Skip to content
Back to search

Awesome_SEO_Writing_Skill

Share the awesome skills for SEO Writing. All the skills are developed by Flaq AI Team

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/flaqai--awesome-seo-writing-skill/badge.svg)](/listings/flaqai--awesome-seo-writing-skill)

HTML

<a href="/listings/flaqai--awesome-seo-writing-skill"><img src="/api/listings/flaqai--awesome-seo-writing-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 374 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Awesome SEO Writing Skill
  2. > Created by [Flaq.ai](https://flaq.ai/) — a comprehensive, all-in-one Agentic API solution that gives AI agents and production applications unified access to advanced image, video, and LLM models.
  3. This writing skill distills nearly two years of hands-on SEO writing, content production, fact-checking, image packaging, and publishing experience. It also incorporates useful community ideas, especially Zimu's SEO audit workflow and the reader-focused humanization approach documented by `blader/humanizer`.
  4. **References and acknowledgements:**
  5. - Website: [Flaq.ai — an all-in-one AI Agentic API solution](https://flaq.ai/)
  6. - Community reference: Zimu's [SEO Audit Skill](https://github.com/JeffLi1993/seo-audit-skill)
  7. - Writing reference: [`blader/humanizer`](https://github.com/blader/humanizer), used as inspiration for the post-audit humanization workflow
  8. - WeChat workflow reference: [WeWrite](https://github.com/imraywang/wewrite), used as inspiration for the traceable brief, claim ledger, editorial gate, style profile, and permission-separated WeChat workflow
  9. - User-provided WeChat article: [the original article that prompted this integration](https://mp.weixin.qq.com/s/ebjjsO_rCh5LPlUlqgjBzw)
  10. - Recommended collection: [Awesome Codex Skills](https://github.com/flaqai/awesome_codex_skills)
  11. - Recommended collection: [Awesome Claude Code Skills](https://github.com/flaqai/awesome_claude_code_skills)
  12. ---
  13. [![English](https://img.shields.io/badge/English-Current-brightgreen)](README.md) [![简体中文](https://img.shields.io/badge/%E7%AE%80%E4%BD%93%E4%B8%AD%E6%96%87-View-lightgrey)](README_zh.md) [![繁體中文](https://img.shields.io/badge/%E7%B9%81%E9%AB%94%E4%B8%AD%E6%96%87-View-lightgrey)](README_tw.md) [![日本語](https://img.shields.io/badge/%E6%97%A5%E6%9C%AC%E8%AA%9E-View-lightgrey)](README_ja.md) [![한국어](https://img.shields.io/badge/%ED%95%9C%EA%B5%AD%EC%96%B4-View-lightgrey)](README_ko.md) [![ไทย](https://img.shields.io/badge/%E0%B9%84%E0%B8%97%E0%B8%A2-View-lightgrey)](README_th.md) [![Tiếng Việt](https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-View-lightgrey)](README_vi.md) [![Bahasa Indonesia](https://img.shields.io/badge/Bahasa%20Indonesia-View-lightgrey)](README_id.md) [![Español](https://img.shields.io/badge/Espa%C3%B1ol-View-lightgrey)](README_es.md) [![Français](https://img.shields.io/badge/Fran%C3%A7ais-View-lightgrey)](README_fr.md) [![Deutsch](https://img.shields.io/badge/Deutsch-View-lightgrey)](README_de.md) [![Italiano](https://img.shields.io/badge/Italiano-View-lightgrey)](README_it.md) [![Português](https://img.shields.io/badge/Portugu%C3%AAs-View-lightgrey)](README_pt.md) [![Русский](https://img.shields.io/badge/%D0%A0%D1%83%D1%81%D1%81%D0%BA%D0%B8%D0%B9-View-lightgrey)](README_ru.md) [![العربية](https://img.shields.io/badge/%D8%A7%D9%84%D8%B9%D8%B1%D8%A8%D9%8A%D8%A9-View-lightgrey)](README_ar.md) [![हिन्दी](https://img.shields.io/badge/%E0%A4%B9%E0%A4%BF%E0%A4%A8%E0%A5%8D%E0%A4%A6%E0%A5%80-View-lightgrey)](README_hi.md) [![Türkçe](https://img.shields.io/badge/T%C3%BCrk%C3%A7e-View-lightgrey)](README_tr.md) [![Nederlands](https://img.shields.io/badge/Nederlands-View-lightgrey)](README_nl.md) [![Polski](https://img.shields.io/badge/Polski-View-lightgrey)](README_pl.md)
  14. ---
  15. ## What This Skill Does
  16. Awesome SEO Writing Skill is a reusable workflow for AI coding agents such as Codex and Claude Code. It turns a content request into a structured process covering the task brief, outline, writing, fact-checking, SEO audit, image generation, and file delivery.
