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
kakarot-oncloud/claude-dev-skills/skills/readme-generator Skill
0★ repoGenerates project README.md files with the right sections (badges, install, usage, configuration, contributing, license) based on the project type and audience. Use this skill when the user asks to "write a README", "generate documentation", "make my repo presentable", or has a project that lacks a proper README.
eroveda/blueprint-skills/skills/generate-blueprint-summary Skill
0★ repoUse this skill AFTER all other Blueprint skills have generated their outputs. Produces BLUEPRINT.md — a master index document that ties together all the project blueprint files (analysis, decomposition, specs, architecture, flows, user guide, API catalog). This is the "table of contents" or "dashboard" of the project blueprint. It's the first file someone should open when arriving at the project. ## When to invoke this skill - After running the Stage 1 skills (universal-framework, swebok-decompose, swebok-generate-spec) - After running the Stage 2 documentation skills (architecture-doc, functional-flows, user-guide, api-catalog) - When the user asks for a "project summary", "blueprint dashboard", "table of contents", or "BLUEPRINT.md" ## When NOT to invoke - Before other skills have generated their outputs - For projects without complete blueprint generation
eroveda/blueprint-skills/skills/generate-functional-flows Skill
0★ repoCreates FUNCTIONAL_FLOWS.md describing user-facing flows in plain language. Use when documenting for non-technical stakeholders (managers, PMs, clients). Do NOT use for technical architecture (use generate-architecture-doc) or API docs (use generate-api-catalog). Trigger with "generate functional flows", "document user flows", or "create FUNCTIONAL_FLOWS.md".
eroveda/blueprint-skills/skills/generate-user-guide Skill
0★ repoCreates USER_GUIDE.md for end-users (not developers). Use when preparing onboarding material or end-user documentation. Do NOT use for API docs (use generate-api-catalog) or technical architecture (use generate-architecture-doc). Trigger with "generate user guide", "document for end users", or "create USER_GUIDE.md".
SeidSmatti/misc-CC-Plugins/plugins/academic-latex/skills/compile Skill
0★ repoCompiles a LaTeX document end-to-end across pdflatex / xelatex / lualatex. Auto-detects the right compiler from preamble features, runs latexmk for multi-pass + bib backend orchestration (biber or bibtex), and surfaces a clean error summary on failure. Use when the user asks to compile, build, render, "make the PDF", "run latex", or hands a .tex file expecting a PDF. Delegates to /academic-latex:debug on failure and /academic-latex:docs-lookup when uncertain about a package or option.
SeidSmatti/misc-CC-Plugins/plugins/academic-latex/skills/docs-lookup Skill
0★ repoFetches authoritative LaTeX package documentation (CTAN, TUG, package author repos) when a sibling skill is uncertain about a package, option, command, or compiler behavior. Use when the answer to a LaTeX question is not 100% certain, when picking a non-trivial package option, or when the user asks "is this still the right way?". The no-guessing gate for the academic-latex suite.
SeidSmatti/misc-CC-Plugins/plugins/academic-latex/skills/multilingual Skill
0★ repoConfigures multilingual LaTeX documents — Latin scripts (English, French, German, Spanish, etc.), RTL (Arabic, Hebrew, Persian), CJK (Chinese, Japanese, Korean), and Indic (Devanagari, Tamil, Thai, Bengali). Picks babel vs polyglossia based on engine and script; sets fonts via fontspec; handles bidi (XeLaTeX) and luabidi (LuaLaTeX). Use when the document has more than one language or any non-Latin script, or when /academic-latex:author needs the right setup. Delegates to /academic-latex:docs-lookup for non-trivial language-specific options.
