Docs & writing
16,614 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
Pdbjork/hermosskills-site/skills/ecc-brand-voice Skill
no license0★ repoBuild a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.
The same file is in 1 other repository
Ecc competitive report structure
Pdbjork/hermosskills-site/skills/ecc-competitive-report-structure Skill
no license0★ repoUse after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space analysis, strategic recommendations, and team alignment trigger questions. Final step in the three-skill competitive pipeline.
Pdbjork/hermosskills-site/skills/static-site-ship Skill
no license0★ repoShip a redesigned (or new) static website end-to-end on a VPS — design the site, build it, validate it, deploy to a static mirror under /var/www or equivalent, smoke-test nginx (with the right Host header) AND the backend capture service, write a handoff report, and ping the user. Load when the user asks to "redesign", "build", "ship", "deploy", or "publish" a website, especially a research/education/foundation/nonprofit public-facing site where privacy-by-default, consent-first forms, and "no false claims" discipline matter. Skip for SPA / SSR app deploys (Next.js, Vite, etc.) — those have their own build pipelines. Skip for hosted-platform-only deploys (Vercel/Netlify/Cloudflare Pages with no VPS mirror).
Pdbjork/hermosskills-site/skills/stop-slop Skill
no license0★ repoRemove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
The same file is in 4 other repositories
Pdbjork/hermosskills-site/skills/workers-best-practices Skill
no license0★ repoReviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
The same file is in 5 other repositories
puntorigen/skills/edit-docx Skill
no license0★ repoInspect and edit Microsoft Word .docx files while preserving formatting, styles, and layout - 100% locally with python-docx, no cloud or API keys. A small CLI (docx_tool.py) lists every document element with a stable index (paragraphs, tables, images, headers/footers), then applies surgical edits: run-aware find/replace that keeps bold/italic/font/color even across split runs, insert paragraphs with a chosen style, edit or append table cells, add table rows copying the previous row's formatting, delete elements, and list available styles. Use when the user wants to read, inspect, edit, modify, update, or fill in a Word document or .docx file; do find-and-replace in a .docx while keeping formatting; change or add table rows/cells; insert headings or paragraphs; work with headers/footers; or template a report, contract, or letter - without opening Word.
puntorigen/skills/pdf-documents Skill
no license0★ repoRead and create PDF documents entirely on-device - no cloud, no API keys. For reading, uses Docling (IBM's document AI) to turn a PDF into structured JSON, Markdown, text, or HTML with real layout understanding: extracted tables (as headers/rows + HTML), section/heading hierarchy, page images, and optional OCR for scanned pages (native macOS Vision OCR). For writing, uses fpdf2 to render a professional, multi-page PDF from a simple JSON config - titles, headings, justified paragraphs, styled tables with alternating rows, images with captions, bullet/numbered lists, key-value KPI blocks, dividers, headers and footers with page numbers. Use when the user wants to read, parse, extract, or inspect a PDF (text, tables, or structure), scrape data out of a PDF, OCR a scanned PDF, or generate/create a polished PDF report, invoice, proposal, or data sheet from data.
HeyEddi-com/skills/skills/heyeddi-intake Skill
0★ repoTranslates vague user prompts into HeyEddi product docs (personas, route intent, voice), route-specific handoff artifacts (wireframes, user mockups, or briefs), and skill-routing under .heyeddi/. Use first on new projects before @heyeddi-design, @heyeddi-handoff, or @flutter-engineering. Never hand-write product.md: use write_product.
