",[],[226,227,164,228,136,229,165,230,231,232,233,234,47,235,236,49,237,238,239,176],"make","make ugc","research","create","Video","Captions","ads","short","hooks","head","style","trending","talking-head","approve",{"skillNo":241,"name":242,"nameZh":6,"description":243,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":128,"licenseFileUrl":244,"sourceHtmlUrl":245,"categories":246,"keywords":247,"publishedAt":57},"01M6WN10ARAA63Y8K1YNGXJ2RM","lead-signals","Find and qualify public buying signals through Treg, rank fitting business accounts and optionally enrich authorized business contact information.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FSKILL.md",[],[248,249,250,164,136,165,251,252,191,253,254,47,255,256,257,258,259,260,261,176],"signals","lead","lead signals","how","find","ready","as","how to","qualify","people","information","enrich","changes","funding"]