SeidSmatti/misc-CC-Plugins/plugins/academic-latex/skills/template Skill
0★ repoGenerates ready-to-compile LaTeX scaffolds — journal article, thesis, beamer presentation, lab report, CV, letter, multilingual document. Each template ships a minimal-but-correct preamble with the suite's typography defaults (microtype, booktabs, amsmath, hyperref+cleveref). Picks engine (pdflatex / xelatex / lualatex) per the document's needs. Use when the user asks to start a new paper, thesis, talk, report; "give me a LaTeX template"; "scaffold a new article"; "set up a beamer deck".
koloskus/jotbook/skills/jotbook-stage Skill
0★ repoStage a recently-discussed concept as a lightweight jot. **CRITICAL — auto-invoke this skill at the end of any turn where you delivered a substantive multi-paragraph explanation of a domain concept (a system, mechanism, piece of code, design rationale, or pattern the user might want to revisit). Don't ask permission, don't hedge, don't skip because the topic feels minor — staging is cheap and reversible; failing to capture is permanent. Stage and report in one line.** Writes a small pointer file under the configured jots directory; does not write the full entry.
reasonless-throne486/sast-skills/sast-files/.agents/skills/sast-report Skill
0★ repoConsolidate all SAST vulnerability results from the sast/ folder into a single final report ranked by severity and confidentiality impact. Reads all *-results.md files and produces sast/final-report.md. Run after all vulnerability detection skills complete. Use when asked to generate a final report, consolidate findings, or summarize security results.
reasonless-throne486/sast-skills/sast-files/.claude/skills/sast-report Skill
0★ repoConsolidate all SAST vulnerability results from the sast/ folder into a single final report ranked by severity and confidentiality impact. Reads all *-results.md files and produces sast/final-report.md. Run after all vulnerability detection skills complete. Use when asked to generate a final report, consolidate findings, or summarize security results.
puukis/lstack/skills/changelog Skill
0★ repoGenerate a CHANGELOG.md entry from git log since last tag — invoked via /changelog
puukis/lstack/skills/docs Skill
0★ repoWrites accurate documentation by reading source first — never invents API signatures
Endika/eskills/skills/postmortem Skill
0★ repoUse when capturing an important bug or production failure — record the incident, root cause, fix, and lesson as an archivable markdown document.
dills122/ai-central/templates/skills/imported/agent-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.
The same file is in 11 other repositories
Backend to frontend handoff docs
dills122/ai-central/templates/skills/imported/agent-toolkit/backend-to-frontend-handoff-docs Skill
0★ repoCreate API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.
The same file is in 3 other repositories
dills122/ai-central/templates/skills/imported/agent-toolkit/c4-architecture Skill
0★ repoGenerate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document system architecture, visualize software structure, create C4 diagrams, or generate context/container/component/deployment diagrams. Triggers include "architecture diagram", "C4 diagram", "system context", "container diagram", "component diagram", "deployment diagram", "document architecture", "visualize architecture".
The same file is in 7 other repositories
dills122/ai-central/templates/skills/imported/agent-toolkit/openapi-to-typescript Skill
0★ repoConverts OpenAPI 3.0 JSON/YAML to TypeScript interfaces and type guards. This skill should be used when the user asks to generate types from OpenAPI, convert schema to TS, create API interfaces, or generate TypeScript types from an API specification.
The same file is in 5 other repositories
dills122/ai-central/templates/skills/imported/agent-toolkit/react-useeffect Skill
0★ repoReact useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.
The same file is in 5 other repositories
dills122/ai-central/templates/skills/imported/antfu-skills/vitepress Skill
0★ repoVitePress static site generator powered by Vite and Vue. Use when building documentation sites, configuring themes, or writing Markdown with Vue components.
The same file is in 5 other repositories
dills122/ai-central/templates/skills/imported/claude-skills/engineering/skills/runbook-generator Skill
0★ repoGenerate operational runbooks from a service name — deployment, incident response, maintenance, and rollback workflows. Templated structure customizable per environment. Use when documenting on-call procedures for a new service, standardizing incident response across teams, or producing runbooks before launching to production.