HeyEddi-com/skills/skills/pre-merge-gate Skill
0★ repoRuns pre-merge checks (tests, build, types, optional UI audit) and returns a markdown pass/fail report. Use when QA approves a PR or before merge to main.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.agents/skills/pre-merge-gate Skill
0★ repoRuns pre-merge checks (tests, build, types, optional UI audit) and returns a markdown pass/fail report. Use when QA approves a PR or before merge to main.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.agents/skills/product-translator Skill
0★ repoTranslates vague user prompts into HeyEddi product docs (personas, route intent, voice), professional mockups, mockup briefs, and skill-routing under .heyeddi/. Use first on new projects before @heyeddi-design, @heyeddi-handoff, or @flutter-engineering. Never hand-write product.md — use write_product.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.cursor/skills/pre-merge-gate Skill
0★ repoRuns pre-merge checks (tests, build, types, optional UI audit) and returns a markdown pass/fail report. Use when QA approves a PR or before merge to main.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.cursor/skills/product-translator Skill
0★ repoTranslates vague user prompts into HeyEddi product docs (personas, route intent, voice), professional mockups, mockup briefs, and skill-routing under .heyeddi/. Use first on new projects before @heyeddi-design, @heyeddi-handoff, or @flutter-engineering. Never hand-write product.md — use write_product.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/product-translator-intake/.agents/skills/product-translator Skill
0★ repoTranslates vague user prompts into HeyEddi product docs (personas, route intent, voice), professional mockups, mockup briefs, and skill-routing under .heyeddi/. Use first on new projects before @heyeddi-design, @heyeddi-handoff, or @flutter-engineering. Never hand-write product.md — use write_product.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/product-translator-intake/.cursor/skills/product-translator Skill
0★ repoTranslates vague user prompts into HeyEddi product docs (personas, route intent, voice), professional mockups, mockup briefs, and skill-routing under .heyeddi/. Use first on new projects before @heyeddi-design, @heyeddi-handoff, or @flutter-engineering. Never hand-write product.md — use write_product.
Ego-System/fable-mode/skills/fable-writing Skill
0★ repoFable 5's writing discipline for prose that works: reports, documentation, READMEs, explanations, summaries, PR descriptions, commit messages, UX copy, emails, announcements. Use whenever the deliverable is text a human will read. Governs selection, structure, clarity, and calibration. Plugs into the fable-core loop; self-contained if fable-core is absent. Calibration exemplars in references/exemplars-writing.md.
gulmezeren2-byte/industrial-engineering-ai-skills/skills/weekly-ops-report Skill
0★ repoTurn raw operational data into a weekly management report that answers exactly three questions - what changed, where is it concentrated, what needs a decision. Use when the user mentions weekly report, haftalık rapor, yönetim raporu, ops review, KPI summary, or asks to summarize operational data for managers. Differentiator - contract-first reporting with plain-language findings and driver decomposition, never a chart dump.
shaokanp/pi-skills/skills/write-good-goal Skill
0★ repoWrite, refine, or audit paste-ready Codex or Claude Code goal text with feasible scope, explicit boundaries, agent-achievable Done criteria, progress selection, and human or follow-up gates. Use for goal-mode prompts, multi-round coding-agent objectives, or criteria that depend on future evidence or human decisions. Use agent-workflow to execute the team or loop; handle ordinary project plans directly.
angpysha/api2skill/.agents/skills/grill-with-docs Skill
0★ repoRelentless interview to sharpen a plan or design. All resolved information is written via Spec Kit (/speckit.* → spec.md/plan.md). Glossary (CONTEXT.md) and ADRs supplement only. Composes grilling + domain-modeling + spec-kit.
angpysha/api2skill/.agents/skills/openapi-contract Skill
0★ repoUniversal backend HTTP contract skill. Write OpenAPI 3.x (Swagger) specs from approved requirements. Architect or Team Lead authors the schema in Phase 5/6; Developer implements exactly to operationIds and request/response models. Use when REQ includes HTTP/API behavior.
angpysha/api2skill/src/Api2Skill/templates/api2skill-creator Skill
0★ repoInterview the user about an OpenAPI/Swagger API (including multi-spec, base URL, and authorization), assemble exact api2skill CLI commands, then guide secrets.json setup from secrets.example.json placeholders. Prefer Plan mode for multi-spec interviews.
tylensthilaire/skill-llm-wiki/skills/setup-llm-wiki Skill
no license0★ repoSet up an agent-maintained wiki in a project: a wiki/ folder of small, cross-linked markdown docs, a few contract lines in AGENTS.md, and the knowledge-operations conventions doc that governs them. Use this whenever the user asks to set up a wiki, knowledge base, or "second brain" for a project; whenever another skill needs a wiki to seed its conventions into and none exists; whenever a project has scattered documentation with no home for agent-readable knowledge; or whenever someone asks "where should project knowledge live". Runs once per project: it sets up the wiki, seeds its conventions, and is then no longer needed.
