Docs & Writing
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
-
nexu-io Bundle Shuffle TextLetters shuffle through random neighbors then settle into the word — a quick playful reveal for a short label. Final text is the real content; instant under prefers-reduced-motion.
-
nexu-io Bundle Rotating TextOne word swaps for the next in place — a compact way to cycle a few phrases in a headline. One rotator per view; short words. Under prefers-reduced-motion it swaps text with no travel.
-
nexu-io Bundle Toggle SpringA switch whose knob springs across on toggle — a tactile, satisfying on/off state change. Use for settings/form switches. Honors prefers-reduced-motion (quick linear slide). Trigger on user intent only; keep the spring subtle — never to convey loading/progress.
-
dnyoussef Bundle When Creating Presentations Use PPTX GenerationWhen Creating Presentations Use Pptx Generation
-
kyrie66nb Bundle DocRead, create, and edit DOCX.
-
kyrie66nb Skill Ultraqa[OMX] Adversarial dynamic e2e QA workflow - generate hostile scenarios, test, verify, fix, report, and clean up
Audited -
kyrie66nb Skill Word DOCXWord and DOCX editing alias for Documents and officecli-docx.
-
kyrie66nb Skill Paper CompileCompile LaTeX papers to PDF.
-
kyrie66nb Skill Lunwen Format DOCXFormat Chinese thesis DOCX.
-
kyrie66nb Skill CLI Anything OfficecliGenerate and fix DOCX reports.
-
kyrie66nb Bundle Officecli DOCXCreate and edit Word DOCX.
-
kyrie66nb Bundle Officecli PPTXCreate and edit PowerPoint decks.
-
kyrie66nb Bundle Officecli Academic PaperAcademic paper DOCX tools.
-
kyrie66nb Bundle Math OlympiadSolve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes.
-
maxrave-dev Skill Slide Transition Defaults To Half A HeightA vertical slide transition defaults to HALF the element's height, so it appears already halfway through its own movement and the first part is missing — which reads as a pop, not a slide. Covers passing the full height, the sign that decides which edge it comes from, pairing a shorter fade with a longer slide so the element is opaque before it settles, making exit quicker than enter, and publishing the pair as shared values so every screen matches. Use when a bar or panel seems to snap into place instead of sliding, when enter and exit feel mismatched, or when the same control animates differently on two screens.
-
modu-ai Bundle Doc Hwp아래아한글(.hwpx) 문서를 만들어 드립니다 — 한컴오피스에서 열리는 공문서·기안서·품의서·보고서를 작성하고, 기존 HWP 파일을 HWPX로 변환합니다. 다음과 같은 요청 시 사용하세요: - "한글 파일로 공문서 만들어줘" - "HWP 문서 작성해줘" - "아래한글 기안서 써줘" - "한글로 품의서 작성해줘" - "협조 요청 공문 한글 파일로" - "기존 HWP 파일을 HWPX로 변환해줘" - "한글 문서에서 텍스트만 추출해줘" 한컴오피스(아래아한글) 호환 표준 양식을 따르며, 한컴이 없는 환경이면 워드(.docx) 생성으로 대체할 수 있습니다. 아래아한글(.hwpx) 문서를 만들 때는 Claude 기본 생성 대신 이 스킬을 사용하세요. [책임 경계] vs moai-officer:doc-docx: 이 스킬=한컴 .hwpx 한글 파일, 저 스킬=MS 워드 .docx 파일.