The same file is in 4 other repositories
dills122/ai-central/templates/skills/imported/claude-skills/product-team/code-to-prd/skills/code-to-prd Skill
0★ repoReverse-engineer any codebase into a complete Product Requirements Document (PRD). Analyzes routes, components, state management, API integrations, and user interactions to produce business-readable documentation detailed enough for engineers or AI agents to fully reconstruct every page and endpoint. Works with frontend frameworks (React, Vue, Angular, Svelte, Next.js, Nuxt), backend frameworks (NestJS, Django, Express, FastAPI), and fullstack applications. Trigger when users mention: generate PRD, reverse-engineer requirements, code to documentation, extract product specs from code, document page logic, analyze page fields and interactions, create a functional inventory, write requirements from an existing codebase, document API endpoints, or analyze backend routes.
The same file is in 2 other repositories
ardellashuddery616/modularity/skills/document Skill
no license0★ repoProduces modularity review documents in both Markdown and HTML formats. Use when writing the final review output from a modularity analysis.
The same file is in 1 other repository
riteshkew/yc-skills/skills/cardinal-outbound-writer Skill
0★ repoGiven a prospect brief and a seller's offer, generate a personalized 3-touch outbound sequence grounded only in specific facts from the brief — no fabrication, no spam.
riteshkew/yc-skills/skills/menza-data-analyst Skill
0★ repoPoint this skill at a CSV and ask natural-language questions — total, average, min, max, top-N, filtered count, and group-by — and get a Markdown answer with supporting tables. Trigger when a user wants to explore or summarise tabular data without writing code.
ak-ship/fullstack-agent-skills/skills/doc-craft Skill
0★ repoWrite documentation that engineers actually read — READMEs that get you running in under 5 minutes, API docs with executable examples, inline JSDoc/TSDoc/docstrings that explain the why. No corporate filler, no "this function does what its name says", no AI-generated cadence. Use when the user says "write a README", "document this", "add docstrings", "write the API docs", "write a CHANGELOG", or hands over a module and asks for docs.
ak-ship/fullstack-agent-skills/skills/mcp-forge Skill
0★ repoScaffold a production-ready Model Context Protocol (MCP) server from an OpenAPI spec, API reference URL, or pasted endpoint list. Use when the user says "build an MCP server", "wrap this API as MCP", "expose this service to Claude", "create MCP for <service>", or pastes a swagger/OpenAPI JSON and asks Claude to make it callable as tools. Produces a typed TypeScript server, auth handling, retry/backoff, and a one-command install path.
specscore/specstudio-skills/skills/recap Skill
0★ repoConsumes an approved SpecScore Feature plus the latest `specstudio:verify` report at HEAD and produces a per-AC drift report at spec/features/<feature-slug>/_recap/<sha>.md. For each AC, dispatches one built-in AI subagent (serial, not parallel) that classifies divergence between spec and code into the 4-bucket verdict set {no-drift, spec-tighter-than-code, code-tighter-than-spec, contradiction}. Aggregates verdicts into a Markdown report opened by a grep-friendly YAML summary block, emits `recap.completed`, and transitions only to `specstudio:review`. Applies publication policy to the report checkpoint. Trigger: "recap", "/recap", "specstudio:recap", or the explicit downstream transition from `specstudio:verify`.
specscore/specstudio-skills/skills/verify Skill
0★ repoConsumes an approved SpecScore Feature and produces a machine-checkable per-AC verdict report at spec/features/<feature-slug>/_verify/<sha>.md. Walks `git log` for the `Verifies:` commit-message trailer per AC, dispatches one built-in AI subagent per mapped AC (serial, not parallel), aggregates verdicts into a Markdown report opened by a grep-friendly YAML summary block, emits `verify.completed`, and transitions only to `specstudio:recap`. Applies publication policy to the report checkpoint. Trigger: "verify", "/verify", "verify this feature", "specstudio:verify", or the explicit downstream transition from `specstudio:implement`.
