Docs & writing
16,621 rows, by stacks then stars
3,030 of these skill files have been read, by 1,951 distinct authors, and what they tell an agent counted. What Docs & writing authors agree on, and what they forbid
patdhlk/skills/skills/grill-with-docs Skill
0★ repoGrilling session that challenges a plan against the project's recorded domain model - existing decisions, requirements, and glossary terms from the sphinx-needs spec - and updates term and decision directives inline as the discussion crystallises. Use when the user wants to stress-test a plan against their project's documented language and decisions, or says "grill me with docs" / "check this plan against our decisions".
The same file is in 1 other repository
patdhlk/skills/skills/to-prd Skill
0★ repoTurn the current conversation context into a PRD as a living sphinx-needs spec document - one feature directive plus child requirement directives, traceably linked. Use when the user wants to create a PRD, capture a feature plan as requirements, or says "turn this into a PRD" / "write this up as a spec".
The same file is in 1 other repository
wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-architecture-docs Skill
0★ repoWrite or refactor architecture/design/ADR docs (current-state + first-principles form). Use when editing `docs/*设计*`/`*架构*`/`*ADR*`/`*RFC*`, or user asks write/修改 architecture/设计/ADR docs, or complains doc is 啰嗦/口水/AI味/AI痕迹/对话记录/辩证过程. Do NOT use for README or pitfall.
wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-engineering-playbook Skill
0★ repoWrite or refactor cross-project engineering playbook (Agent/LLM + backend; source in `docs/private/engineering-playbook/`, publish to 飞书/blog NOT GitHub). Use when user asks 写/沉淀/提炼 工程经验/Agent 经验/playbook/第一性原理/跨项目复用/技术博客/去AI味/AI痕迹. Do NOT use for project pitfalls.
wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-issue-backlog Skill
0★ repoWrite or refactor known-issues/backlog tracker (problem-first, evidence-before-solution). Use when editing `docs/KNOWN_ISSUES_AND_BACKLOG*.md`, or user asks 记录 bug/补 issue/整理待办/复审 issue, or complains entry has 拍脑袋解法/补丁式方案/启发式/AI味/先入为主. Do NOT use for postmortems or pitfall archive.
wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-pitfall-archive Skill
0★ repoWrite or refactor a pitfall archive (recurring failures → invariants; Google SRE blameless multi-incident form). Use when editing `*DEPLOYMENT*`/`*MANUAL*`/`*RUNBOOK*`/`*PITFALL*`/`*坑*`/`*手册*` under `docs/`, or user asks 沉淀部署经验/踩坑/故障复盘/去AI味/不再犯同样错误. Do NOT use for single postmortems.
wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-readme Skill
0★ repoWrite or refactor public README per standard-readme spec + GitHub 10-second rule. Use when editing `README.md`/`README_EN.md`/subfolder README, or user asks 写/同步/修改/更新 README, or complains README has 口水话/啰嗦/AI味/AI痕迹/中英混写/不像专业 GitHub 项目. Do NOT use for `docs/*.md`.
wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-skill Skill
0★ repoWrite or refactor an Agent Skill / SKILL.md (agentskills.io spec; portable across Cursor, Claude Code, etc.). Use when user asks to 写/create/refactor/audit/优化 a skill or SKILL.md, or asks why a skill 没触发/太长. Do NOT use for Cursor Rules, CLAUDE.md, AGENTS.md, MCP server.
wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-tech-article Skill
0★ repoWrite or refactor dense technical blog / Feishu articles for personal portfolio. Use when editing `docs/private/tech-articles/*.md`, or user asks 写技术博客/复习笔记/面试沉淀/干货/高密度/减少噪声/去AI味/AI痕迹/用图表达. Do NOT use for README, issue backlog, ADR, or pitfall archive.
RegionallyFamous/youish/skills/youish Skill
0★ repoRewrite, edit, tighten, punch up, or diagnose prose into better, concise writing that still sounds like the writer. Use for emails, posts, notes, thought dumps, docs, copyedits, diagnosis, voice profiles, or requests to make writing clearer, shorter, sharper, warmer, persuasive, less AI-sounding, or more like the user. Preserves facts, stance, rhythm, humor, formality, uncertainty, and weirdness. Needs source text or an established voice.
