Docs & writing
16,632 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
Lucas-Fong/html-report-stable-base/skills/html-report Skill
3★ repoUse when supplied content or an existing HTML report needs a stable editable browser shell in either long-screen single-page mode or 16:9 PPT mode, including global and per-element styling, ECharts canvas support, standalone HTML delivery, or optional PPTX export in PPT mode.
Martin-Hausleitner/martins-awesome-skills/skills/software-development/plan Skill
3★ repoPlan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.
The same file is in 1 other repository
Martin-Hausleitner/martins-awesome-skills/skills/software-development/writing-plans Skill
3★ repoUse when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.
The same file is in 1 other repository
mrDesign-ww/vault-os/shell/claude/skills/jira-expert Skill
3★ repoAtlassian Jira expert for creating and managing projects, planning, product discovery, JQL queries, workflows, custom fields, automation, reporting, and all Jira features. Use when setting up or configuring Jira projects, writing JQL and advanced searches, creating dashboards, designing workflows, or performing technical Jira operations.
The same file is in 3 other repositories
mrDesign-ww/vault-os/shell/claude/skills/team-communications Skill
3★ repoWrite internal company communications — 3P updates (Progress/Plans/Problems), company-wide newsletters, FAQ roundups, incident reports, leadership updates, status reports, project updates, and general internal comms. Use this skill any time the user asks to draft, edit, or format something meant for internal audiences. Trigger on keywords like "3P", "weekly update", "newsletter", "FAQ", "internal comms", "status report", "company update", "team update", "incident report", or any request to summarize work for leadership, teammates, or the broader company. Even casual requests like "write my update" or "summarize what my team did this week" should trigger this skill.
The same file is in 5 other repositories
mrDesign-ww/vault-os/shell/claude/skills/write-a-skill Skill
3★ repoCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
The same file is in 20 other repositories
gy910210/hermes-research-skills/skills/report-maintainer-zh Skill
3★ repo研究文稿维护器:为版本化 Markdown 报告创建新文件、更新索引、给旧版加更新提示、合并专题稿进入成熟主稿,并检查跨文档链接、一致性和 benchmark 元数据缺口。需要把研究结果真正维护成项目文档时调用。
angad-kandhari/deliberate/skills/explore Skill
3★ repoCodebase-familiarity discipline. Load when working in a codebase you didn't write, before adding code to it. Covers reading before writing, searching for the existing solution before creating a new one, finding and matching the house style, copying the nearest neighbor, mapping the blast radius before changing shared code, and preferring codebase consistency over imported best practice.
angad-kandhari/deliberate/skills/memory Skill
3★ repoMemory discipline. Load when the agent keeps persistent memory across sessions - CLAUDE.md, AGENTS.md, auto-memory, memory banks, or any notes file the next session will read. Covers writing selectively, never recording what the repo already knows, structuring memory as index plus topics, stamping claims that can go stale, trusting the repo over the memory, pruning on write, and routing each fact to the right home.
angad-kandhari/deliberate/skills/pentest Skill
3★ repoPenetration-testing discipline for authorized security assessment. Load to audit a codebase or system you own (or are explicitly authorized to test) for vulnerabilities - then fix them with secure. Also covers scoped engagements: red-team exercises, CTFs, bug-bounty targets. Covers confirming authorization and scope first, mapping the attack surface, testing methodically against a threat model, proving findings with safe repro, controlling blast radius, reporting for the defender, and closing the find-fix-confirm loop with secure and verify. This is offensive testing to make systems safer; it is the counterpart to secure (writing safe code).
lawzava/megapowers/plugins/megapowers/skills/humanizing-prose Skill
3★ repoUse to draft or edit user-facing docs, release notes, PRs, announcements, or errors. Triggers on "humanize", "sounds like AI", "slop", or "read naturally".