NOGIT007/holding-accounting/skills/yearly-bookkeeping Skill
0★ repoEnd-of-year bookkeeping pipeline for a small holding company. Trigger when the user asks to "start regnskab YYYY", "lav årsregnskab", "bogfør året", "close the books YYYY", or creates a new regnskab{YYYY}/ folder. Drives the full input → markdown → xlsx → reports → approval → annual report → ERP pipeline by orchestrating the four phase-specific skills.
alinafe82/cognitive-deadlift/skills/docs-claim-audit Skill
0★ repoAudit README, docs, comments, examples, and public copy against repository evidence. Use when merging documentation changes or public claims to ensure claims are backed by files, tests, scripts, examples, or explicit limitation language. NOT for typo-only edits or private notes that make no factual claims.
alinafe82/cognitive-deadlift/skills/read-the-docs-first Skill
0★ repoCheck local docs, ADRs, interfaces, schemas, and primary upstream sources before guessing. Use when work depends on APIs, frameworks, repo conventions, architecture decisions, or policy. NOT for purely local refactors or cases where code is the only source of truth.
alinafe82/cognitive-deadlift/skills/thinking-ledger-review Skill
0★ repoReview thinking ledgers for substantive reasoning evidence. Use when accepting a staged or submitted thinking ledger for non-trivial work to check problem, assumptions, alternatives, evidence, verification, tradeoffs, and risk. NOT for checking only whether a ledger file exists or for reviewing unrelated prose docs.
brandhaug/skills/write-like-a-human Skill
no license0★ repoStrip AI writing tropes from prose — negative parallelism ("It's not X, it's Y"), em-dash addiction, "delve"-family vocabulary, punchy fragments, false suspense, signposted conclusions, and ~30 other tells. Use when writing or editing prose meant for humans (blog posts, docs, READMEs, announcements, marketing copy, emails), when the user says text "sounds like AI" or asks to humanize it, or mentions "write like a human".
husnain067/codebase-knowledge-skills/codebase-glossary Skill
0★ repoExtract the domain vocabulary of a codebase — the terms, abbreviations, status values, and entity names that mean something specific in this project. Use this skill when the user asks "what does X mean here", "extract the domain terms", "build a glossary", "what are the project-specific words", "explain the terminology", or any variant focused on vocabulary rather than full architecture. The output is a single Markdown file with a glossary table (term, meaning, where used), an acronym list, and a status/enum value reference — focused on words that mean something specific in this codebase that an outsider wouldn't know. This skill captures domain language: project-specific nouns, business terms, status values like 'trialing' or 'completed', scope strings, and any term that shadows a common word but has a project-specific meaning. It is narrow by design and produces ONLY the glossary. It does not cover architecture, naming conventions, testing, or error handling — point the user to the relevant sister skill if they need those.
husnain067/codebase-knowledge-skills/codebase-overview Skill
0★ repoProduce a high-level overview of a codebase — architecture, tech stack, directory layout, key design decisions, current state of work, and deployment setup. Use this skill when the user asks to "analyze this codebase", "give me an overview", "scan the repo", "what is this project", "onboard me to this codebase", "map out this repo", or "summarize what's in here". The output is a Markdown file that helps a new developer (or Claude) understand the big picture in 5 minutes — what the project is, how it's organized, what tech it uses, what's actively being worked on, and how it deploys. This skill produces an OVERVIEW, not a deep reference. For naming conventions, error handling patterns, testing structure, or domain vocabulary, recommend the focused sister skills (codebase-conventions, codebase-error-handling, codebase-testing-guide, codebase-glossary) which each go deep on one area.
husnain067/codebase-knowledge-skills/codebase-testing-guide Skill
0★ repoDocument the testing setup of a codebase — what framework is used, where tests live, how to run them, what's mocked and how, what fixtures/factories exist, and what testing patterns repeat. Use this skill when the user asks "how do tests work here", "document the test setup", "what's the testing approach", "where are the tests", "how do I write a test in this project", "explain the mocking", or any variant focused on the test suite rather than full architecture. The output is a single Markdown file capturing test framework + config, test file location and naming, mocking and fixture patterns, test helpers, how to run the suite, coverage setup, and notable testing idioms — each documented with real examples copied from the actual codebase. This skill is narrow by design and produces ONLY the testing reference. It does not cover architecture, naming conventions, error handling, or domain vocabulary — point the user to the relevant sister skill if they need those.
Skillpack forge demo release notes
guorunjie/skillpack-forge-demo/.codex/skills/skillpack-forge-demo-release-notes Skill
0★ repoUse when updating the tiny release-note helper in this fixture.
markbaindesign/bain-studio/.claude/skills/changelog Skill
no license0★ repoUpdate the project CHANGELOG.md at release time. Reads git log since last tag and QA review-passed items, proposes a semver version bump, and writes a Keep a Changelog formatted entry. Invoke before /release-report and /review-checklist.
markbaindesign/bain-studio/.claude/skills/ga-report Skill
no license0★ repoPull Google Analytics 4 data for a client project and compile a branded benchmark report with action points. Authenticates via service account, fetches sessions/users/channels/pages/devices, writes a markdown report, and outputs a branded PDF via brand-doc.
markbaindesign/bain-studio/.claude/skills/nike Skill
no license0★ repoWrite or refine a proposal, scope document, or client-facing summary. Invoke with a brief slug or paste text inline. Enforces studio voice, proposal format, and ACCURACY.md guard rails.
markbaindesign/bain-studio/.claude/skills/perf-audit Skill
no license0★ repoPerformance audit against a live URL using Google PageSpeed Insights. Runs mobile + desktop, surfaces Core Web Vitals, and produces a prioritised fix list (P1-P4) ordered by impact. Saves a dated markdown report to context/perf/ in the project directory.
markbaindesign/bain-studio/.claude/skills/release-report Skill
no license0★ repoGenerate a client-facing release report from CHANGELOG.md. Plain English, no technical jargon. Outputs a dated markdown file and optionally creates a Gmail draft. Run after /changelog at release time.
markbaindesign/bain-studio/.claude/skills/seo-audit Skill
no license0★ repoTechnical SEO audit across key pages of a live site. Checks robots.txt, sitemap, per-page metadata (title, description, canonical, H1, JSON-LD, Open Graph), and Core Web Vitals via Google PageSpeed Insights API (free, no account needed). Saves a dated markdown report to context/seo/ in the project directory. Run at project start, after SEO work, or on demand.
1shooperman/shooperman-claude-plugins/plugins/slack-publish/skills/compose Skill
0★ repoDraft a new Markdown file for Slack publishing and save it to the XDG cache directory (~/.cache/slack-publish/). Use when the user wants to write or compose a message to send to Slack, e.g. "compose a Slack message", "draft a release announcement for Slack", "write a new post for #general", or runs /slack-publish:compose.
LkwdBrian/styleshift/modes/hemingway Skill
0★ repoActivates Hemingway writing mode. ALWAYS trigger when the user types `/hemingway`, `/mode hemingway`, or asks to "write like Hemingway", "respond in Hemingway style", or "use Hemingway mode". Applies iceberg theory, short declarative sentences, no adverbs, concrete imagery only, and dialogue-heavy structure.
cynthiaschomp/Claude-Project-Management-Skill-Ecosystem/scope-creep Skill
0★ repoUse this skill whenever a client requests work that may fall outside their contracted project scope. Triggers on: "scope creep", "out of scope", "client wants more", "they're asking for extra", "not in the contract", "new request on existing project", "change request", "additional work", "they added to the list", "this wasn't in the original scope", or any situation where a client email, message, or conversation includes a request that needs to be checked against project scope. ALWAYS use this skill before writing any scope analysis, PRD, change order, or ticket for scope-related work. This skill covers detection, documentation (PRD), ticketing, and the full approval workflow through to client quote.
csepulv/michi/toolkit/skills/michi-docs-site Skill
0★ repomy approach to building software, embodied in an agent-centric toolkit
talgacapri/pm-os/.claude/skills/design-backlog-writer Skill
no license0★ repoCreate Design Epics and Design Tasks from PRDs or plans, following a JTBD-driven design backlog structure. Optimised for designer flexibility — defines WHAT data/components are needed, never dictates HOW screens should be laid out. Use when asked to "create design tasks", "write design backlog", "design epic", "break down for design", "design deliverables from this PRD", or any request to create design-oriented backlog items separate from engineering stories.
talgacapri/pm-os/.claude/skills/feature-results Skill
no license0★ repoPost-launch analysis and results documentation. Document what shipped and what we learned.