ULudo/codex-science-skills/skills/writing-reviewer Skill
no license0★ repoReview or rewrite scientific manuscript prose for peer-review-ready clarity, concision, paragraph flow, terminology consistency, grammar, tone, and professional wording while preserving technical meaning. Use after structure and technical claims are stable. Do not strengthen unsupported claims.
aidehua08/codex-obsdian/plugins/codex-obsdian/skills/obsidian-markdown Skill
0★ repoExplain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
The same file is in 1 other repository
aidehua08/codex-obsdian/skills/obsidian-markdown Skill
0★ repoExplain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
The same file is in 1 other repository
tjrice42/design-judgment-skills/visual-storytelling Skill
no license0★ repoCreate genuine diagrams, flows, and informative visuals that tell a story in the user's visual language — instead of flattening content into card grids or converting diagrams into text summaries. Use this skill whenever building portfolio pages, case-study visuals, or prototypes that present process, systems, comparisons, timelines, or data; whenever the user shares a diagram, sketch, or whiteboard photo to be recreated on their site; and whenever you notice yourself about to render information as a grid of icon-title-description cards. Pairs with voice (prose) — this is voice for visuals.
tjrice42/design-judgment-skills/voice Skill
no license0★ repoApply the user's personal writing voice to any prose written on their behalf — portfolio copy, case studies, bios, emails, LinkedIn posts, application materials. Use this skill whenever writing or editing text the user will publish or send as their own words, even if they don't mention voice or style. Also use it when the user wants to calibrate, update, or review their voice profile, or says something "doesn't sound like me."
tjrice42/design-judgment-skills/writing-guardrails Skill
no license0★ repoApply anti-AI-tell guardrails to any prose written on a person's behalf, in any project. Use this skill whenever producing text a human will publish or send as their own words (emails, documents, posts, marketing copy, READMEs, case studies, bios) even if no personal voice profile exists. Also use it when asked to "humanize" text, remove AI tells, or review writing for machine-sounding patterns. Complements a voice profile when one exists; stands alone when one doesn't.
NovateStudioGit/novate-studio-skills/copywriting/copy-writing Skill
0★ repoCompose high-conviction copy by synthesising the principles of the greatest copywriters in history — Ogilvy, Schwartz, Halbert, Hopkins, Bernbach, with Sugarman, Lansdowne Resor, Kennedy, and Bird as supporting lenses. Use for any copywriting task — cold emails, ads, headlines, landing pages, captions, brand lines, sales pages, product copy, outbound sequences, founder posts, scripts. Triggered by `/copy-writing` or natural-language requests like "we need copy for X", "we need strong copy for Y", "write the copy for Z", "draft the headline for…", "rewrite this so it actually converts". Runs a brief discovery exchange to lock the brief, picks a dominant voice from the masters, drafts the copy, then runs it through a fixed quality filter before delivering.
NovateStudioGit/novate-studio-skills/creative-production/visual-prompt Skill
0★ repoExpand a short visual brief into a Shlabu-density, paste-ready prompt for any modern image or video generation tool — Kling, Veo, Sora, Seedance, Higgsfield, Flux, GPT Image, Nano Banana, or Midjourney. Trigger this skill in TWO modes. (1) Explicit — the user types `/visual-prompt` or natural-language like "expand this prompt", "make this prompt detailed", "give me the long version", "Shlabu this", "write the detailed prompt for [scene]". (2) Auto-detect — the user's last message LOOKS like a raw visual brief: a short declarative scene description (1–4 sentences), photographic/cinematic vocabulary like "shot of", "POV", "angle", "frame", "lit by", "hero shot", a subject + setting + intent shape, and no other clear request type (not a question, not a feedback note, not a code request, not a meta-conversation). When triggered in auto-detect mode, do NOT compose the prompt yet — first respond with a one-line gate asking Will to confirm by typing `/visual-prompt`, then wait. Only compose after explicit confirmation. Output is a single comma-spliced prose paragraph at Shlabu density (250–350 words) for prose tools, or a comma-separated keyword + parameter line for Midjourney.
NovateStudioGit/novate-studio-skills/email-marketing/klaviyo-campaign Skill
0★ repoGenerate, design, and schedule a complete Klaviyo email campaign in one command — subject line A/B variants, preheader, body copy, designed HTML template, segment assignment, scheduled send. Approval gate before anything goes live. Trigger when the user says "send a campaign", "write me a Klaviyo campaign", "draft an email for X", "schedule a campaign", or pastes a campaign brief. Replaces the writer + designer + sender roles in one pass.
NovateStudioGit/novate-studio-skills/email-marketing/klaviyo-weekly Skill
0★ repoMonday morning Klaviyo intelligence — pulls last 7 days of campaign + flow performance, attributes revenue, flags underperformers, recommends one A/B test, one flow tweak, and one new campaign theme for the week ahead. ~2 min, fully automated. Trigger when the user says "weekly report", "Monday update", "how did emails do last week", "Klaviyo weekly", or per-cron on Mondays.
