Writing Assistance
Drafting, editing and summarizing text. As of 2026-11-21, 77 indexed products match this subcategory (50 with full profiles); 33 were published in the last 90 days, against 19 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, oh-story-claudecode leads, holding 27% of the stars of the 64 products here with their own repository. The most common form is MCP servers (69% of indexed products).
SubcategorySegment label: Thin DER
Segment statistics
Whole catalogue (all 77 indexed products, not only profiled ones). Calculated 2026-11-21.
Thin. Among the smallest 30% of nodes at its level, and launches are not outpacing the catalogue. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.142, attention is spread as if across about 7 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 53 | 68.8% | 27 |
| Agent skills | 15 | 19.5% | 15 |
| Plugins | 5 | 6.5% | 5 |
| Rules packs | 3 | 3.9% | 2 |
| Agent projects | 1 | 1.3% | 1 |
3 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Long-form WritingBooks, articles and technical writing. | 32 | 21 | 14 | Thin |
| SummarizationCondensing long text. | 20 | 13 | 5 | Thin |
| ProofreadingGrammar, spelling and style checks. | 16 | 12 | 9 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (50 of 77), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | oh-story-claudecode网文写作 Agent 技能包:扫榜、拆文、大纲细纲、长短篇连载、伏笔追踪、去AI味与封面生成,适配 Claude Code / Codex 等 | Agent skills for writing web novels | Agent skill | zenstory-ai | 8.8k | 1d ago | MIT | ||
| 2 | KunLocal-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI. | Agent project | KunAgent | 6.4k | 5d ago | — | ||
| 3 | yomiyasuAI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese | Agent skill | nanaism | 3.4k | 1d ago | MIT | ||
| 4 | claude-blogFree, open source blog writer for Claude Code. Researches current sources, writes answer-first posts for Google and AI answers, has an independent reviewer score each one out of 100 and ships only after five delivery gates. 32 skills, 30 /blog commands, 5 agents. Active development at AI-Marketing-Hub/claude-blog; public releases ship here. | Agent skill | AgriciDaniel | 2.8k | 18d ago | MIT | ||
| 5 | BeautifulRustAgent Skills that teach coding agents to write, review, and port idiomatic Rust, plus a tested clippy config. Works with Claude Code, Codex, Copilot, Cursor, and Gemini CLI. | Agent skill | morganlinton | 2.1k | 13d ago | MIT | ||
| 6 | video-search-and-summarizationNVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs. | MCP server | NVIDIA-AI-Blueprints | 2.0k | today | Apache-2.0 | ||
| 7 | Claude-Skills403 AI skills, 76 expert agents, and 973 stdlib Python tools for every team: engineering, UI/UX design, PM, marketing, C-level, compliance, business ops, research, founders, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants. | MCP server | borghei | 1.2k | 13d ago | — | ||
| 8 | simplified-technical-englishAn Agent Skill that makes an LLM write in ASD-STE100 Simplified Technical English. Rules, approved word list, and a check tool. | Agent skill | 0xpili | 1.0k | 3mo ago | — | ||
| 9 | oh-story-dshDeepSeek Harness 故事创作插件:集成网文写作、短剧漫剧、小说改游戏与视频解说四个可视化工作台 | DeepSeek Harness plugin for novels, short dramas, games & video recaps | Agent skill | zenstory-ai | 811 | 1d ago | MIT | ||
| 10 | recallStop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline. | Plugin | raiyanyahya | 770 | 2mo ago | MIT | ||
| 11 | video-recap-skillsAI 视频解说 Agent 技能包:自动切镜、看画面写解说词、配音混音合成成片,可导出剪映/CapCut 草稿,无需 GPU | Agent skills for narrated video recaps & CapCut drafts | Agent skill | zenstory-ai | 648 | 1d ago | MIT | ||
| 12 | humanities-writing-companionEnd-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation. | Agent skill | tizzy916 | 500 | 2mo ago | — | ||
| 13 | story-skillsAgent Skills for end-to-end story writing in markdown, packaged as Codex and Claude Code plugins. | Agent skill | danjdewhurst | 441 | 7d ago | MIT | ||
| 14 | iso-24495ISO 24495 Plain Language skills and plugin | Agent skill | GaZmagik | 213 | today | MIT | ||
| 15 | jDocmunch MCPSection-level doc search for .md, .rst, .adoc, .org, .ipynb, .html, .yaml, .json, and OpenAPI specs. | MCP server | jgravelle | 207 | 3d ago | — | ||
| 16 | attention-controlAir traffic control discipline for agent output. Written for a reader with ADHD. | Agent skill | aaddrick | 158 | 3mo ago | MIT | ||
| 17 | economist-style-guide-pluginClaude Code plugin that applies The Economist style guide - clarity, precision, brevity. Unofficial. | Plugin | TAJD | 130 | 3mo ago | MIT | ||
