Writing & Editing

Stage 5 of a wp-site-kit WordPress build - titles and descriptions, canonical URLs, one schema owner and JSON-LD, sitemaps, robots.txt and llms.txt, AI crawler access, redirects (301 vs 302), legacy URL maps, Search Console, and adding languages one pilot at a time with Polylang (hreflang, .po/.mo strings, native review). Use for "SEO", "schema", "redirect", "old URLs", "translate the site", "add French/Spanish", "hreflang", "canonical".

Write the quiz for one unit (for example a video check at the start of the session) into the course's quiz source, then create it in the course's quiz tool - through a connector if one is connected, otherwise as an import file. Type the unit after the command.

Guidance for writing the information on an organization's Vianido profile while updating and managing it (tagline, mission, description, About page blocks, metrics and figures, image alt text, quotes). Use whenever drafting or rewriting profile content for an organization on Vianido.

Write developer documentation people actually read and trust. Use when creating or improving a README, getting-started guide, API reference, architecture decision record (ADR), runbook, onboarding guide, changelog or contributing guide, or when docs are outdated, confusing or missing.

Finds the phrases people actually search for and puts them in the right places on YouTube, TikTok, Instagram and Google. Builds a keyword table with search intent and placement (title, first line, spoken opening, on-screen text, description, chapters), checks titles and captions against the target phrase, and uses a keyword connector such as vidIQ when one is connected. Use when someone asks about SEO, keywords, search, discoverability, hashtags, or why a good video is not being found. Showrunner has no search-volume data of its own and says so.

Read, revise and develop screenplays, series and novels stored in Scenaloom (scenaloom.com) through its MCP server. Use when the user mentions Scenaloom, or their script, screenplay, episode, scene, novel chapter, characters, locations, beats, outline or comments in Scenaloom, or asks to punch up dialogue, fix structure, leave notes, or make character portraits and storyboard frames from their project.

Drafts a Privacy Policy, Terms of Service and Refund Policy for a SaaS, digital product or website from a short questionnaire, adapted to the payment provider (Creem, Paddle, Lemon Squeezy as Merchant of Record, or Stripe/direct) and to where users are (EU/UK GDPR, California CCPA/CPRA, China PIPL notes), then renders them as Markdown, HTML or Next.js pages and links them in the footer. Output is a starting template, NOT legal advice - the user must review it and have it checked by a qualified lawyer. Use when the user needs privacy policy, terms, refund policy, legal pages, or a payment provider (Paddle/Creem/Lemon Squeezy/Stripe) review asks for them.

Writing text another AI will act on. Use when writing or improving a subagent prompt, a prompt for another session, a handoff, a message to an external AI, an autonomous-run brief, a skill or CLAUDE.md, or choosing a reader's model and effort. Not for explaining a prompt.

Construct a project README through user choices about its structure, section content, and visuals. Use for a new README, a major README redesign, or an explicit README constructor request.

Write Instagram DMs that get replies - the keyword delivery, the first message to someone who engaged, the collab pitch, and the two follow-ups. Use when the user says "DM this person", "what do I send them", "outreach message", "how do I follow up", "pitch this brand", or is reaching out to someone specific.

글쓰기 루프: 접수 → 설계 → 초안 → 윤문 → 점검 → 판정(되돌리기) → 넘기기를 돌려 글을 완성하는 상위 스킬. doc-coauthoring(기획·초안), marketingskills(카피·SNS·이메일·보도·행사), humanize-korean(한국어 AI 티 제거), stop-slop(5축 채점), policy-media-desk(평가로 느껴지지 않는 문체, 씨줄×날줄, 보도자료 변환 규칙, 선거법), ax100-log-desk(사실·해석 구분), ax-classroom-builder(교육 안내), draft-preview·docx·google-docs(전달)를 한 사슬로 엮는다. 트리거: 글쓰기 루프, 글 완성해줘, 초안부터 마무리까지, 보고서·기획안·제안서·칼럼·인사말·보도자료·홍보문·뉴스레터·SNS 글 써줘/다듬어줘, 퇴고, 글 점검·채점, 몇 번 고쳐서 좋은 글로.

스토리텔링 루프: 로그라인을 북극성으로 삼아 접수 → 로그라인 공방 → 뼈대 → 인물 → 장면·회차 설계 → 초고 → 점검(로그라인 대조·대항 리뷰·실화/공공 게이트) → 판정(작가 반박·되돌리기) → 넘기기를 돌리는 상위 스킬. screenwriting(jtydhr88 작법 22모듈, sw-workflow 단계표·story-bible), screenplay-review-checklist(37개 기준 대항 리뷰), writing-loop(기획의도·홍보 문장), marketingskills(쇼츠·홍보), humanize-korean(지문·기획서만)을 엮는다. 트리거: 스토리텔링 루프, 로그라인 잡아줘, 드라마 대본, 시나리오, 극본, 웹드라마, 숏폼 드라마, 단편영화, 연극, 영상 시리즈 구성안, 쇼츠 대본, 실화 각색, 평전 서사, 이야기 구조, 시놉시스, 트리트먼트, 회차 구성, 공모전 원고.

JSON-LD 구조화 데이터 작성·점검: Event(행사·전시·박람회, 취소·연기 상태), Organization + sameAs(네이버 사이트 연관채널), WebSite(Google 사이트 이름), BreadcrumbList, ItemList. Google과 네이버의 지원 차이 포함. "구조화 데이터", "schema.org", "JSON-LD", "리치 결과", "Event schema", "이벤트 마크업" 요청에 사용. Structured data templates aligned to Google and Naver docs.

Build the slides for one unit from its approved session plan - one section per input block, one slide per group task - in the course's slide format. Type the unit after the command.

여러 검색·공유·AI 채널(Google, 네이버, Daum/카카오, Bing, Brave, DuckDuckGo, Apple, X, 카카오톡, Meta, ChatGPT·Perplexity·Claude 검색)을 한 번에 맞추는 SEO 작업의 시작점. 대상 채널을 정하고 하위 Skill(google-search, naver-search, daum-search, other-search-engines, ai-crawlers, structured-data, social-preview, indexnow, scaled-pages, browser-compat)을 순서대로 조합해 점검·구현·보고한다. "SEO 해줘", "검색 노출 점검", "구글이랑 네이버 둘 다", "SEO audit", "launch SEO checklist" 같은 요청에 사용. Entry point that combines search engine, AI crawler, social preview, structured data and browser skills.

Use when filling in or auditing App Store privacy and compliance answers and Google Play App content declarations - Apple App Privacy labels, Play Data safety (CSV import), Health apps declaration and Health Connect permissions, advertising ID, PrivacyInfo.xcprivacy and required-reason APIs, export compliance (ITSAppUsesNonExemptEncryption), age rating, account deletion (in-app, web URL, re-authentication), consent and disclosure for AI features, and rules for health data. Derives every answer from a code and SDK scan so the forms, the privacy policy and the in-app text say the same thing.

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Go and find the reels that are actually working right now in the user's niche, rank them by how far each beat its own account, name the hook formula each one used, and turn that into a swipe file they can shoot from. Use when the user says "find viral videos", "what's working right now", "what are people posting in my niche", "reverse engineer this account", "build me a swipe file", "why is this reel doing numbers", or asks what to make next and has no evidence to answer with.

네이버 검색 SEO(서치어드바이저·웹마스터도구): 검색로봇 Yeti, robots.txt, 사이트 소유 확인, 대표 URL·로봇 메타(noindex, nosourceinfo), title·description·오픈그래프, RSS·사이트맵 제출, 수집 요청·검색 제외, JavaScript·SPA, 모바일, 파비콘, 콘텐츠·스팸 정책, IndexNow. "네이버에 안 나와요", "네이버 SEO", "서치어드바이저", "Yeti 차단", "네이버 사이트맵 제출" 요청에 사용. Naver Search Advisor SEO for Korean sites.

Run a coding or research task through humanize (hmz), an agent-flow orchestrator that drives Claude Code, Codex and other agent CLIs in loops such as actor + reviewer (rlar). Use when the user says "use humanize", "use hmz", "run it in hmz", "rlar this", or wants a task done by an implementer agent checked by a separate reviewer agent, a long unattended agent loop (hours to days), or Claude implementing while Codex reviews. Not for rewriting text to sound more human.

Write, revise and analyze prose as a manifold of meanings presented like music. Use when a passage must carry more than it says (ambiguity on purpose, foreshadowing, a second sense the reader completes later) without turning into flat, uniformly "deep" machine prose; and to analyze a piece with the same framework (name its genre, read its shape, reconstruct its ledger, name what fails and why). Covers the three dials (ambiguity 1 to 5, default 4; the writer's mindset and how far gone; the reader's strength, which caps density), the ledger of promise and payment, the glance (what a page says before a word is read), the topic and stress positions, purpose and genre, the three punches (land, refrain, release), rhythm as emotion, tempo, forms with transitions, the figures (recursive paragraph, litany, withheld word), the swear as an accent, and the dash redeemed as a rest. Pairs with the Poet tool when it is available; works without it.

Use when building, checking or deploying the website that a mobile app needs for its store listings and launch - privacy policy, terms, support and web account-deletion pages that work signed-out; hosting apple-app-site-association and assetlinks.json; invite/referral pages (/i/<code>) that open the app or fall back to the store with the Play install referrer; a landing page with store badges and honest per-country prices filled at the edge; Open Graph images; technical SEO (hreflang, canonical, sitemap, robots.txt, JSON-LD); Search Console, Bing Webmaster and IndexNow; AI crawler policy and llms.txt; and a Cloudflare Worker deploy with a production approval gate. Includes a site checker and an IndexNow ping script.

Use when asked to review a branch or pull/merge request and track its issues until they are fixed, or when invoked by name. Asks for the target branch, base branch and ticket, checks the environment, reviews the code and its prose, verifies every finding against the code, and publishes a read-only Artifact page listing each issue with its status, evidence, fix assessment and file:line. Re-reviews the branch on each update, drafts PR comments and tickets for the user to post, and keeps a small re

Florida business entity lookup in official Florida Division of Corporations records, the data behind Sunbiz. Send a business name and get candidate matches with document number, status, filing type and date, registered agent, officers, home state, annual report status, status change history, and the Florida source file for each record. Use it for KYB before paying, onboarding, or contracting with a Florida company. Florida only. A result is a candidate name match, not proof of identity. 0.10 USD