NovateStudioGit/novate-studio-skills/knowledge-ops/notion-import Skill
0★ repoBulk-import rows from CSV / Google Sheets / markdown / pasted data into an existing Notion database, with auto-inferred column mapping and a dry-run report before any write. Use when the user says "import this into Notion", "load these rows", "add this CSV to the database", "bulk-add to <tracker>". Never writes without showing the mapping + sample first.
jae-labs/skills/skills/md-docs Skill
0★ repoUse ONLY to update or initialize README.md, CLAUDE.md, or AGENTS.md. Do not trigger for other Markdown files.
jae-labs/skills/skills/postmortem-writer Skill
0★ repoAssists the user in writing high-quality, blameless, and actionable incident postmortems (RCA reports) by conducting an interactive interview and generating a structured markdown file.
jae-labs/skills/skills/writing-plans Skill
0★ repoUse when you have a spec or requirements for a multi-step task, before touching code. Mandatory after approved spec/triage for substantial implementation work; do not skip straight to coding.
justinneuman-coder/unicornkick-skills/unicornkick-writer Skill
0★ repoAI coaches that refuse to do the work for you. Launch Dreams. Start Thriving. Write the book. Launch the business. Run the ultra. Open Agent Skills (agentskills.io) for Claude, Codex, Gemini, Cursor, and more. Free, from Ultra-Normal LLC
BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/doc-coauthoring Skill
0★ repoStructured coauthoring workflow for documentation, PRDs, RFCs, technical specs, decision records, proposals, handoffs, roadmaps, postmortems, and project plans. Use when the user wants to write, refine, review, or stress-test a substantial document so it is clear for real readers and execution-ready.
BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/internal-comms Skill
0★ repoPractical internal communication writing workflow for status reports, 3P updates, leadership updates, project updates, incident reports, FAQs, launch notes, team announcements, and executive summaries. Use when the user asks to write, polish, summarize, or package work for teammates, stakeholders, leadership, or future handoff.
BAKUGOS1/SkilledAgents-Toolkit/skills/codex/doc-coauthoring Skill
0★ repoStructured coauthoring workflow for documentation, PRDs, RFCs, technical specs, decision records, proposals, handoffs, roadmaps, postmortems, and project plans. Use when the user wants to write, refine, review, or stress-test a substantial document so it is clear for real readers and execution-ready.
BAKUGOS1/SkilledAgents-Toolkit/skills/codex/internal-comms Skill
0★ repoPractical internal communication writing workflow for status reports, 3P updates, leadership updates, project updates, incident reports, FAQs, launch notes, team announcements, and executive summaries. Use when the user asks to write, polish, summarize, or package work for teammates, stakeholders, leadership, or future handoff.
AGilbertDev/agilbertdev-recipes/skills/tutorial-mode Skill
no license0★ repoCollaboration mode for learning-by-building. Use when AGilbertDev wants to learn a project rather than have it built for him. Teach step by step, point at the right tools, and do NOT write or edit the code for the user. This is an opt-in per-project mode, not an always-on convention.
Andiedie/skills/skills/documentation-maintenance Skill
no license0★ repoDocumentation maintenance for agent-first project docs. Use when asked to create, update, prune, reorganize, review, or decide whether to document repository knowledge such as agent instructions, context maps, ADRs, runbooks, docs indexes, or docs-as-code.
Andiedie/skills/skills/documentation-reseed Skill
no license0★ repoOne-off documentation reseed for clearing old doc structure into a dated backup, rebuilding agent-first sources of truth from verified repo facts and old-doc evidence, and pruning stale docs. Use for full repository docs resets, not routine documentation maintenance.
selamy-labs/agent-skills/skills/c4-architecture Skill
0★ repoUse when documenting a system's architecture, not just drawing one diagram. Apply the C4 model — context, container, component, deployment — choosing the level by audience, stopping at context plus container for most teams, and writing the result into versioned markdown.
selamy-labs/agent-skills/skills/command-creator Skill
0★ repoUse when turning a repeated workflow into a Claude Code slash command. Structure the command markdown, choose argument handling and allowed tools, and write agent-executable steps so the workflow runs consistently instead of being re-explained every time.
selamy-labs/agent-skills/skills/criticality-tiered-reporting Skill
0★ repoUse when deciding what a service or worker should report and how loudly — alerts, progress updates, logs, notifications. Tier output by criticality so the important signal is not buried in routine chatter.
selamy-labs/agent-skills/skills/readme-excellence Skill
0★ repoUse when creating or auditing a repository README. A README earns its keep — every section answers a real reader question, the quickstart actually runs, and a diagram appears only when it replaces prose.
selamy-labs/agent-skills/skills/typed-rewrite-migration Skill
0★ repoUse when migrating an untyped or legacy core to a typed/rewritten one without a risky big-bang cutover. Strangle it incrementally behind a stable boundary, run old and new in parallel to prove equivalence, and cut over slice by slice while both stay green.