  17. - Writes SEO-focused how-to articles, comparisons, listicles, and explainers.
  18. - Aligns the title, introduction, headings, FAQ, conclusion, and metadata with one search intent.
  19. - Checks product features, prices, dates, statistics, policies, and comparison claims.
  20. - Separates deterministic SEO checks from semantic editorial judgment.
  21. - Humanizes the audit-corrected draft while preserving verified facts, search intent, citations, code, links, and the author's intended voice.
  22. - Produces 16:9 article images and uses local Markdown paths by default.
  23. - Optionally compresses and uploads images to Cloudflare R2 when local configuration exists.
  24. - Includes a dedicated `linkedin-writer` workflow for LinkedIn search-led topic discovery, professional thought leadership, native long-form SEO settings, discussion design, auditing, and publishing packages.
  25. - Includes a dedicated `medium-writer` workflow for Medium Topic research, publication matching, author-led long-form storytelling, responsible AI disclosure, editorial review, and publishing packages.
  26. - Includes a dedicated `wechat-writer` workflow for Chinese WeChat Official Account topics, source-led writing, mobile readability, style calibration, editorial review, and publish-ready packaging.
  27. ## Design Principles
  28. ### 1. Search intent before keyword density
  29. The article must answer why the reader searched. The title, first 100 words, sections, FAQ, and conclusion should solve the same core problem instead of repeating an exact keyword.
  30. ### 2. Outline before body copy
  31. The workflow starts with a task card of no more than ten lines, followed by title selection and an outline. Even one-shot article requests internally follow `task card -> outline -> draft` to reduce drift and repetition.
  32. ### 3. Facts and opinions stay separate
  33. Dates, prices, product capabilities, policies, statistics, and comparative claims require evidence. Recommendations are editorial judgment. Unverified claims should be cited, softened, or removed rather than invented for SEO completeness.
  34. ### 4. Audit-driven improvement
  35. The skill checks measurable items such as title length, keyword position, H1 count, FAQ presence, and metadata before evaluating intent, depth, credibility, and prose quality. Factual risks and high-impact issues are fixed first.
  36. ### 5. Humanize after the audit, then verify again
  37. Once factual and SEO issues are fixed, the workflow runs a dedicated humanization pass inspired by [`blader/humanizer`](https://github.com/blader/humanizer). It looks for clusters of mechanical writing such as inflated significance, promotional language, vague attribution, repetitive transitions, forced symmetry, uniform rhythm, generic conclusions, and chatbot artifacts. It does not invent personal experience or promise to bypass AI detectors. Any changed facts, keywords, metadata, links, code, or image paths are rechecked before delivery.
  38. ### 6. Files are the primary deliverable
  39. General SEO articles live under `writer/output/<article-slug>/`. Platform-specific skills use isolated output directories: LinkedIn packages live under `writer/linkedin-writer/output/<article-slug>/`, and Medium packages live under `writer/medium-writer/output/<story-slug>/`. The article, audit, images, and optional upload manifest stay together for publishing, review, and handoff.
  40. ### 7. Local images first, R2 as progressive enhancement
  41. Every article starts with portable local references:
  42. ```markdown
  43. ![AI video workflow](./section-01-16x9.png)
  44. ```
  45. The skill uploads images only when `writer/config/r2.config.json` exists and is valid. Without that file, the local article remains a complete deliverable: no credentials are requested and the writing task does not fail.
  46. ## Repository Structure
  47. ```text
  48. .
  49. ├── README.md
  50. ├── README_*.md
  51. └── writer/
  52. ├── SKILL.md
  53. ├── medium-writer/
  54. │ ├── SKILL.md
  55. │ ├── references/
  56. │ │ ├── medium-article-template.md
  57. │ │ ├── medium-review-rubric.md
  58. │ │ └── medium-topic-research.md
  59. │ ├── scripts/
  60. │ │ └── audit-medium-markdown.mjs
  61. │ └── output/ # Generated Medium story packages; Git-ignored
  62. ├── linkedin-writer/
  63. │ ├── SKILL.md
  64. │ ├── references/
  65. │ │ ├── linkedin-article-template.md
  66. │ │ ├── linkedin-business-depth-and-humanization.md
  67. │ │ ├── linkedin-review-rubric.md
  68. │ │ └── linkedin-topic-research.md
  69. │ ├── scripts/
  70. │ │ └── audit-linkedin-markdown.mjs
  71. │ └── output/ # Generated LinkedIn article packages; Git-ignored
  72. ├── wechat-writer/
  73. │ ├── SKILL.md
  74. │ ├── profile/
  75. │ │ └── style-profile.example.md
  76. │ ├── references/
  77. │ │ ├── frameworks-and-hooks.md
  78. │ │ ├── mobile-writing-and-packaging.md
  79. │ │ ├── wechat-brief-and-evidence.md
  80. │ │ └── wechat-review-rubric.md
  81. │ └── scripts/
  82. │ └── audit-wechat-markdown.mjs
  83. ├── config/
  84. │ └── r2.config.example.json
  85. ├── references/
  86. │ ├── fact-check-and-style.md
  87. │ ├── humanization.md
  88. │ ├── output-packaging.md
  89. │ ├── r2-image-upload.md
  90. │ ├── r2-security.md
  91. │ ├── seo-article-template.md
  92. │ └── seo-audit-checklist.md
  93. ├── scripts/
  94. │ └── upload-r2.mjs
  95. └── output/
  96. └── <article-slug>/
  97. ├── article.md
  98. ├── seo-audit.md
  99. ├── hero-16x9.png
  100. └── image-urls.json # Created only after a successful R2 upload
  101. ```
  102. ## How to Use
  103. Copy the `writer/` directory into the root of your target project, then explicitly ask your agent to use it:
  104. ```text
  105. Use the writer skill to create an English how-to article about
  106. "AI music detector" for YouTube creators.
  107. Main keyword: AI music detector
  108. Supporting keywords: AI-generated music, Content ID, music copyright
  109. Length: 1,200-1,500 words
  110. Requirements: fact-checking, three 16:9 images, SEO audit, and file output.
  111. ```
  112. The agent should read `writer/SKILL.md` first and load only the references needed for the task:
  113. - Complete article or reusable prompt: `writer/references/seo-article-template.md`
  114. - SEO audit and optimization: `writer/references/seo-audit-checklist.md`
  115. - Fact-heavy writing and comparisons: `writer/references/fact-check-and-style.md`
  116. - Post-audit humanization: `writer/references/humanization.md`
  117. - File and image packaging: `writer/references/output-packaging.md`
  118. - Optional R2 upload: `writer/references/r2-image-upload.md`
  119. - Credential safety: `writer/references/r2-security.md`
  120. - LinkedIn Article and newsletter workflow: `writer/linkedin-writer/SKILL.md`
  121. - LinkedIn business-depth research and final humanization: `writer/linkedin-writer/references/linkedin-business-depth-and-humanization.md`
  122. - Medium long-form and publication workflow: `writer/medium-writer/SKILL.md`
  123. - WeChat Official Account workflow: `writer/wechat-writer/SKILL.md`
  124. ## Standard Workflow
  125. 1. Infer or create the article task card.
  126. 2. Generate and select the SEO title.
  127. 3. Build the outline and section notes.
  128. 4. Write the Markdown article.
  129. 5. Generate 16:9 images and insert local relative paths.
  130. 6. Verify current and high-risk claims.
  131. 7. Run the SEO audit and fix high-priority findings.
  132. 8. Humanize the corrected draft and run the post-humanization integrity check.
  133. 9. Save everything under `writer/output/<article-slug>/`.
  134. 10. Upload images only if valid local R2 configuration exists.
  135. 11. Re-audit changed sections and deliver exact file paths.
  136. ## Optional Cloudflare R2 Configuration
  137. No cloud configuration is required. To enable R2 uploads:
  138. ```bash
  139. cp writer/config/r2.config.example.json writer/config/r2.config.json
  140. ```
  141. Fill in the ignored local file, then run:
  142. ```bash
  143. node writer/scripts/upload-r2.mjs \
  144. --file writer/output/<article-slug>/hero-16x9.png \
  145. --article writer/output/<article-slug>/article.md \
  146. --manifest writer/output/<article-slug>/image-urls.json \
  147. --seoName "AI music detector hero" \
  148. --keyword "AI music detector" \
  149. --alt "AI music detector workflow hero image"
  150. ```
  151. Behavior:
  152. - Valid default config: compress and upload the image, update the article URL, and write `image-urls.json`.
  153. - Missing default config: return `skipped: true` without compressing, uploading, or editing the article.
  154. - Missing or invalid explicit `--config <path>`: fail with a clear configuration error.
  155. - The original local image is always retained.
  156. Use `--dryRun` before the first upload to preview the object key and public URL.
  157. ## Output Contract
  158. A normal article package contains at least:
  159. ```text
  160. writer/output/<article-slug>/article.md
  161. writer/output/<article-slug>/hero-16x9.png
  162. ```
  163. It may also contain `seo-audit.md`, section images, compressed `*-r2.webp` copies, and `image-urls.json` after successful uploads.
  164. The article should use one H1, useful H2/H3 sections, an FAQ, a conclusion, and an SEO meta pack containing SEO Title, Excerpt, Meta Description, and Tags.
  165. ## LinkedIn Writer
  166. Use `writer/linkedin-writer/SKILL.md` for LinkedIn Articles, newsletter editions, LinkedIn-native thought leadership, B2B long-form content, and search-led topic planning.
  167. The LinkedIn workflow adds platform-specific safeguards and outputs:
  168. - a two-surface topic-research pass combining LinkedIn search with Google `site:linkedin.com` discovery across public Posts, Articles/Pulse pages, newsletters, and Company material;
  169. - a query/evidence log that keeps Google snippets, creator conversations, practitioner experience, vendor claims, and verified facts separate;
  170. - a refreshable 2026 seed map covering AI-enabled work, leadership, skills-first hiring, career development, business growth, B2B thought leadership, governance, and human capabilities;
  171. - a professional task card defining the reader's role, work situation, decision, thesis, expertise basis, and discussion tension;
  172. - a business insight map covering the decision trigger, buying group, economics, implementation, measurement, risks, scenarios, and next action;
  173. - a claim-source ledger for current data, product claims, platform rules, and commercial disclosure;
  174. - native article structures for practitioner playbooks, decision guides, change analysis, leadership memos, career guides, and evidence-led points of view;
  175. - LinkedIn SEO settings with a maximum 60-character SEO title and a 140-160-character SEO description target;
  176. - a separate publishing pack covering profile/Page voice, Article/newsletter choice, cover, feed commentary, hashtags, mentions, disclosure, and measurement;
  177. - an eight-dimension editorial gate, a LinkedIn-specific final humanization/去 AI 化 pass, and deterministic warnings for mechanical style clusters and thin business context.
  178. All generated LinkedIn files are isolated under `writer/linkedin-writer/output/<article-slug>/`, rather than the parent writer's general `writer/output/` directory.
  179. Example:
  180. ```text
  181. Use the linkedin-writer skill to create an English LinkedIn Article about
  182. how product leaders should evaluate AI agents before production.
  183. Audience: B2B SaaS product leaders
  184. Requirements: refresh LinkedIn topic signals, use Google to inspect public
  185. LinkedIn conversations, verify current claims, develop stakeholder/economic/
  186. implementation context, include a decision framework and one counterargument,
  187. run final LinkedIn humanization, and prepare the complete local package.
  188. Do not publish.
  189. ```
  190. Run the mechanical audit with:
  191. ```bash
  192. node writer/linkedin-writer/scripts/audit-linkedin-markdown.mjs \
  193. writer/linkedin-writer/output/<article-slug>/article-linkedin.md \
  194. --keyword "<primary topic phrase>"
  195. ```
  196. The script validates deterministic structure, packaging, mechanical-style clusters, and common business-depth signals only. It does not determine human or AI authorship, verify facts or originality, confirm professional authority or publication, predict performance, or guarantee an AI-detector result.
  197. ## Medium Writer
  198. Use `writer/medium-writer/SKILL.md` for Medium stories, publication submissions, field notes, tutorials, essays, explainers, reviews, and evidence-led opinion pieces. It treats Medium as a reader network and editorial ecosystem rather than a generic SEO syndication endpoint.
  199. The Medium workflow adds:
  200. - a refreshable Topic radar using Medium search, Topic pages, recent stories, publications, external search demand, and adjacent community signals without inventing search volume;
  201. - a dated 2026 seed map spanning applied AI, data science, software engineering, product and UX, careers, leadership, entrepreneurship, self-improvement, writing, science, climate, society, and ethics;
  202. - a Medium Story Brief that records the reader transformation, author reason, original contribution, evidence plan, primary Topic, publication fit, language, canonical choice, and AI-assistance state;
  203. - up to five relevant Medium Topics selected by reader fit instead of keyword repetition, plus a publication scorecard based on current rules and recent-story evidence;
  204. - native long-form structures for lived-experience essays, reported explainers, tutorials, field notes, arguments, case studies, and reflective reviews;
  205. - selective imagery: no forced image after every heading, with rights, credit, alt text, and AI-image captions recorded when applicable;
  206. - an explicit authorship gate: fabricated experience is blocked, material generated prose is disclosed according to current Medium policy, and primarily AI-generated writing is not presented as paywall-eligible;
  207. - a separate publishing pack for title, subtitle, preview, cover, Topics, publication status, canonical setting, disclosure, distribution state, and post-publication learning;
  208. - a nine-dimension editorial rubric and a deterministic Markdown audit script.
  209. All generated Medium files are isolated under `writer/medium-writer/output/<story-slug>/`, rather than the parent writer's general `writer/output/` directory.
  210. Example:
  211. ```text
  212. Use the medium-writer skill to create an English Medium story about what
  213. small product teams learn when evaluating AI agents beyond the demo.
  214. Audience: product builders and engineering leaders
  215. Requirements: refresh current Medium Topics and publication candidates,
  216. verify current claims, use only author-confirmed experience, prepare the
  217. complete local Medium publishing package, and do not publish.
  218. ```
  219. Run the mechanical audit with:
  220. ```bash
  221. node writer/medium-writer/scripts/audit-medium-markdown.mjs \
  222. writer/medium-writer/output/<story-slug>/article-medium.md \
  223. --pack writer/medium-writer/output/<story-slug>/medium-publishing-pack.md \
  224. --topic "<primary Medium Topic>"
  225. ```
  226. Add `--ai-assisted` when generated prose remains in the final story and `--ai-images` when AI-generated or AI-assisted images are used. The script checks deterministic structure, disclosure placement, image captions, Topics, and publishing-pack fields. It cannot verify facts, originality, authorship, rights, publication acceptance, paywall eligibility, or distribution outcomes.
  227. ## WeChat Writer
  228. Use `writer/wechat-writer/SKILL.md` for Chinese WeChat Official Account articles, topic planning, title and digest creation, source-led drafting, article review, style calibration, mobile-first editing, and local publishing packages.