victorgrein/victorgrein-skills/engineering/to-spec Skill
no license0★ repoTurn explicitly designated input documents into an approved implementation spec in a per-spec folder under .context/specs. Use when the user explicitly invokes $to-spec with local or attached documents, documentation URLs, or pasted Markdown and wants uncertainties resolved through a one-question-at-a-time interview before the spec is written.
jcdavis131/cursor-agent-skills/skills/document-non-action Skill
0★ repoWhen you deliberately choose not to do something that looks like it would be part of the task, state the non-action and its rationale explicitly so it isn't read as an oversight. Use whenever you skip a plausible-looking step on purpose — a file you didn't edit, a feature you didn't wire, an existing issue you didn't rework, a test you didn't add — because of a real constraint or a lane/spec boundary.
jcdavis131/cursor-agent-skills/skills/readiness-report Skill
0★ repoDelivers a structured production-readiness handoff — numbered items needing operator input, each classified pre-existing vs introduced and tagged with repo issue IDs, plus exact verification commands. Use when a multi-task build is ready for operator review, before a deploy gate, or when decisions are the operator's to make.
jcdavis131/cursor-agent-skills/skills/sme-fanout Skill
0★ repoSpawn parallel subject-matter-expert subagents each owning one lane of a complex task, with a fixed output contract, then synthesize. Use when a task spans multiple distinct domains (e.g. security + perf + docs + tests + schema), when a single-agent pass would be shallow across all of them, or when the user asks for a multi-perspective review/report.
frankxai/skills/skills/tools/defuddle Skill
0★ repoExtract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
The same file is in 6 other repositories
uglyrobot/docsbot-agent-skills/skills/docsbot-documentation-search Skill
0★ repoSearch and fetch a DocsBot bot's indexed documentation, knowledge base, and training sources through a per-bot remote MCP server. Activate when a user asks to use an agent to answer from, inspect, retrieve, or cite content already indexed in a specific DocsBot bot.
paulgrape/skill-auditor/templates/website-i18n Skill
0★ repoInternationalisation essentials for a website — URL structure for locales, hreflang, localised metadata, the lang attribute on inline content, language switchers, RTL support, and locale-aware formatting. Use when adding multilingual or multi-regional content to a site.
vaibhavsaxena022/skills/keep-it-simple Skill
0★ repoWrite the simplest code that solves the actual problem — avoid over-engineering. Use whenever writing or reviewing code, especially when tempted to add abstraction, config, or generality "for the future". Favors boring, direct, minimal solutions.
vectojs/vectojs-skills/skills/vectojs-paradigm Skill
0★ repoAgent skills for building, optimizing, embedding, and exporting VectoJS projects with Codex, Claude Code, Cursor, and GitHub Copilot.
Paldom/landing-page-builder-skills/skills/landing-page-copywriting Skill
0★ repoWrites and edits conversion copy for marketing landing pages - voice-of-customer mining, outcome-first headlines, value props, CTA labels, specific social proof. Use when the user asks to write, draft, rewrite, or fix landing-page copy, a hero headline, CTA text, or messaging. Not for section layout, visual design, or A/B testing.
SamyakJhaveri/loam/cultivation/marketplace/business-process/skills/sop-writer Skill
0★ repoTakes a process description and generates a complete Standard Operating Procedure document with numbered steps, decision points, checklists, and troubleshooting guidance. Use when user says "write an SOP", "create SOP", "standard operating procedure", "document this process", "write a procedure for", or asks to formalize any business process.
SamyakJhaveri/loam/cultivation/marketplace/pocock-engineering/skills/grill-with-docs Skill
0★ repoGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (DOMAIN.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
SamyakJhaveri/loam/seed/.claude/skills/grill-with-docs Skill
0★ repoGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (DOMAIN.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions. NOT for implementation review (use /multi-review) or architecture analysis (use /improve-codebase-architecture).