Chykalophia/cro-research-reporting/skills/report-information-design Skill
0★ repoThis skill should be used when turning analysis or research into a polished, well-organized report, brief, audit, or one-pager, especially a self-contained HTML document. Trigger phrases: "build a report", "write up the findings", "create an HTML report/brief/audit", "turn this research into a report", "how should I present this", "organize this information", "make it look professional", "add an executive summary and recommendations". Use it whenever findings need to become a shareable deliverable.
The same file is in 1 other repository
secapi-ai/secapi-skills/write-country-regime-report Skill
no license0★ repoWrites a dated country macro brief from the high-signal pack and regime context. Use when observed data, release timing, and uncertainty must be separated from forecast.
shuymn/skills/skills/proofread Skill
no license0★ repoReview text for AI writing tropes and mechanical prose patterns, then report findings with concrete rewrite suggestions. Use when the user asks to proofread, lint, or polish writing — especially docs, blog posts, READMEs, commit messages, PR descriptions, or any prose that should read as human-written. Also use when the user says "check for AI slop", "does this sound like AI", "make this sound more natural", or wants to de-AI their text.
percymcn/agent-cookbook/skills/research/research-paper-writing Skill
0★ repoWrite ML papers for NeurIPS/ICML/ICLR: design→submit.
The same file is in 3 other repositories
percymcn/agent-cookbook/skills/software-development/writing-plans Skill
0★ repoWrite implementation plans: bite-sized tasks, paths, code.
The same file is in 1 other repository
andersonoliveiraventurini/esquadrao-classe-a/.agents/skills/storytelling Skill
no license0★ repoAcione este esquadrão quando precisar construir, estruturar ou diagnosticar narrativas — storytelling de marca, roteiros e arcos de história, pitch, apresentações persuasivas, manifestos de movimento e desbloqueio criativo. Reúne frameworks como Jornada do Herói, Beat Sheet, Story Circle, Story Grid, Sparkline e ABT. Keywords: storytelling, narrative, screenplay, pitch, brand-story, persuasion
andersonoliveiraventurini/esquadrao-classe-a/esquadrao-completo/skills/storytelling Skill
no license0★ repoAcione este esquadrão quando precisar construir, estruturar ou diagnosticar narrativas — storytelling de marca, roteiros e arcos de história, pitch, apresentações persuasivas, manifestos de movimento e desbloqueio criativo. Reúne frameworks como Jornada do Herói, Beat Sheet, Story Circle, Story Grid, Sparkline e ABT. Keywords: storytelling, narrative, screenplay, pitch, brand-story, persuasion
andersonoliveiraventurini/esquadrao-classe-a/storytelling/skills/storytelling Skill
no license0★ repoAcione este esquadrão quando precisar construir, estruturar ou diagnosticar narrativas — storytelling de marca, roteiros e arcos de história, pitch, apresentações persuasivas, manifestos de movimento e desbloqueio criativo. Reúne frameworks como Jornada do Herói, Beat Sheet, Story Circle, Story Grid, Sparkline e ABT. Keywords: storytelling, narrative, screenplay, pitch, brand-story, persuasion
esaldgut/ai-native-engineering-workspace/global-skills/aws-go/mongo-ttl-bson-tag-match Skill
0★ repoWhen creating or modifying a MongoDB TTL index from Go, the index Keys field MUST match the Go struct's bson tag exactly (byte-for-byte, case-sensitive) and the field MUST serialize to BSON Date. MongoDB silently skips documents that lack the indexed field or whose field isn't a date — no error, no warning, no log. A snake_case-vs-camelCase typo between bson:"expiresAt" and a Keys:{"expires_at"} index leaks storage forever and you find out weeks later via the cost graph. Use before any migration that calls SetExpireAfterSeconds, or when writing the first timestamped document of a new collection.
esaldgut/ai-native-engineering-workspace/global-skills/claude-code-workflow/project-init Skill
0★ repoInitialize or audit a project against a generic platform-base documentation set so that work never starts from an ambiguous context. Applies the rule "no project starts ambiguously": the project loads context from the generic platform base first, then extends it. Auto-invoke when a project's CLAUDE.md has no "Platform Base Context" block, when the user asks to initialize or bootstrap context, or when starting work in an unfamiliar repo. Generates/verifies the base context block in CLAUDE.md (via @import) and suggests per-domain extension docs.