  229. The WeChat workflow adds safeguards that are not part of a normal SEO draft:
  230. - a brief that records the reader problem, thesis, added value, counterargument, boundaries, and allowed personal material;
  231. - a claim-source ledger that separates facts, inference, opinion, and user-provided experience;
  232. - seven article frameworks instead of one generic content template;
  233. - a five-dimension editorial gate covering accuracy, viewpoint, usefulness, voice, and readability;
  234. - separate `draft.md` and `article.md` files so an unreviewed draft cannot be mistaken for final copy;
  235. - optional style learning where a single edit remains a candidate rule until repeated or confirmed;
  236. - a deterministic Markdown audit for headings, digest, mobile paragraph length, local image paths, source signals, generic phrases, and personal-event provenance.
  237. Example:
  238. ```text
  239. Use the wechat-writer skill to create a Chinese WeChat Official Account article
  240. about how small AI teams should evaluate image-generation APIs.
  241. Audience: AI product founders
  242. Article type: comparison and decision guide
  243. Requirements: current source verification, a claim ledger, two revision passes,
  244. a mobile-first final article, and a local image plan. Do not publish.
  245. ```
  246. Run the mechanical audit with:
  247. ```bash
  248. node writer/wechat-writer/scripts/audit-wechat-markdown.mjs \
  249. writer/output/<article-slug>/article.md \
  250. --keyword "<core topic>"
  251. ```
  252. The script reports deterministic signals only. It does not verify facts, originality, authorship, or editorial quality.
  253. ## Security
  254. - Never commit `writer/config/r2.config.json`.
  255. - Never include R2 credentials in prompts, articles, audits, manifests, logs, screenshots, or final responses.
  256. - Do not automatically search for or download remote credential files.
  257. - Prefer a bucket-scoped R2 token with the minimum required permissions.
  258. - Rotate credentials immediately if they appear in chat, Git history, logs, or screenshots.
  259. ## Related Skill Projects
  260. - [Awesome Codex Skills](https://github.com/flaqai/awesome_codex_skills)
  261. - [Awesome Claude Code Skills](https://github.com/flaqai/awesome_claude_code_skills)
  262. - [SEO Audit Skill](https://github.com/JeffLi1993/seo-audit-skill)
  263. - [Humanizer](https://github.com/blader/humanizer), which inspired the post-audit humanization pass
  264. - [WeWrite](https://github.com/imraywang/wewrite), which inspired parts of the WeChat-specific task, evidence, review, and workflow design
  265. ## About Flaq.ai
  266. [Flaq.ai](https://flaq.ai/) provides unified API access to image, video, music, and language models for AI agents and production applications. The Flaq AI team maintains this repository as an open-source resource for practical, verifiable, and reusable content workflows. Model availability, capabilities, and pricing can change, so verify current details on the official site before publishing time-sensitive claims.
  267. ## More Prompt Projects from Flaq AI
  268. The following public, non-archived prompt libraries were verified from the [Flaq AI GitHub organization](https://github.com/orgs/flaqai/repositories):
  269. | Project | Focus |
  270. |---|---|
  271. | [Awesome MiniMax H3 Video Prompts](https://github.com/flaqai/awesome-minimax-h3-video-prompts) | Production-oriented audiovisual prompts and MiniMax H3 workflows |
  272. | [Awesome Seedance 2.5 Prompts](https://github.com/flaqai/awesome_seedance_2_5) | Seedance 2.5 video prompts for marketing, social, cinematic, UGC, and advertising use cases |
  273. | [Awesome Qwen Image 3 Prompts](https://github.com/flaqai/awesome-qwen-image-3) | Multilingual Qwen Image 3 prompt library with visual examples |
  274. | [Awesome Wan 3.0 Prompts](https://github.com/flaqai/awesome_wan-3-0-prompts) | Wan 3.0 video prompt patterns and creative workflows |
  275. | [Awesome FLUX 3 Prompts](https://github.com/flaqai/awesome-flux-3-prompts) | FLUX 3 video prompts for commercial and creative production |
  276. ## License
  277. See [LICENSE](./LICENSE).
  278. ## Flaq.ai Affiliate Program
  279. Flaq.ai now offers an affiliate program for developers and creators. After registering, you can share your unique referral link, recommend Flaq.ai services, and earn commissions on eligible orders from referred users. [Join the Flaq.ai Affiliate Program](https://flaq.ai/affiliate-program/) and review the official page for current commission rates and program rules.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.