SamyakJhaveri/loam/seed/.claude/skills/handoff Skill
0★ repoUse when ending a session with unfinished work, switching context, or preparing for another agent to continue. Write or update a handoff document so the next agent with fresh context can continue this work. NOT for: session notes, commit messages, or PR descriptions — only structured handoffs for agent continuity.
SamyakJhaveri/loam/seed/_research/skills/paper-write Skill
0★ repoDraft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.
ats4321/claude-engineering-skills/skills/documentation-practices Skill
0★ repoWrite and maintain documentation that stays true. Auto-load when writing or updating a README, contributor guide, docstring, ADR, .env.example, or any docs; when documentation contradicts code; when deciding what (and what NOT) to document; or when setting up docs for a new project. Covers README-as-executable-contract, the four documentation types (tutorial/how-to/reference/explanation), docs-near-code placement, drift management (date-stamps, re-verification, delete-wrong-docs), and writing docs AI agents can execute. NOT for ADR content design (system-design) and NOT for code comments' engineering rationale (change-control governs the diff they ride in).
ats4321/claude-engineering-skills/skills/validation-and-testing Skill
0★ repoRisk-first test strategy for ANY codebase. Auto-load when writing tests, adding a runnable check to a change, deciding what to test first, bootstrapping tests into an untested project, or choosing between mocks/fakes/monkeypatch. Covers testing the highest-risk surface first (security boundaries, parsers, money paths), preferring monkeypatch and hand-rolled fakes over mocking libraries, leaving at least one runnable check per non-trivial change, adding a first test to an untested codebase, and knowing when NOT to write a test (trivial one-liners). Trigger keywords: test, testing, pytest, unit test, coverage, mock, monkeypatch, fake, fixture, "add a test", "how do I test", "is this tested".
yousefkadah/laravel-ai-kit/skills/write-test Skill
0★ repoUse when adding or fixing a test in a Laravel project that uses Pest. Covers feature vs unit tests, factories, fixtures, failure-path coverage, and tenant-isolation assertions.
dungsil/skills/skills/writing-java-tests Skill
0★ repoWrite, improve, or review Java tests with JUnit, Mockito, Spring Boot, Spring Data JPA, and JSpecify across unit, integration, and E2E levels. Use only for Java test work, including domain, use-case, entity, validation, repository, adapter, HTTP API, nullability, or Java test-level selection decisions.
dungsil/skills/skills/writing-javadoc Skill
0★ repoWrite or review concise Korean Javadoc comments for Java code. Use when adding, revising, or checking Javadocs for Java types, constructors, fields, methods, private helpers, parameters, return values, null behavior, exceptions, deprecations, references, generic type parameters, test-aligned contracts, or project style consistency.
dungsil/skills/skills/writing-kdoc Skill
0★ repoWrite or review concise Korean KDoc comments for Kotlin code. Use when adding, revising, or checking KDoc for Kotlin classes, objects, functions, properties, constructors, extension receivers, type parameters, return values, exceptions, deprecations, symbol links, or Dokka output.
dungsil/skills/skills/writing-kotlin-tests Skill
0★ repoWrite, improve, or review Kotlin tests with kotlin-test, MockK, Spring Boot, and Spring Data JPA across unit, integration, and E2E levels. Use only for Kotlin test work, including domain, use-case, entity, validation, repository, adapter, coroutine, HTTP API, nullability, or Kotlin test-level selection decisions.
kulapoo/opencode-agent-harness/.opencode/skills/documentation-and-adrs Skill
0★ repoRecords decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
ceilidhboy/skills/skills/boost-documentation-search Skill
0★ repoSearch Laravel Boost documentation effectively when Boost-specific information is needed.
ceilidhboy/skills/skills/monthly-report-generator Skill
0★ repoGenerate monthly development reports for clients using git history, PRs, and ADRs. Research commits/PRs/ADRs for a given repo and date range, then produce a plain-English HTML report for non-technical clients plus a Markdown version for email. Optionally update the project wiki. Use when user says "monthly report", "client report", "development report", "report for [client]", "summarise work", or asks you to document work done over a period.
ceilidhboy/skills/skills/write-a-skill Skill
0★ repoCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
ceilidhboy/skills/skills/writing-skills-readme-first Skill
0★ repoBefore creating any new skill, check the user's personal skills repo if they have one. Use the write-a-skill skill for the template. This is the mandatory starting point for all skill creation work.
