[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-newsletter-writer-ai-pack-fr":3,"seo:pack:newsletter-writer-ai-pack:fr":103},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":102},"newsletter-writer-ai-pack","📰","#F59E0B","new","Nouveau · cette semaine","Stack IA Complète de l'Auteur de Newsletter — Kit Substack \u002F Beehiiv","Dix picks pour les auteurs de Substack, Beehiiv, ConvertKit et Ghost qui traitent l'envoi hebdomadaire comme une ligne de production : idée, recherche, brouillon, prose, hook, image, capture RSS et la plateforme qui détient la liste.",[16,28,36,46,53,63,70,77,85,92],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4297,"721d23c5-ffea-448c-b2a6-67c905855aad","claude-code-agent-content-marketer-721d23c5","Claude Code Agent: Content Marketer","Use this agent when you need to develop comprehensive content strategies, create SEO-optimized marketing content, or execute multi-channel content campaigns to drive engagement...","TokRepo精选",46,0,"en","skill","Skill",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":34,"view_count":35,"vote_count":24,"lang_type":25,"type":26,"type_label":27},391,"f09e9348-2bdc-45aa-9907-cfb30290f69b","storm-ai-research-report-generator-stanford-f09e9348","STORM — AI Research Report Generator by Stanford","Stanford's LLM-powered system that researches any topic and writes a full Wikipedia-style article with citations. Simulates multi-perspective expert conversations.","Skill Factory",203,{"id":37,"uuid":38,"slug":39,"title":40,"description":41,"author_name":42,"view_count":43,"vote_count":24,"lang_type":25,"type":44,"type_label":45},722,"9c6cbf5f-e46b-40d6-aaf6-d2a4d5a0e657","jina-reader-ai-friendly-web-content-extraction-9c6cbf5f","Jina Reader — AI-Friendly Web Content Extraction","Convert any URL to clean markdown for AI consumption. Free API at r.jina.ai strips ads, navigation, and clutter. Used by AI agents for web research and RAG.","MCP Hub",6919,"mcp","MCP",{"id":47,"uuid":48,"slug":49,"title":50,"description":51,"author_name":52,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4543,"068b43a3-539f-11f1-9bc6-00163e2b0d79","folo-ai-powered-rss-reader-modern-web-068b43a3","Folo — AI-Powered RSS Reader for the Modern Web","An open-source RSS reader that uses AI to summarize, translate, and filter feeds, delivering a clean reading experience across web, desktop, and mobile with real-time sync.","AI Open Source",{"id":54,"uuid":55,"slug":56,"title":57,"description":58,"author_name":59,"view_count":60,"vote_count":24,"lang_type":25,"type":61,"type_label":62},312,"64bf132d-10f5-4c1a-adcc-9fb19af8cb3b","fabric-100-ai-prompt-patterns-everything-64bf132d","Fabric — 100+ AI Prompt Patterns for Everything","Fabric organizes 100+ AI prompt patterns for real-world tasks. 40.3K+ GitHub stars. 20+ providers, CLI + REST API, custom patterns. MIT.","Prompt Lab",193,"prompt","Prompt",{"id":64,"uuid":65,"slug":66,"title":67,"description":68,"author_name":52,"view_count":69,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2604,"ae682a86-4771-11f1-9bc6-00163e2b0d79","zettlr-open-source-markdown-editor-academic-writing-ae682a86","Zettlr — Open-Source Markdown Editor for Academic Writing","Zettlr is a cross-platform Markdown editor designed for researchers and writers, combining distraction-free writing with citation management, Zettelkasten note-linking, and academic export via Pandoc.",145,{"id":71,"uuid":72,"slug":73,"title":74,"description":75,"author_name":52,"view_count":76,"vote_count":24,"lang_type":25,"type":26,"type_label":27},1865,"13b1fee7-3cf7-11f1-9bc6-00163e2b0d79","vale-syntax-aware-prose-linter-technical-writing-13b1fee7","Vale — Syntax-Aware Prose Linter for Technical Writing","Vale is a command-line tool that enforces writing style guides on your prose, supporting custom rules for documentation teams to ensure consistent terminology, tone, and formatting across Markdown, AsciiDoc, and more.",73,{"id":78,"uuid":79,"slug":80,"title":81,"description":82,"author_name":83,"view_count":84,"vote_count":24,"lang_type":25,"type":26,"type_label":27},776,"84500559-5ce6-41c7-ba22-9712153bb821","together-ai-image-generation-skill-claude-code-84500559","Together AI Image Generation Skill for Claude Code","Skill that teaches Claude Code Together AI's image generation API. Covers FLUX and Kontext models for text-to-image, image editing, and style transfer with correct parameters.","Together AI",128,{"id":86,"uuid":87,"slug":88,"title":89,"description":90,"author_name":52,"view_count":91,"vote_count":24,"lang_type":25,"type":26,"type_label":27},1328,"300e919c-381e-11f1-9bc6-00163e2b0d79","ghost-professional-publishing-platform-modern-journalism-300e919c","Ghost — Professional Publishing Platform for Modern Journalism","Ghost is an open-source publishing platform