-
modu-ai Skill Cs Voc Triage고객의 소리(VOC) 전체를 다루는 엄브렐러 스킬 — 멀티채널 리뷰를 통합 분석하고(리뷰는 VOC의 한 원천), 폭주하는 VOC의 처리 우선순위를 3축 분류 + KTAS 응급실 5단계로 판별합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "리뷰 모아서 분석해줘", "리뷰 분석해줘", "수백 개 리뷰 정리", "감정 분석 리뷰", "쿠팡 리뷰 키워드", "리뷰 인사이트 액션플랜", "멀티채널 리뷰 통합", "VOC 분류해줘", "VOC 처리 순서", "고객 문의 우선순위", "응급 VOC 분류", "VOC 트리아지", "KTAS 응급실 분류 VOC" 2개 동작 모드가 자연어로 자동 선택됩니다 — ① 리뷰 집계 모드(4채널 리뷰 → 감정·키워드·인사이트·액션플랜 4단 분석) ② VOC 분류·트리아지 모드(고객 핏·빈도·핵심 가치 3축 × KTAS 5단계 응급도 → 처리 순서 + 응답 템플릿). 텍스트 산출물(인사이트·액션플랜·응답 템플릿)은 moai-coworker:ai-slop-reviewer를 자동 체이닝합니다. [책임 경계] 응답 메시지 카피 작성은 moai-cs:cs-channel-message, 분석 결과 PPT는 moai-officer:doc-pptx로 위임.
-
modu-ai Bundle Doc DOCX편집 가능한 워드(.docx) 문서를 만들어 드립니다 — 보고서, 계약서, 제안서, 공문서, 기획서를 한국형 디자인 톤으로 바로 쓸 수 있게 출력합니다. 다음과 같은 요청 시 사용하세요: - "보고서 워드 파일로 만들어줘" - "계약서 DOCX로 작성해줘" - "공문서 양식대로 써줘" - "제안서 워드 문서 만들어줘" - "사업 기획서 docx로 정리해줘" - "협조 공문 한 장 작성해줘" - "분기 보고서를 깔끔한 톤으로 워드로 뽑아줘" Claude 브랜드 톤 기반 모던 디자인 시스템과 한국 공문서 표준 양식을 함께 지원하며, 텍스트가 끝나면 AI 슬롭 검수로 자연스럽게 다듬을 수 있습니다. 보고서·문서를 워드(.docx) 파일로 만들 때는 Claude 기본 생성 대신 이 스킬을 사용하세요 (서식·디자인 보존).
-
modu-ai Skill Meta Feedback버그 리포트와 기능 요청을 수집하여 GitHub Issues에 자동 등록합니다. 다음과 같은 요청 시 이 스킬을 사용하세요: - "버그 신고", "기능 요청", "피드백", "개선 제안" - "/project feedback" 커맨드 실행 - "이슈 등록", "문제 신고", "bug report", "feature request" - 특정 플러그인/스킬의 문제점 보고 단순 불만 표출이나 일반 대화, 플러그인 사용법 질문에는 사용하지 마세요.
-
modu-ai Bundle Consult Sbiz365소상공인365(bigdata.sbiz.or.kr)에서 받은 상권분석 PDF를 첨부하면, 유동인구·경쟁 점포·예상 매출을 분석한 창업 타당성 보고서(Word)를 만들어 드립니다. 다음과 같은 요청 시 사용하세요: - "이 상권 PDF 분석해줘" - "소상공인365 보고서 분석해줘" - "이 지역에서 창업해도 될까?" - "창업 타당성 검토해줘" - "이 동네 카페 차려도 괜찮을까?" - "유동인구랑 경쟁 점포 분석해줘" - "예상 매출 어느 정도일지 봐줘" PDF를 첨부하면 업종·예산·목적을 먼저 물어본 뒤, 5대 분석과 창업 타당성 점수까지 담은 보고서를 만들고 AI 표현 다듬기로 이어집니다. [책임 경계] vs 산업 단위는 moai-consultant:consult-market, 온라인 카테고리·검색 키워드 단위는 moai-seller:commerce-market-research를 사용하세요. 이 스킬=오프라인 상권 단위 분석.
-
netvar1337 Skill Ponytail DebtUse to list ponytail: shortcut comments as a debt ledger (/ponytail-debt). Report only.
Audited -
netvar1337 Skill Eac Usermode Telemetry ReEasyAntiCheat_EOS.exe / usermode telemetry RE: modules, IPC to driver, heartbeats, report formats, packing.
Audited -
netvar1337 Skill Zdi Researcher GuidelinesUse when planning, triaging, packaging, or submitting vulnerability research to Trend Micro Zero Day Initiative (ZDI). Encodes official submission criteria, valuation factors, disclosure timelines, exclusivity rules, current product-interest suspensions, report quality bar, and portal workflow. Pair with zero-day-target-eligibility before investing in a target.
Audited -
pavel-kravchenko Skill Algo TriesImplement a trie (prefix tree) in Python for O(m) word insert/search, O(p) prefix checks, and O(p+k) prefix enumeration; build autocomplete, spell-checkers, and k-mer/gene-name lookup over DNA or dictionary strings. Use when asked for prefix tree, trie data structure, autocomplete implementation, dictionary/word membership, longest-prefix match, gene-name or k-mer prefix search, or radix/compressed trie.
-
acaprino Skill Research Deep ResearcherIterative web investigator for one research sub-question: orients with broad queries, reads the pages that matter, keeps a ledger of claims with sources and dates, narrows round by round and stops at saturation, then returns a compressed cited report. The worker that /research:team-research spawns in parallel, one per sub-question; also usable alone for a single focused investigation. TRIGGER WHEN: spawned by /research:team-research with a spawn block, or the user asks for one question to be investigated in depth across several sources with citations. DO NOT TRIGGER WHEN: the question is a single-fact lookup (use quick-searcher), the user wants a whole multi-question research run with a plan and a report file (use /research:team-research), the task is about local code or files, or the user is implementing or editing code.
-
acaprino Skill Team Research"Deep web research run: clarify scope only when needed, show a plan of sub-questions for approval, spawn one iterative researcher per sub-question in parallel, verify contradictions, synthesize a long-form cited report and write it to disk. Web only."
-
acaprino Skill Humanize TextDetect the 24 catalogued patterns and edit them out, then self-score the result. TRIGGER WHEN: the user asks to humanize prose/text, remove AI-sounding copy, or rewrite articles/blog posts/documentation for natural voice. DO NOT TRIGGER WHEN: cleaning up source code (use /clean-code:clean-code) or translating text.
Audited -
acaprino Skill Humanize DocsEdits documentation in place for a human reader. TRIGGER WHEN: the user asks to humanize existing docs, improve scannability, or rewrite dense technical writing for progressive disclosure. DO NOT TRIGGER WHEN: humanizing prose/articles (use /text-humanizer:humanize-text) or creating new docs (use /codebase-mapper:docs-create).
-
acaprino Skill Codebase Mapper Doc HumanizerRewrites technical docs into clear, scannable narrative. TRIGGER WHEN: documentation exists but reads like a wall of text or AI output. DO NOT TRIGGER WHEN: humanizing prose or articles rather than technical docs (use text-humanizer:text-humanizer), or generating new documentation from source code (use codebase-mapper:documentation-engineer).
-
acaprino Skill Instagram GrabDownload every photo and video from an Instagram profile at full resolution, including carousel slides and reels, into a local folder that can be re-run to pick up only what is new. TRIGGER WHEN: the user asks to grab, download, archive, mirror or back up the media of an Instagram profile or account, or wants the photos and videos of a page for reuse elsewhere. DO NOT TRIGGER WHEN: the target is a single post URL the user already has, a platform other than Instagram, or the task is building a new scraper for a different site, which belongs to the grabber-development skill and its specialists.
-
acaprino Skill Codebase Xray Partition Quality WorkerRuns Pattern and Risk Detection plus Documentation Health over one partition, writing 05-risks.md and 06-documentation.md into its owned partition directory (05 only in lite mode). TRIGGER WHEN: spawned by /codebase-xray:team-analyze in its second wave.
Audited -
argentaios Skill Argentos SongseeGenerate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.
Audited -
thinkfleetai Skill PDF ReaderPDF reading and extraction
-
thinkfleetai Skill API DocumenterGenerate API documentation: OpenAPI 3.1 specs, interactive docs with Swagger/Redoc, SDK generation, and JSDoc/TSDoc extraction.
-
netvar1337 Skill PlanUse for plan-mode only: write an actionable markdown plan under .hermes/plans/, no execution.
Audited -
dnyoussef Bundle DocumentationDocumentation
Frequently asked questions
What are Docs & Writing agent skills?
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
Which Docs & Writing skills are most installed?
Popular Docs & Writing skills on SkillMD right now include shuffle-text, rotating-text, toggle-spring. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Docs & Writing skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.