Syo-M/codex-frontend-skills/.agents/skills/i18n Skill
0★ repoInternationalization for catalogs, ICU messages, Intl formatting, locale routing, language switching, localized validation, and RTL. 日本語の依頼例:「多言語対応」「翻訳」「ロケール切替」「日付や通貨表示」「RTL対応」。
Syo-M/codex-frontend-skills/plugins/codex-frontend-skills/skills/i18n Skill
0★ repoInternationalization for catalogs, ICU messages, Intl formatting, locale routing, language switching, localized validation, and RTL. 日本語の依頼例:「多言語対応」「翻訳」「ロケール切替」「日付や通貨表示」「RTL対応」。
DejusDevspace/my-skills/document-api-for-agents Skill
no license0★ repoUse when a user wants to inspect a repository's live API surface and produce agent-facing documentation such as OpenAPI and a concise Markdown guide from routes, handlers/controllers, request schemas, response serializers, middleware, and configuration. Use this when documenting APIs for frontend or agent integration, and keep legacy collections like Bruno untouched unless explicitly requested.
msageha/skills/stirling-pdf Skill
0★ repoStirling PDF document processing. Use when: user asks to convert, merge, split, compress, OCR, or manipulate PDF files. Also for converting between PDF and Markdown/images/Word/HTML. Useful alongside Obsidian for PDF-to-Markdown conversion.
huguryildiz/ALETHEIA/plugins/aletheia/skills/statistical-reporting Skill
0★ repoOperating discipline for rigorous, reproducible computational-science research — a portable, markdown-only Claude skill pack: 18 disciplines, a generator, and read-only auditor agents.
huguryildiz/ALETHEIA/skills/core/build-log Skill
0★ repoUse when a phase completes or a sanity-gate result is being fixed as permanent evidence — writing a new numbered entry under the build-log directory. The bar is high; single-module additions and small changes do not get entries. Trigger phrases: "phase N is done, log it", "the gate passed, record it", "write a build log entry", "completion note", "fix this result as evidence".
huguryildiz/ALETHEIA/skills/core/evidence-convention Skill
0★ repoUse when launching any computational campaign whose results will be kept, cited, or decided upon — sweeps, batch runs, Monte Carlo draws, precomputes — and when auditing for "dark runs" (results that exist only in caches, scratch dirs, or chat logs). Defines where evidence lands and what a run must record. Trigger phrases: "where do the results go", "record this run", "write the meta file", "dark run", "promote these results", "run report".
huguryildiz/ALETHEIA/skills/extended/statistical-reporting Skill
0★ repoUse when a numeric result is about to be reported, compared, or put in a paper — enforcing replication counts, uncertainty intervals, paired comparisons on matched instances, and visible denominators. Also use when designing how many runs a claim needs. Trigger phrases: "is this difference real", "how many replications", "report with confidence intervals", "single run result", "compare method A vs B", "is N=3 enough".
IcodeNet/agent-skills/skills/documentation Skill
0★ repoWrites and updates docs, READMEs, runbooks, specs, and ADRs. Use when documenting a feature, writing a runbook, updating README/setup docs, or recording decisions. Do not use for competitive research briefs or for code comments that only restate the next line.
IcodeNet/agent-skills/skills/grill-with-docs Skill
0★ repoGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
The same file is in 11 other repositories
IcodeNet/agent-skills/skills/release Skill
0★ repoPrepare a release: decide the semantic version bump, write the changelog / release notes from actual changes, and tag. Use when releasing or publishing a package or service version, cutting a release branch, or when asked "what version should this be" or to write release notes. Do not use for the deploy execution itself (use deploy-checklist).