built for professional publishers. It bundles a blazing-fast Node.js CMS, Substack-style paid memberships, email newsletters, and SEO — everything a modern publication needs, self-hosted.",194,{"id":93,"uuid":94,"slug":95,"title":96,"description":97,"author_name":98,"view_count":99,"vote_count":24,"lang_type":25,"type":100,"type_label":101},2982,"d826f667-d0f9-4ded-895e-19ed5d774b47","resend-audiences-manage-email-lists-from-ai-agents","Resend Audiences — Manage Email Lists from AI Agents","Resend Audiences API lets agents add, remove, segment, unsubscribe email recipients. Tag-based segments. Compliant unsubscribe built in.","Resend",82,"script","Script","tokrepo install pack\u002Fnewsletter-writer-ai-pack",{"pageType":104,"pageKey":8,"locale":25,"title":105,"metaDescription":106,"h1":107,"tldr":108,"bodyMarkdown":109,"faq":110,"schema":126,"internalLinks":163,"citations":176,"wordCount":189,"generatedAt":190},"pack","Newsletter Writer's AI Full Stack — 10 Picks for Substack, Beehiiv, ConvertKit, Ghost","Content Marketer agent, STORM, Jina Reader, Folo, Fabric, Zettlr, Vale, Together AI image gen, Ghost, Resend Audiences — the 10-asset stack a solo newsletter writer uses for idea pipeline, deep research, draft, prose lint, cover image, and the publishing platform that owns the list. Install via TokRepo.","Newsletter Writer's AI Full Stack — A Solo Operator's Production Line","Ten picks wired in order: idea pipeline first (RSS + prompt patterns), then a research agent that goes deep, then draft in a markdown editor, lint the prose, generate one cover image, and send through a platform that gives you the subscriber list as a file you can export. Built for the Substack \u002F Beehiiv \u002F ConvertKit \u002F Ghost writer who sends every week and refuses to hand the audience to a platform that can change the deal.","## What's in this pack (six layers: idea \u002F research \u002F draft \u002F edit \u002F image \u002F send)\n\nThis is the stack a serious solo newsletter writer assembles once the weekly send stops being a hobby and starts being a job. Ten picks chosen so that **every layer of the pipeline has one good default**, no decisions to make on Tuesday morning.\n\n- **Idea layer (2 picks):** Folo turns the entire web's RSS into one inbox you skim once a day. Fabric's 100+ prompt patterns gives you a hook-writer, a summariser, an angle-finder, an analogy-maker — all one shell command away.\n- **Research layer (2 picks):** STORM does the deep-research multi-source synthesis when you commit to a topic. Jina Reader is the lighter daily tool — paste any URL, get clean markdown an LLM can actually read.\n- **Draft layer (2 picks):** Content Marketer agent turns the brief into an outline plus draft. Zettlr is the markdown editor you actually finish in (footnotes, citations, distraction-free).\n- **Edit layer (1 pick):** Vale catches the prose tells — passive voice, weasel words, your personal banned-word list. The thing that stops your newsletter sounding like every other AI-assisted newsletter.\n- **Image layer (1 pick):** Together AI Image Generation produces the cover\u002Fhero image in 60 seconds at indie pricing. One per send, no Canva tab.\n- **Send layer (2 picks):** Ghost is the self-hosted publishing + newsletter platform that gives you the subscriber list and the public web archive in one place. Resend Audiences is the API-first option if you want to drive sends from your own scripts or agents.\n\n## Install in this order (research → draft → edit → image → schedule → grow)\n\n1. **Folo** — set this up first. The compounding asset of a newsletter writer is taste, and taste is built by reading. Folo's AI-powered RSS reader pulls every blog, Substack, and news site into one queue; you skim, you star, you flag-for-newsletter. Five minutes a day, three months in, your idea backlog is bottomless.\n2. **Fabric** — install second. 100+ prompt patterns means you stop writing prompts at 9pm on a Monday. `extract_wisdom`, `write_hook`, `find_logical_fallacies`, `create_summary` — every common writer move is a one-liner. Wires cleanly into a shell pipeline with the other picks.\n3. **Jina Reader** — install third. The day-to-day research tool. Paste any URL → clean markdown an LLM can read without HTML noise. Combine with Folo: read flag → Jina Reader extract → drop into your notes for the draft.\n4. **STORM (by Stanford)** — install fourth. When a topic deserves a real essay rather than a quick take, STORM does the multi-source research and produces a structured draft you then *rewrite in your voice*. Don't ship STORM output verbatim; use it to short-circuit the \"open 30 tabs\" phase.\n5. **Claude Code Agent: Content Marketer** — install fifth. The agent that turns brief + research into outline + first draft, with explicit hook variants. Pair with a `style.md` so the draft already speaks in your cadence.\n6. **Zettlr** — install sixth. Where you actually finish. Markdown-first, footnotes, citation manager hooks, distraction-free mode. Substack and Beehiiv both import markdown cleanly; Ghost takes markdown natively.\n7. **Vale** — install seventh. Prose linter you can extend with your own banned-word list. Catch \"dive into,\" \"in this issue we'll explore,\" \"the world of X\" — the AI tells that make readers unsubscribe.\n8. **Together AI Image Generation** — install eighth. Cover image, generated in 60 seconds. One per send. Stop opening Canva.\n9. **Ghost** — install ninth. The platform layer. CMS + newsletter + member payments in one self-hostable Node app. The bet: own the list, own the archive, never get rugged.\n10. **Resend Audiences** — install tenth. The API-first send infrastructure for when you want an agent to schedule sends, segment by cohort, or run drip sequences without a UI in the loop.\n\n## How they fit together (ASCII pipeline)\n\n```\n  ┌─ Folo (RSS inbox) ─┐    ┌─ Fabric (prompt patterns) ─┐\n  │ daily 5-min skim   │    │ hook \u002F angle \u002F summary       │\n  └─────────┬──────────┘    └──────────────┬───────────────┘\n            │                              │\n            ▼                              ▼\n        starred items ──────► idea queue (one doc)\n                                    │\n                                    ▼\n                ┌────────── topic chosen ──────────┐\n                │                                  │\n                ▼                                  ▼\n         Jina Reader                      STORM (deep research)\n         (single URL → md)                (multi-source synth)\n                │                                  │\n                └────────────┬─────────────────────┘\n                             ▼\n          Claude Code Agent: Content Marketer\n          (brief + research → outline + draft + hook variants)\n                             │\n                             ▼\n                       Zettlr (write)\n                             │\n                             ▼\n                       Vale (prose lint)\n                             │\n                             ▼\n           Together AI Image Gen (one cover)\n                             │\n                             ▼\n             ┌─── Ghost ───┐    or    ┌── Resend Audiences ──┐\n             │ post + send  │          │ API-driven send      │\n             │ + archive    │          │ + segments + drips   │\n             └──────┬───────┘          └──────────┬───────────┘\n                    ▼                              ▼\n                subscribers read · open · share · forward\n                    │\n                    ▼\n             back into Folo as growth signal (referrer, mentions)\n```\n\nThe critical joins: **Folo + Fabric** (raw signal becomes idea), **Jina Reader + STORM** (research at two depths), and **Vale before send** (catch the AI tells before they ship).\n\n## Tradeoffs you'll hit\n\n- **AI draft consistency vs personal voice** — A Content Marketer agent gives you a draft every time. The draft is competent. It is not *you*. The lever that closes the gap is a maintained `style.md` (banned phrases, your sentence rhythm, the three things you always argue) fed to the agent as system context. Update it monthly. If you skip this, your last six issues sound identical to six other AI-assisted newsletters and your open rate slides.\n- **Substack vs Beehiiv vs Ghost vs ConvertKit** — Substack: fastest start, they own discovery and Notes, but the list is hostage and the revenue cut is real. Beehiiv: better analytics, recommendations network, no revenue cut on subs but ad-tier monetization is the pitch. Ghost: you own everything but you run the server (or pay Ghost Pro $9-25\u002Fmo). ConvertKit (now Kit): strongest creator-commerce tooling but weaker reader-facing web archive. Rule: if you'd cry losing the list, Ghost; if you want growth-by-platform, Substack or Beehiiv; if you sell digital products to the list, Kit.\n- **Paid newsletter vs free** — Paid only makes sense once you have a free audience that already trusts you. Most newsletters that launch paid on day one die. Pattern: 18+ months free, 5K+ engaged subscribers, a clear premium-content thesis (deep research, private community, course access). Then paid. Switching free → paid is easier than switching paid → free.\n- **Self-host (Ghost \u002F Listmonk) vs hosted (Substack \u002F Beehiiv)** — Self-host costs ~$5\u002Fmo + your time when something breaks. Hosted costs 0-10% of revenue plus deal-change risk. For a one-person newsletter still finding its voice, hosted is fine. For a newsletter that's part of your business, self-host the moment you can afford the ops.