talgacapri/pm-os/.claude/skills/storytelling Skill
no license0★ repoApply the right storytelling framework to any draft. Rewrites pitches, updates, memos, and narratives using Golden Circle, Minto's Pyramid, Pixar Pitch, StoryBrand, What-So What-Now What, or ABT.
talgacapri/pm-os/.claude/skills/sync-to-notion-doc Skill
no license0★ repoSync finalized Markdown documents from PM-OS to the Notion Documentation DB. Detects, classifies, converts, and pushes MD files as properly formatted Notion pages.
talgacapri/pm-os/.claude/skills/write-prod-strategy Skill
no license0★ repoProduct strategy docs using 7-component framework
jzills/claude-marketplace/plugins/dotnet-integration-tests/skills/write-integration-tests Skill
no license0★ repoUse this skill whenever the user asks to write, generate, or add integration tests for C# or .NET code. Trigger on: "write integration tests", "add integration tests", "test this endpoint", "test this API", "integration test for this controller", "test against the database", "write end-to-end tests", "test this repository with a real database", "add integration test coverage". Also trigger when the user shows a controller, repository, or service and asks for tests that require real infrastructure (database, message broker, HTTP, etc.) rather than mocks.
jzills/claude-marketplace/plugins/dotnet-xml-docs/skills/dotnet-xml-docs Skill
no license0★ repoUse when writing, reviewing, or generating XML documentation comments (///) for C# or .NET code. Trigger on: "add XML docs", "document this class", "write doc comments", "add IntelliSense comments", "document the API", "add triple-slash comments", "add summary comments", or any request involving /// documentation in C#/.NET. Also trigger proactively when the user asks to review or complete a public API surface that lacks documentation.
jzills/claude-marketplace/plugins/skill-changelog/skills/skill-changelog Skill
no license0★ repoUse this skill whenever a skill is being created, modified, or improved — including when writing or editing a SKILL.md, adding/removing references, updating scripts, or changing a skill description. Also trigger when a user says "add a changelog", "track skill changes", "initialize changelog", "update the changelog for this skill", "switch to auto", or "switch to opt-in". This skill must run as part of any skill editing workflow to ensure CHANGELOG.md stays current.
mickzijdel/dev-hooks/plugins/dev-hooks/skills/agent-brief Skill
0★ repoUse when writing a task brief for an agent — dispatching a subagent, handing off work, or turning a fuzzy request into instructions — and you want it aimed at an outcome, not a method. Triggers on "brief an agent", "write a task for a subagent", "spec this out for an agent", or a handoff that says what to do but not why or what's out of scope. Pairs with the intent-check hook.
mickzijdel/dev-hooks/plugins/dev-hooks/skills/github-actions Skill
0★ repoWrite, review, and harden GitHub Actions workflows against supply-chain attacks, and bump a whole fleet of repos' action pins to the latest versions. Use when writing or editing a workflow YAML (.github/workflows/*.yml, ci.yml), when asked to review a CI workflow or audit GitHub Actions security, when the ci-action-ref-reminder hook fires, or when the user wants to "bump my actions", "update the fleet", "pin actions to SHAs", run zizmor, or close supply-chain / pull_request_target / script-injection / GITHUB_TOKEN-permissions gaps. Pairs with references/security-checklist.md (the full checklist) and dev-env-setup's CI templates.
mickzijdel/dev-hooks/plugins/thinking-tools/skills/adr Skill
0★ repoUse when making a significant architectural or technical decision that shouldn't be re-litigated later — choosing a tool, pattern, or approach with real trade-offs. Write one ADR per decision, proactively the moment such a decision lands — don't wait to be asked. Triggers on "record this decision", "why did we choose X", "document our approach to Y", "write an ADR", or when completing a decision that cost real deliberation (library selection, database strategy, auth approach, deployment model).
mickzijdel/dev-hooks/plugins/writing/skills/github-readme Skill
0★ repoThis skill should be used when creating or revising a GitHub README for a software project, including section structure, onboarding flow, examples, and contribution guidance.