lawzava/megapowers/plugins/megapowers/skills/writing-plans Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
lawzava/megapowers/plugins/megapowers/skills/writing-skills Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
barlevalon/skills/catalog/skills/grill-with-docs Skill
3★ repoA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
The same file is in 19 other repositories
barlevalon/skills/catalog/skills/ponytail Skill
3★ repoForces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
barlevalon/skills/catalog/skills/research Skill
3★ repoInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
The same file is in 11 other repositories
barlevalon/skills/catalog/skills/writing-great-skills Skill
3★ repoReference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
The same file is in 11 other repositories
barlevalon/skills/skills/documentation-system Skill
3★ repoPortable Agent Skills for AI-assisted engineering workflows
ezzatmakar/ai-code-skills/skills/laravel-pr-review Skill
3★ repoReviews pull requests, merge requests, branch changes, and code diffs for Laravel and PHP applications (Laravel 9–12, PHP 8.0–8.4). Use when asked to review a PR or changed code for security, performance, and clean-code quality, then create one detailed Markdown report containing evidence, impact, rationale, recommendations, validation results, references, and a merge verdict. Supports Quick, Standard, and Deep review modes and can optionally post findings as inline PR comments. Do not use for feature implementation unless the user separately asks for fixes.
ezzatmakar/ai-code-skills/skills/nextjs-pr-review Skill
3★ repoReviews pull requests, merge requests, branch changes, and code diffs for Next.js and React applications (App Router and Pages Router, Next.js 13–16). Use when asked to review a PR or changed code for security, performance, and clean-code quality, then create one detailed Markdown report containing evidence, impact, rationale, recommendations, validation results, references, and a merge verdict. Supports Quick, Standard, and Deep review modes and can optionally post findings as inline PR comments. Do not use for feature implementation unless the user separately asks for fixes.
ezzatmakar/ai-code-skills/skills/pre-push-review Skill
3★ repoReviews your local uncommitted changes before you push, in any language or framework (auto-detected), and scores Security, Performance, and Clean Code as Pass/Warn/Fail with an overall push-readiness recommendation. Use before pushing or committing — "check my changes before I push", "review my local diff", "is this safe to push?" — to get one Markdown report with evidence, impact, fixes, verification, references, and a per-measurement scorecard. Supports Quick, Standard, and Deep review modes. Do not use for feature implementation unless the user separately asks for fixes.
marco-souza/skills/.agents/skills/docs Skill
no license3★ repoWrite and maintain project documentation including READMEs, API docs, ADRs, CHANGELOGs, and inline code comments. Use when: the user asks to write documentation, update a README, create an API reference, draft an ADR, add a CHANGELOG entry, or improve inline comments. Do NOT use when: the user wants to format markdown (use markdown-format), review code (use pr-review), or create a PRD (use create-prd).
marco-souza/skills/.agents/skills/learning Skill
no license3★ repoCapture and organize learnings from coding experiences, debugging sessions, and problem-solving. Use when: the user wants to save a learning, document a discovery, record a pattern, or create a reference for future work. Do NOT use when: creating project documentation (use docs), writing PRDs (use create-prd), or when the user wants to read existing learnings without creating new ones.
marco-souza/skills/.agents/skills/markdown-format Skill
no license3★ repoFormat and lint Markdown files following standard conventions and best practices. Use when the user asks to format markdown, lint markdown files, fix markdown formatting, or ensure markdown follows style guidelines. Do NOT use when the user wants to convert between formats (Markdown to HTML, etc.) or when processing non-Markdown content.
marco-souza/skills/.agents/skills/test Skill
no license3★ repoGuide for writing effective tests using best practices: test pyramid, Arrange-Act-Assert pattern, mocking strategies, and coverage guidelines. Use when the user asks to write tests, improve test coverage, refactor tests, or understand testing best practices. Do NOT use when the user wants to run existing tests without modification, or when the focus is on test infrastructure setup (CI/CD, test frameworks installation).
Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-triage-report Skill
3★ repoBug triage validation system, Immunefi report format, and 20 real paid bounty examples dissected. Use this when validating a finding before submitting, writing an Immunefi report, checking if a bug is actually valid, or studying real examples of paid vulnerabilities.
jazz1x/galmuri/skills/doc Skill
3★ repoDocument adapter. Calls the distill engine, formats the result as markdown, and saves it to a file. Inherits the prior distill save flow. Triggers: "문서로", "정리해서 저장", "doc", "기록으로", "shrink", "줄여줘", "압축"
docmd-io/docmd-skills/skills/docmd-writer Skill
3★ repoUse this skill when writing or reviewing prose inside a docmd site. Owns Diátaxis doc types, voice, page structure, and code-block conventions; defers to docmd-skills for all docmd-specific syntax (containers, tabs, cards, grids, steps, collapsibles, buttons, tags, embeds, changelogs, Mermaid, frontmatter). Multi-lingual and SEO-aware.
agoradynamics/wick/.claude/skills/wick-changelog-summary Skill
no license3★ repoProduce a one-paragraph narrative summary of a CHANGELOG.md version entry — suitable for release announcements, blog posts, or social copy. Preserves technical specifics (file paths, command names, counts) rather than vaguifying them. Defaults to the latest version; optionally takes a version like "v1.0.0". Refuses to invent content if the version isn't in the file.
samhcus/skills/skills/confirm-gate Skill
no license3★ repoSurface your interpretation of the task before writing any code or making any changes. Use this at the START of any Build mode task - before opening a single file to edit. Critical when the request contained multiple ideas, was written in fragments, affects more than 2 files, or has any ambiguity about scope. Triggers on "build", "create", "add", "implement", "write", "make", "fix", "update" when the request is non-trivial. Do not skip this step to save time - a wrong interpretation wastes more time than a confirmation.
samhcus/skills/skills/repo-bootstrap Skill
no license3★ repoBootstrap a new GitHub repo with all standard Mad House files. Creates the repo, clones it locally under the correct org path, and writes README, .gitignore, .env.example, Dockerfile, CHANGELOG, and AGENTS.md template. Triggers on "new repo", "bootstrap a repo", "create a new project", "start a new repo", "scaffold repo".
lindoelio/my-agent-skills/postgres-database-designer Skill
no license3★ repoDesign and implement production-ready PostgreSQL databases from requirements through deployment. Use this skill whenever someone wants to create a database schema, design entity relationships, normalize data structures, create tables/indices, write SQL migrations, or implement PostgreSQL databases — whether for simple CRUD apps or complex enterprise systems. Triggers on phrases like "design a database", "create schema", "normalize tables", "PostgreSQL", "write migration", "ERD", "entity relationship", "database design", or when asked to organize data into tables with foreign keys. Respects implementation preferences (raw SQL, Prisma, Drizzle, etc.) and adapts documentation output accordingly.
ihatesea69/HieuNghi-AI-Skills/airesearch_skills/18-multimodal/whisper Skill
3★ repoOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
The same file is in 4 other repositories
ihatesea69/HieuNghi-AI-Skills/airesearch_skills/20-ml-paper-writing Skill
3★ repoWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
The same file is in 2 other repositories
ihatesea69/HieuNghi-AI-Skills/devto_skills/blog-writer Skill
3★ repoProfessional blog writing agent for dev.to with SEO-optimized Markdown format. Use when writing technical blogs, tutorials, or experience sharing. Output includes frontmatter with title, tags, series, canonical URL, cover image, and SEO-optimized content.
schalkneethling/claude-toolkit/skills/frontend-testing Skill
3★ repoWrite tests that start with acceptance criteria, then add implementation tests for robustness. Use when writing unit tests (Vitest), end-to-end tests (Playwright), visual regression tests, or accessibility tests. Emphasizes user-centric testing, semantic locators, accessibility validation, and the balance between acceptance and implementation testing.
schalkneethling/claude-toolkit/skills/project-goal Skill
3★ repoInspect a project, ask targeted user questions, and write a root GOAL.md that clearly defines the project's goals, intended audience, success criteria, constraints, and explicit non-goals. Use when asked to create, draft, update, clarify, document, or recover a project's goal, north star, mission, scope, or GOAL.md from an existing repository.
schalkneethling/claude-toolkit/skills/semantic-html Skill
3★ repoWrite well-considered semantic HTML that serves all users. Use when creating components, page structures, or reviewing markup. Emphasizes native HTML elements over ARIA. Treats proper document structure and accessibility as foundations rather than afterthoughts.
momentmaker/kaijutsu/skills/community/readme-update Skill
3★ repoDetect README staleness and propose a targeted update. Use when the user says "update readme", "is the readme out of date", "readme refresh", "/readme-update", or after merging a feature that likely changes installation, usage, or public API. Reads the README's last-touched commit, walks the commits since, and proposes a section-by-section diff.
momentmaker/kaijutsu/skills/core/spec-driven-development Skill
3★ repoAuthor a PRD-style spec before writing implementation. Use when the user says "write a spec", "PRD", "design doc", "spec out", "let's plan this", or invokes /spec. Produce a written, reviewable artifact (problem, scope, non-goals, acceptance criteria, open questions). End with `jutsu swarm doc-review <spec.md>` to surface gaps before declaring done.
yarlson/yarstack/plugins/yarstack/skills/changes-report Skill
3★ repoReport all repository changes that entered a target branch during one required date or period, grouped by product change and written as plain English for a broad audience. Use for daily, weekly, date-range, or relative-period change summaries rather than explaining one known diff.
yarlson/yarstack/plugins/yarstack/skills/critical-journey-document Skill
3★ repoCreate one concise evidence-linked product journey record for one actor pursuing one goal. Use when product behavior needs traceable ownership, acceptance, telemetry, or service-flow documentation for a current decision or delivery gate.
yarlson/yarstack/plugins/yarstack/skills/docs-drift-review Skill
3★ repoReview documentation for drift caused by the current code or configuration change. Use to identify concrete inaccuracies and, when authorized, repair only directly affected documentation.
yarlson/yarstack/plugins/yarstack/skills/docs-review Skill
3★ repoAudit or improve general repository documentation against implemented behavior. Use for deliberate README or documentation-quality work not owned by a more specific documentation skill.
yarlson/yarstack/plugins/yarstack/skills/english-text-review Skill
3★ repoReview English technical prose without modifying it. Use for plain-English feedback on comments, docstrings, documentation, commit or pull request text, issues, reports, runbooks, logs, errors, command help, and other human-readable technical writing rather than factual or marketing review.
yarlson/yarstack/plugins/yarstack/skills/repo-context-document Skill
3★ repoCreate, update, or consolidate adopted current-state documentation under docs/context/. Use for durable implemented architecture, ownership, runtime, domain, flow, terminology, or engineering-practice context.
arthjean/skills/skills/find-docs Skill
no license3★ repoRetrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service -- even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training data may not reflect recent API changes or version updates. Always use for: API syntax questions, configuration options, version migration issues, "how do I" questions mentioning a library name, debugging that involves library-specific behavior, setup instructions, and CLI tool usage. Use even when you think you know the answer -- do not rely on training data for API details, signatures, or configuration options as they are frequently outdated. Always verify against current docs. Prefer this over web search for library documentation and API details.
arthjean/skills/skills/grill-with-docs Skill
no license3★ repoA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
The same file is in 19 other repositories
arthjean/skills/skills/research Skill
no license3★ repoInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
The same file is in 11 other repositories
arthjean/skills/skills/skill-doctor Skill
no license3★ repoAudit a Claude Code skill or workflow for structural quality, idempotency, and best-practice compliance. Runs 30+ binary checks grounded in Anthropic's official skill authoring docs, Agent Patterns research, and production patterns. Produces a severity-weighted report (FAIL/WARN/NOTE). Use when the user says 'audit this skill', 'check my skill', 'skill-doctor', 'review my workflow', or provides a path to a skill directory. Do NOT use for codebase audits (use meta-audit) or PRD reviews (use meta-review-prd).
arthjean/skills/skills/write-prd Skill
no license3★ repoFully autonomous research-informed PRD generator. Researches the domain, makes all design decisions based on research + codebase context, then produces a complete PRD with epics, stories, acceptance criteria, quality gates, and a JSON status tracking file. Invoke with /write-prd [feature description].
arthjean/skills/skills/writing-great-skills Skill
no license3★ repoReference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
The same file is in 11 other repositories
roebi/agent-skills/skills/create-awesome-readme-en Skill
no license3★ repoGenerates a curated awesome-list README.md by discovering GitHub repositories under a given topic tag, analyzing each repository's content, and labeling them by category and quality signals. Use when a user wants to create or update an awesome list, curate a collection of GitHub repos by topic, generate a categorized README from a GitHub topic search, or automate awesome-list maintenance. Trigger phrases: "create awesome list", "update awesome readme", "curate repos by topic", "generate README from GitHub topic", "label repos from topic tag".
Create questions and answers en
roebi/agent-skills/skills/create-questions-and-answers-en Skill
no license3★ repoRuns a structured Q&A loop with a user: prompts them for questions one at a time, answers each question, then compiles all questions and answers into a downloadable Markdown file at the end. Use this skill whenever a user wants to test a configuration, probe knowledge, document a session, or explore a topic interactively. Activate for phrases like: "let us do a Q&A", "ask me questions", "I have questions for you to answer", "test my setup with questions", "compile a Q&A document", or "end of questions".
roebi/agent-skills/skills/quick-documentation-en Skill
no license3★ repoGenerates compact JSDoc comments or Python docstrings directly above function definitions. Activate for phrases like "doc-this", "document this", "add docs", "add a docstring", "add JSDoc", or whenever the user requests documentation for a code block. Supports JavaScript, TypeScript, and Python. Does not alter any code logic.
roebi/agent-skills/skills/translate-skill-de Skill
no license3★ repoÜbersetzt einen bestehenden Agent Skill (SKILL.md und alle gebündelten Dateien) von einer natürlichen Sprache in eine andere. Der übersetzte Skill wird auf Deutsch verfasst und als UTF-8 gespeichert. Diesen Skill verwenden, wenn ein Benutzer einen Skill übersetzen, in eine andere Sprache portieren oder für Sprecher einer anderen Sprache zugänglich machen möchte. Aktivieren bei Phrasen wie: "Skill übersetzen", "Skill von X nach Y übersetzen", "deutsche Version dieses Skills erstellen", "Skill ins Französische portieren", "Sprachvariante erstellen" oder "SKILL.md übersetzen".
roebi/agent-skills/skills/translate-skill-en Skill
no license3★ repoTranslates an existing Agent Skill (SKILL.md and all bundled files) from one natural language to another. The translated skill is written in English and saved as UTF-8. Use this skill whenever a user wants to translate a skill, port a skill to another language, make a skill accessible to speakers of a different language, or create a language variant of an existing skill. Activate for phrases like: "translate this skill", "translate skill from X to Y", "make a German version of this skill", "port skill to French", "create a language variant", or "translate SKILL.md".
leek/agent-skills/skills/nightly-docs-sweep Skill
3★ repoRun a documentation sweep so repo docs match the current implementation.
leek/agent-skills/skills/research-plus Skill
3★ repoInvestigate a question against high-trust primary sources and capture the findings as a cited Markdown file, run as a background subagent so the main session keeps working. Use when the user wants a topic researched, docs or package facts gathered, reading legwork delegated, or a wayfinder-plus research ticket resolved.
uzysjung/uzys-agent-harness/templates/skills/codex-consult Skill
3★ repoConsult OpenAI Codex (via the local `codex` CLI, non-interactive `codex exec`) for the two things it is comparatively strong at: (1) CONCISE, well-STRUCTURED writing — tightening verbose prose, restructuring a doc into a clean outline / tables / sections, executive summaries, README skeletons, changelog entries — and (2) IMAGE GENERATION — hero/placeholder art, logos, simple illustrative art, produced as real PNG files on disk (labeled flowcharts / architecture / sequence diagrams are NOT this — render those natively as Mermaid). Use whenever a document needs to get SHORTER and better ORGANIZED (not prettier-sounding), or whenever the user wants a generated image. Triggers: "codex한테 물어봐 / codex로 정리해 / 간결하게 정리해줘 / 구조화해줘 / 문서 구조 잡아줘 / 이미지 만들어줘 / 그림 생성해줘", or in English "ask codex", "tighten this up", "make this concise", "restructure this doc", "generate an image". Korean NUANCE/copy polish belongs to the sibling skill gemini-consult — this skill owns structure, concision, and images. Returns candidates/files for the user to choose from; never auto-applies.