\n- **Stock photos vs AI-generated cover images** — AI cover images are good enough at 60 seconds. They start to look generic by the 20th issue. Mitigate by maintaining a visual style guide (palette, composition rule, recurring motif) and feed it to Together AI as part of every prompt. Otherwise rotate in real photography or illustration every 4th issue to break the AI-template feel.\n\n## Common pitfalls\n\n- **The AI-newsletter voice.** Symptoms: every issue opens with \"Have you ever wondered,\" closes with \"Until next week, friends,\" and uses \"dive into,\" \"the world of X,\" \"in this issue we'll explore.\" Fix: put those phrases in your Vale config as errors. Force yourself to rewrite the opening line of every draft by hand, without the agent. Cadence asymmetry is what makes readers feel a human is on the other end.\n- **No cohort segmentation.** All 3K subscribers get every send. The 200 hyper-engaged ones get the same email as the 200 who haven't opened in 6 months. You burn the engaged group and the dormant group never reactivates. Even a two-cohort split (engaged-last-30-days vs everyone) lets you write a re-engagement send without spamming people who don't need one.\n- **Substack lock-in.** You spend three years building 10K subscribers on Substack. You export the list (Substack does let you). You import to Ghost. Open rate drops because you've lost the Substack-network discovery and your domain reputation is fresh. The lock-in isn't the export button; it's the distribution. Plan an exit *while* you're on Substack: cross-publish to a personal domain via custom domain, build a SEO archive elsewhere, accustom the list to your real URL.\n- **Cover images that scream AI.** Smooth gradient, vaguely human face with one extra finger, painterly lighting on a person at a laptop. Readers spot it now. Fix: pick a specific visual identity (e.g., flat editorial illustration, 1990s magazine collage, single typographic poster) and constrain Together AI to that grammar. Stop using the default \"hero image of X\" prompt.\n- **Shipping STORM output verbatim.** STORM produces a structured, citation-rich draft. It also produces *encyclopedia voice*: balanced, hedged, neutral. Newsletter readers signed up for your hot take, not Wikipedia. Use STORM as research compression; rewrite the entire prose in your voice before sending.",[111,114,117,120,123],{"q":112,"a":113},"Will readers notice that AI helped write the newsletter?","If you ship the agent's first draft, yes — within two issues. The tells are structural (every paragraph the same length, every issue the same shape) and lexical (\"dive into,\" \"in this issue,\" balanced hedging instead of opinion). The fix is not to hide the AI use; it's to use the AI for the parts readers don't care about (research compression, outline, draft skeleton) and write the parts they do care about by hand (opening line, hot take, last line). Vale catches the lexical tells, your style.md catches the structural ones, and the rewrite is on you. Done right, the newsletter reads as more researched than your competition without feeling like a model's output.",{"q":115,"a":116},"Substack vs Beehiiv — who actually owns the subscriber data?","Both let you export the list as CSV (email + subscription date + paid status). Both technically respect that you own the relationship. The asymmetry is in distribution: Substack's Notes feed and recommendations network drive a meaningful share of new subscribers; Beehiiv's recommendations network does the same; ConvertKit has the weakest organic discovery. So you 'own' the list in the sense that you can leave with the addresses, but if 40% of your growth came from the platform's network, leaving costs you that growth rate. Plan accordingly: from day one, ask new subscribers where they heard about you; track what % is platform-network vs your own channels. When the platform-share drops below 25%, you can move without losing momentum.",{"q":118,"a":119},"Which image tool should I actually use for the cover image?","Together AI Image Generation if you want a hosted API at indie-friendly pricing and don't want to babysit a GPU. Local ComfyUI or Automatic1111 if you're already running Stable Diffusion and care about iteration cost. Midjourney if you want the best out-of-the-box aesthetic and don't mind that the workflow is Discord-shaped. For one cover per weekly send, Together AI wins on speed and price (~$5\u002Fmo at indie volume). For a newsletter that visually defines the brand (think every issue's image is screenshotted), invest in either Midjourney or a real illustrator on rotation.",{"q":121,"a":122},"If I submit my newsletter to a Substack publication, does AI use count against me?","Substack's stance as of 2026: AI use is allowed; undisclosed AI-only generation of low-effort content is not. The line publications care about is editorial judgement — did a human pick the topic, structure the argument, and stand behind the take? An AI-assisted draft you researched, edited, and have a point of view on is fine. A bot reposting LLM output every Tuesday is not. If the publication you're pitching has a disclosure policy, follow it; otherwise the safe default is: AI tools used for research and drafting, all editorial judgement is yours, you sign your name.",{"q":124,"a":125},"How many subscribers before I should turn on paid?","There is no magic number, but the realistic floor for paid making more than $1K\u002Fmo at typical conversion rates (3-7% of engaged subs paying $5-10\u002Fmo) is around 3-5K engaged free subscribers. 'Engaged' means opening within the last 30 days, not total signups. Below that, paid is a distraction from the only thing that matters (growing the free list and refining the voice). Above 5K engaged, a paid tier with a clear premium thesis (deep-dive issues, archive access, private community) is worth turning on. Don't gate the weekly send behind paid — gate adjacent extras. The free send is what brings new readers in; killing it kills growth.",{"@context":127,"@type":128,"name":129,"description":130,"numberOfItems":131,"inLanguage":25,"itemListElement":132},"https:\u002F\u002Fschema.org","ItemList","Newsletter Writer's AI Full Stack","Ten AI assets for Substack \u002F Beehiiv \u002F ConvertKit \u002F Ghost writers: idea pipeline, deep research, draft, prose lint, cover image, and the publishing platform that owns the list.",10,[133,137,140,143,146,149,152,155,158,161],{"@type":134,"position":135,"name":20,"url":136},"ListItem",1,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fclaude-code-agent-content-marketer-721d23c5",{"@type":134,"position":138,"name":32,"url":139},2,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fstorm-ai-research-report-generator-stanford-f09e9348",{"@type":134,"position":141,"name":40,"url":142},3,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fjina-reader-ai-friendly-web-content-extraction-9c6cbf5f",{"@type":134,"position":144,"name":50,"url":145},4,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Ffolo-ai-powered-rss-reader-modern-web-068b43a3",{"@type":134,"position":147,"name":57,"url":148},5,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Ffabric-100-ai-prompt-patterns-everything-64bf132d",{"@type":134,"position":150,"name":67,"url":151},6,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fzettlr-open-source-markdown-editor-academic-writing-ae682a86",{"@type":134,"position":153,"name":74,"url":154},7,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fvale-syntax-aware-prose-linter-technical-writing-13b1fee7",{"@type":134,"position":156,"name":81,"url":157},8,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Ftogether-ai-image-generation-skill-claude-code-84500559",{"@type":134,"position":159,"name":89,"url":160},9,"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fghost-professional-publishing-platform-modern-journalism-300e919c",{"@type":134,"position":131,"name":96,"url":162},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fresend-audiences-manage-email-lists-from-ai-agents-d826f667",[164,168,172],{"url":165,"anchor":166,"reason":167},"\u002Fen\u002Fpacks\u002Fcontent-creator-ai-studio","Content Creator's AI Studio pack","Adjacent stack for the same writer when they branch into video \u002F podcast \u002F TikTok — share the same Content Marketer agent and Ghost as publishing platform",{"url":169,"anchor":170,"reason":171},"\u002Fen\u002Fpacks\u002Fai-marketing-content-studio","AI Marketing Content Studio pack","When the newsletter becomes the lead-magnet of a marketing function, this pack adds the SEO \u002F landing \u002F campaign tooling around it",{"url":173,"anchor":174,"reason":175},"\u002Fen\u002Ffeatured","Featured assets on TokRepo","Browse the wider curated catalog of agent-ready writer and publishing tools",[177,181,185],{"claim":178,"source_name":179,"source_url":180},"STORM is a knowledge curation system by Stanford OVAL that researches a topic from multiple sources and synthesises a structured article","STORM project page","https:\u002F\u002Fstorm.genie.stanford.edu\u002F",{"claim":182,"source_name":183,"source_url":184},"Ghost is an open-source publishing platform with a built-in email newsletter engine and member-payments support","Ghost official site","https:\u002F\u002Fghost.org\u002F",{"claim":186,"source_name":187,"source_url":188},"Jina Reader returns clean LLM-ready markdown for any URL with a single API call","Jina Reader documentation","https:\u002F\u002Fjina.ai\u002Freader\u002F",1660,"2026-05-23T13:30:00Z"]