Nick2bad4u/codex-skills/skills/documentation-maintenance Skill
no license0★ repoMaintains repository docs, TSDoc, TypeDoc output, API comments, and Docusaurus sites. Use when fixing docs drift, TypeDoc diagnostics, TSDoc quality, broken examples/links, or polishing an existing Docusaurus portal.
Nick2bad4u/codex-skills/skills/remark-plugin-maintenance Skill
no license0★ repoBuilds, audits, and maintains remark and remark-lint plugin repos. Use when scaffolding plugins, creating or repairing remark-lint rules, auditing unified/Markdown AST usage, syncing docs/tests/configs, or validating package/CLI behavior.
detro/quirks/skills/keep-a-changelog Skill
0★ repoManages the project's CHANGELOG.md following the detected or requested format (e.g., Keep a Changelog or HashiCorp/Terraform format). Bootstraps a new changelog, creates entries for new releases, or updates in-progress entries in-place based on git history.
frankxai/marine-agent-skills/skills/species-page Skill
0★ repoUse when authoring or updating a Blue Life Commons species page (cetacean, pinniped, turtle, shark/ray, reef). Produces schema-valid Markdown with sourced claims and honest review status. Triggers — "write a species page", "add a species to the commons", "document <species>".
stardustai/stardust-skills/skills/dingtalk-browser-export Skill
0★ repoExport the currently open DingTalk/Alidocs document from a logged-in Chrome session without relying on the browser save dialog. Use this whenever the user asks to export, download, save, or back up the current DingTalk document to Word (.docx), PDF, or Markdown, especially when Chrome download popups would block automation.
yogeshg665/sleuth-fraud-investigator/skills/investigation-reporting Skill
0★ repoProduces an audit-ready case report and a human-readable narrative summarizing the transaction, signals, score, decision, and recommended actions. WHEN: "write the case report", "summarize the investigation", "generate fraud report", "explain the decision", "audit trail", "case narrative".
HM-IT-CODE/forge-skills/skills/engineering/tdd-loop Skill
0★ repoDrives a strict test-driven development loop for any new behavior or bug fix. Use when the user asks to implement a feature, add functionality, fix a bug, or says "use TDD" / "write tests first". Forbids writing production code before a failing test exists.
jimyoshida/generic-agent-skills/.agents/skills/translator Skill
no license0★ repoUse as a Japanese-English / English-Japanese translator. Triggered when the user wants to translate text between Japanese and English. Keywords include "translate", "translation", "put into English", "put into Japanese", "English version", "Japanese version".
krkrkrr/skills/skills/docs/extract-glossary Skill
no license0★ repo指定されたリポジトリ、複数リポジトリ、または GitHub organization から、ドメイン固有の専門用語、業界用語、社内・プロダクト用語、リポジトリ実装マップ、技術構成、オンボーディング向け Mermaid 構成図を抽出・生成するときに使う。ユーザーが「用語集を作る」「ドメイン辞書を作る」「オンボーディング資料にする」「repo/org を見て専門用語をまとめる」「AI が再確認しなくてよい知識ベースを作る」と依頼したら起動する。
krkrkrr/skills/skills/docs/japanese-tech-writing Skill
no license0★ repo日本語の技術文書・書籍原稿の文章規範。整形(一文一行、引用ブロック、脚注、コラム記法)、段落と論証の構成(パラグラフライティング)、論証の厳密さ(ツッコミどころの除去)、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。
krkrkrr/skills/skills/docs/readme-guidelines Skill
no license0★ repoTemplates and policies for README.md files. Use when creating a new README.md, updating an existing one after code changes, or creating/syncing the Japanese version README-ja.md. Covers template selection by project type, section-level writing rules, and which sections to update for which kind of change.
krkrkrr/skills/skills/frontend/frontend-review-weekly Skill
no license0★ repoUse for the weekly AI review. Orchestrates all frontend-review-* skills in order, dispatches the 5 perspective sub-skills in parallel, diffs against last week's KPIs, and produces a weekly report that feeds the ratchet.
Translate programming language
krkrkrr/skills/skills/lang/translate-programming-language Skill
no license0★ repoPlan and execute language-to-language server or application migrations with behavior parity. Use when porting modules, services, APIs, or runtimes between programming languages; generating source-runtime oracles and fixtures; generating migrated parity tests; detecting runtime, standard-library, serialization, numeric, encoding, time, regex, or protocol differences; building temporary compatibility layers; accumulating migration knowledge; benchmarking; shadow testing; canarying; or planning cutover and rollback.