| 18 | WTFMYour coding agent writes the user docs from your codebase, screenshots included. | MCP server | SupportPages-io | 127 | 5d ago | Apache-2.0 | ||
| 19 | LokalBot MeetingsPrivate meeting notes your AI agents can search, from the LokalBot app on your Mac. | MCP server | stevyhacker | 120 | today | GPL-3.0 | ||
| 20 | godot-cursorrulesGodot 4.4 Cursor rules: coding standards, architecture patterns, and performance tips for AI-assisted game dev. | Rules pack | BlueBirdBack | 119 | 1y ago | MIT | ||
| 21 | humanizer-lintA local, zero-dependency prose, copywriting, UI-text, and code-comment linter that flags stiff, AI-sounding writing (stock phrases, flat sentence rhythm, repeated wording) and tells you what to revise. Includes 8 language packs. A style checker, not an AI detector. | Agent skill | yanstd888 | 118 | 14d ago | MIT | ||
| 22 | chinese-webnovel-skills中文网文写作工具包 · Chinese web-novel writing toolkit (23 skills) — a Claude Code plugin, also works in ChatGPT / DeepSeek / Gemini | Agent skill | tance-mang | 110 | 13d ago | MIT | ||
| 23 | FolioSelf-hosted Git-backed team wiki: search, read and edit pages, data tables and whiteboards. | MCP server | evergreen-it-dev | 92 | 2d ago | MIT | ||
| 24 | Bilibili MCP ServerBilibili MCP tool for video metadata, transcripts, subtitles, and comment summarization | MCP server | XZXZZX-Ai | 54 | 2d ago | Apache-2.0 | ||
| 25 | dsh-novel-forge中文长篇写作 MCP Server:24 个工具,用硬门禁治理 AI 写长篇的失忆、设定崩坏与 AI 味 | MCP server | huangziyuan-general | 50 | today | Apache-2.0 | ||
| 26 | antigravity-plugin-ccLocal NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research with citations & branded HTML reports. 13 commands, no Node runtime. | Plugin | MarcosNahuel | 33 | 1mo ago | MIT | ||
| 27 | dsh-novel-writer — 网文写作体检Offline 22-tool Chinese web-novel audits, live chat writing with draft mirror, per-book cleanup. | MCP server | siweina | 32 | 1d ago | MIT | ||
| 28 | Signs of AI WritingAI-writing detection (EN/ES) that shows the evidence: named tells, hidden characters, citations. | MCP server | peopleworks | 31 | 3d ago | MIT | ||
| 29 | AEGIS Academic Integrity CheckerLocal-first paper integrity checks: hallucinated citations, AI-text, plagiarism, venue guidelines. | MCP server | sunilgentyala | 24 | 1d ago | AGPL-3.0 | ||
| 30 | ContentTurn URLs, files and text into media, transcripts, summaries, translations and PDF. | MCP server | LatentNoise | 21 | 1d ago | — | ||
| 31 | context-memPersistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools | MCP server | JubaKitiashvili | 20 | 7mo ago | MIT | ||
| 32 | Boson VideoLet your AI read any video: timed transcript, full-resolution frames, screen text, claim checks. | MCP server | linboxin | 18 | 1mo ago | MIT | ||
| 33 | developer-docs-frameworkAI agent skill for technical docs — Diataxis + 27 rules, 6 style guides (Google, Good Docs). Works with Claude Code, Cursor, Codex, Windsurf. | Rules pack | anivar | 18 | 3mo ago | — | ||
| 34 | etincel-nonfictionTrainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP. | MCP server | etincel.ai | 10 | 3mo ago | MIT | ||
| 35 | Writing Style CheckerProse linter + AI-slop detector: weasel words, passive voice, hedging, and research-cited AI tells | MCP server | theserverlessdev | 9 | 10d ago | MIT | ||
| 36 | youtube-summarizeMCP server that fetches YouTube video transcripts and optionally summarizes them | MCP server | zlatkoc | 6 | 1mo ago | MIT | ||
| 37 | slop-chopFind and remove the writing patterns a profile lists. Deterministic rules, model rewrite opt-in. | MCP server | dcadolph | 5 | 19d ago | MIT | ||
| 38 | LocizeLocize TMS: read and update translations with glossary, style guide, TM and screenshot context. | MCP server | mcp.locize.app | 1 | 9d ago | — | ||
| 39 | AlchemyServes the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells. | MCP server | fernforge | 1 | 4mo ago | MIT | ||
| 40 | yontuTürkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup. | MCP server | senrecep | 1 | 8d ago | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
Launches per month
New Writing Assistance products per monthSRC
Whole catalogue, by publication month, 2025-02 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2025-02 | 1 |
| 2025-12 | 1 |
| 2026-01 | 2 |
| 2026-02 | 3 |
| 2026-03 | 3 |
| 2026-04 | 4 |
| 2026-05 | 7 |
| 2026-06 | 4 |
| 2026-07 | 6 |
| 2026-08 | 10 |
| 2026-09 | 7 |
| 2026-10 | 14 |
| 2026-11 | 10 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
No scored opportunity here
Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .