Agent Skills

---

name: bestblogs-capture

description: Use this skill when the user wants to save, annotate, or review their BestBlogs reading — create/list/update/remove bookmarks, add highlights with optional notes, view highlight-only vs. note-only lists, and manage reading history. Triggers include "收藏这篇 / 给这段划线 / 加个笔记 / 看我的收藏 / 我的笔记 / 我的阅读历史 / 删掉这条历史", "bookmark this on BestBlogs", "highlight this quote", "show my notes", "clear my BestBlogs reading history". Invokes the `bestblogs` CLI.

---

name: bestblogs-discover

description: Use this skill when the user wants to find today's most worth-reading content from BestBlogs, browse personalized feeds, check trending items, search specific topics, or explore curated newsletters. Triggers include "今天有什么值得读的 / BestBlogs 推荐 / 本周 BestBlogs 热趋 / 搜一下 AI coding / 看关注源的最新 / 最近有什么好周刊", "what's worth reading today", "bestblogs trending this week", "bestblogs discover", "search BestBlogs". Invokes the `bestblogs` CLI.

---

name: bestblogs-explain

description: Use this skill when the user wants to understand the "why" behind BestBlogs recommendations — view their interest profile summary, see which followed sources are driving their daily brief, or inspect the score breakdown of a specific resource. Triggers include "BestBlogs 为什么推这条 / 看我的画像 / 我关注的源哪些最有价值 / 这篇文章评分多少", "why did BestBlogs recommend this", "which of my followed sources contribute most", "show score for this resource". Invokes the `bestblogs` CLI.

---

name: bestblogs-profile

description: Use this skill when the user wants to set up, inspect, or update their BestBlogs interest profile and onboarding state (cold start). Triggers include "帮我做 BestBlogs 冷启动 / 设置兴趣标签 / 看我现在的画像 / bestblogs 的 onboarding", "set up my BestBlogs profile", "what topics have I chosen on BestBlogs". Invokes the `bestblogs` CLI.

---

name: bestblogs-read

description: Use this skill when the user wants to deep-read a specific BestBlogs resource (article / podcast / video / tweet) — fetch its metadata + markdown so a local LLM or reader can consume it, and automatically report the read behavior back to BestBlogs. Triggers include "深度阅读这篇 / 拉这篇内容的 markdown / bestblogs read / 给我看看 RAW_xxx 的正文", "deep read this BestBlogs article", "pull markdown for resource RAW_...". Invokes the `bestblogs` CLI.

---

name: bestblogs-topic

description: Use this skill when the user asks about a specific topic, subject area, or wants to explore curated topic pages on BestBlogs. Triggers include "BestBlogs 有什么主题 / 查一下 AI 编程主题 / 给我看 Claude 主题页 / 大模型相关主题", "BestBlogs topic list", "show me topics about AI", "what topics does BestBlogs have", "topic details for vibe-coding", "browse topic pages". Invokes the `bestblogs` CLI.

---

name: bestblogs-trending

description: Use this skill when the user asks about trending, popular, or hot content on BestBlogs. Triggers include "BestBlogs 本周热门 / 本周流行什么 / 最近热门文章 / 今日热门 / 本月 BestBlogs 精选", "BestBlogs trending", "what's trending on BestBlogs", "popular this week", "hot articles this month", "trending tech content". Invokes the `bestblogs` CLI.

---

name: human-writing

description: 通用中文创作与改稿 Skill。用于知乎回答、论坛长帖、公众号文章、博客、评论、人物故事、历史叙事、新闻与行业解读、科普、教程、评测、个人叙事、小说、故事、对白、口播和演讲稿。默认写成一个见过事、查过材料、愿意把来龙去脉讲清楚的人在说话，重点保留中文互联网长回答与长帖的活人感和自然中文韵律，避免空泛的机构腔、喊口号式演说腔、营销腔和模型腔。非虚构长文先检查材料够不够，材料不足时研究、追问或缩短，绝不用重复解释灌字数。现实内容额外核验事实、引语、数据与用户亲历，虚构内容可以创造人物、场景、对白、心理与情节。成稿正文严禁冒号、破折号、“不是……而是……”及同类翻案句，并清除商业黑话和模型惯用黑话。不创建作者画像、个人规则库或个人写作 Skill。

---

name: analytics-dashboard

description: Turn a LinkedIn Analytics export into an interactive dark-themed React dashboard plus a written strategic analysis with 5 data-backed content recommendations. Reads every sheet in the export, builds charts for engagement trend, follower growth, post performance scatter, day-of-week heatmap, and audience breakdown. Use this skill whenever the user says "analyse my linkedin", "linkedin analytics", "build my dashboard", "review my performance", or uploads a LinkedIn Analytics export file. Requires the user's LinkedIn Analytics export (xlsx) as input.

---

name: content-matrix

description: Generate 24 to 40 LinkedIn post ideas in a single table by pairing the user's content pillars with 8 proven content formats. Based on the Justin Welsh content matrix. Use this skill whenever the user says "give me post ideas", "content matrix", "what should I post about", "generate post ideas", "content ideation", or "map out my content for the month". Pulls from about-me.md and voice.md if they exist, otherwise asks for pillars and context.

---

name: gemini-carousel

description: Generate a branded slide-by-slide LinkedIn carousel using Gemini. Takes source content, builds a design brief, waits for approval, then outputs per-slide image generation prompts. 1080x1350 vertical format. Use this skill whenever the user says "carousel", "build a carousel", "turn this into a carousel", "gemini carousel", or wants multi-slide LinkedIn content. Always includes an approval gate between brief and image generation.

---

name: gemini-infographic

description: Generate a hand-drawn whiteboard infographic prompt. Takes source content (a post, newsletter, blog, research note) and returns a complete Gemini image generation prompt with a structured brief. Use this skill whenever the user says "whiteboard infographic", "gemini infographic", "hand-drawn graphic", "turn this into a whiteboard", or wants an AI-generated infographic for a post.

---

name: graphic-designer

description: Create LinkedIn post graphics. Decides between an HTML/CSS structured graphic or an AI-generated infographic based on the post content. Use this skill whenever the user says "design a graphic", "create a visual", "make an image", "graphic for my post", "LinkedIn image", or wants any visual content to pair with a LinkedIn post. Also trigger when the user finishes writing a post and wants a matching graphic.

---

name: hook-generator

description: Generate 6 clickbait-style LinkedIn hook variations for any topic. Two-line hooks built on the formula: a 40-char opening line, a 40-char bold contrast line. Uses supplied numbers and genuine first-person experience when available. Use this skill whenever the user says "write me hooks", "hook ideas", "generate hooks", "I need a hook for a post about...", or pastes a topic and asks for openers. Fast output, no preamble.

---

name: newsletter-voice

description: Build newsletter writing instructions inside a Codex or Claude project. Runs after voice-builder. Produces newsletter-voice.md, a single file the assistant references when drafting newsletters in the user's voice. Works with or without existing newsletter samples: if the user has past issues, the skill analyses them; if not, the skill offers 6 archetypes tuned to the user's voice. Trigger whenever the user says "build my newsletter voice", "learn my newsletter style", "set up my newsletter system", "train on my newsletters", "newsletter onboarding", or drops newsletter samples into chat asking for an analysis. Requires voice-builder to have run first: the skill needs voice.md and about-me.md in the project to work.

---

name: niche-research

description: Surface the 20 most relevant stories in a niche from the last 7 days using available live research tools. Verified dates, real links, shareable angles. Use available browser or web search tools to inspect dated source material. Use this skill whenever the user says "research my niche", "what's trending", "find stories", "this week's news", "content research", or drops a niche and asks what's happening in it. Requires live source access for current research.

---

name: pinned-comment

description: Write deadpan LinkedIn pinned comments AND matching image generation prompts in the user’s voice. Use when the user asks for a pinned comment, pin comment, or first comment for a LinkedIn post. ALWAYS produce the image prompt FIRST, then caption it with the 4-line comment. Output both together unless told otherwise.

---

name: post-formatter

description: Turn a topic into a ready-to-publish LinkedIn post using PAS, AIDA, BAB, STAR, or SLAY frameworks. Up to 20 nonblank lines, mobile-formatted with blank lines between sentences. Use this skill whenever the user says "format this as a post", "turn this into a LinkedIn post", "write it as PAS" or any named framework, or wants a properly structured post from a topic. Different from post-writer: post-formatter applies a strict framework. post-writer drafts in the user's voice without framework constraints.

---

name: post-scorer

description: Score a LinkedIn post using real performance data. Pulls the user's own post history via Apify (or uses cached data) to identify what actually performs, then scores the draft against those patterns. Use this skill whenever the user says "score my post", "review my post", "rate this post", "give me feedback", "how good is this post", or pastes a LinkedIn post and asks for critique. Separates historical comparisons from an explicitly labelled editorial-only fallback. Designed for live scoring at events and everyday post review.

---

name: post-writer

description: Write LinkedIn posts that match the user's voice system (about-me.md and voice.md). Use this skill whenever the user says "write a post", "draft a post", "LinkedIn post", "post about [topic]", "content idea", or wants help writing any LinkedIn content. Also trigger when the user pastes a context dump (notes, transcripts, bullet points) and wants it turned into a post. Always references the voice files in the project before writing. Always outputs the final post in a code block.

---

name: profile-optimizer

description: Rebuild a LinkedIn profile for maximum conversions. Produces new headline options, about section, experience section, featured section strategy, and 4 image generation prompts (banner, profile picture, 2 featured tiles). Use this skill whenever the user says "optimize my profile", "fix my LinkedIn", "rewrite my headline", "profile review", "LinkedIn audit", "rebuild my profile", or wants help with any part of their LinkedIn profile. Also trigger when the user uploads a LinkedIn profile PDF or screenshot for review.

---

name: quote-post

description: Two-step workflow for creating quote posts on LinkedIn. The assistant drafts original short quotes to accompany a caption, then produces a Gemini prompt that recreates a reference image with the chosen quote baked in. Use this skill whenever the user says "quote post", "quote graphic", "motivational post", "build me a quote", or wants a low-effort high-engagement LinkedIn graphic. Optimised for LinkedIn's employee and early-career audience, which skews toward motivational content.

---

name: reels-scripting

description: Turn a reference Instagram Reel into a script for your own Reel, tuned to your voice and repurposed from your newsletter content. Takes a Reel URL or Notion reference link, uses Apify to scrape the video, sends it to Gemini 2.5 Flash for full transcript + hook + structure analysis, then writes a new script applying the same patterns to your newsletter topic. Use this skill whenever the user says "script a reel", "reels scripting", "turn this into a reel", pastes an Instagram Reel URL, or references their Notion outlier reels database. The URL-to-video-analysis route needs APIFY_API_TOKEN and GOOGLE_AI_API_KEY; supplied input can skip the corresponding stages.

---

name: voice-builder

description: Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing. Works for any content format: LinkedIn posts, newsletters, essays, emails, blog posts, tweets, or any other published writing. Use this skill at the start of any project where the user wants the assistant to learn who they are and how they write before drafting new content. Trigger whenever the user says "build my voice", "learn my voice", "set up my content system", "onboard me", "train on my writing", "train on my posts", "I want Claude to sound like me", or drops a batch of writing samples into chat at the start of a project. Also trigger for first-time users who need a voice foundation before writing anything. Always produces two files (about-me.md and voice.md) saved into the project root.