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
batur/ts-baseline-docs/.agents/skills/openapi Skill
1★ repoCreate, update, and review OpenAPI documentation for REST APIs. Use when adding or changing API endpoints, request/response DTOs, route metadata, authentication schemes, error envelopes, pagination, filtering, sorting, examples, generated OpenAPI files, SDK contracts, or contract-test expectations.
Da-loong/agent-skill-os/skills/changelog-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete changelog writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/contributing-guide-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete contributing guide writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/launch-post-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete launch post writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/prd-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete prd writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/readme-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete readme writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/release-notes-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete release notes writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/short-video-script-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete short video script writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/test-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete test writer work with a reliable workflow.
yiyaw-lab/agent-armor/hone Skill
1★ repoClose the grade→improvement loop — read accumulated grade-session report cards, find failures that RECUR across sessions, and propose surgical edits to the skill bodies that caused them; write only on approval. The suite's self-improvement layer (grade-session diagnoses per session; hone sharpens across sessions). Modes: sweep | audit | <skill-name>.
index365usa/agent-skills/skills/index365-read-report Skill
1★ repoUse when the user wants to see the results of an index365 scan without changing code. Triggers: "show my score", "what's wrong with my site", "read the audit report", "list the findings", "what did the audit find", "show the marketing signal report". Read-only: it reads and explains, it does not fix. To fix, use index365-apply-fix or index365-audit-and-fix.
impactbrussels/AINativeOS/skills/write-the-claude-md Skill
1★ repoUse when an agent keeps relearning the codebase from a blank page every session and getting it confidently wrong. Reach for it when a founder says "write my CLAUDE.md", "the agent forgot how our system works again", "it reinvents the structure every time", "set up the master file", "do I need AGENTS.md and a Cursor rules file too", "keep memory across sessions", "it broke a rule nobody told it", or starts a repo and wants every session to begin where the last one stopped. Produces a populated master file (and its AGENTS.md / GEMINI.md / Cursor mirrors) holding the system inventory, principles, constraints, and decisions, plus a one-line session-end update ritual. Run during architect-before-code, before agentic-build-loop.
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/skill-builder Skill
1★ repoComplete guide for designing, writing, testing, iterating, and packaging Claude Skills (SKILL.md files). Use this skill whenever someone wants to: create a new skill from scratch, improve or update an existing skill, understand the skill format, write a SKILL.md, build a skill folder with scripts and references, evaluate whether a skill is well-written, package a skill for distribution, optimize a skill's trigger description, or understand best practices for Agent Skills. Triggers include phrases like "build a skill", "write a SKILL.md", "make a skill for", "improve this skill", "skill format", "create an agent skill", "how do I write a skill", or any request to teach Claude a domain-specific capability through the skills system.
Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/skill-builder Skill
1★ repoComplete guide for designing, writing, testing, iterating, and packaging Claude Skills (SKILL.md files). Use this skill whenever someone wants to: create a new skill from scratch, improve or update an existing skill, understand the skill format, write a SKILL.md, build a skill folder with scripts and references, evaluate whether a skill is well-written, package a skill for distribution, optimize a skill's trigger description, or understand best practices for Agent Skills. Triggers include phrases like "build a skill", "write a SKILL.md", "make a skill for", "improve this skill", "skill format", "create an agent skill", "how do I write a skill", or any request to teach Claude a domain-specific capability through the skills system.
Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/skill-builder Skill
1★ repoComplete guide for designing, writing, testing, iterating, and packaging Claude Skills (SKILL.md files). Use this skill whenever someone wants to: create a new skill from scratch, improve or update an existing skill, understand the skill format, write a SKILL.md, build a skill folder with scripts and references, evaluate whether a skill is well-written, package a skill for distribution, optimize a skill's trigger description, or understand best practices for Agent Skills. Triggers include phrases like "build a skill", "write a SKILL.md", "make a skill for", "improve this skill", "skill format", "create an agent skill", "how do I write a skill", or any request to teach Claude a domain-specific capability through the skills system.
jpoindexter/verified-done/skills/vd-report-the-gap Skill
1★ repoWhen work is partial or unverified, say so plainly and specifically — before the user has to push. Name which Done criteria are executed, which are only code-path, and which are unrun; never let "done", "complete", or "passing" paper over a gap. Scrutinize good news (a green test, "looks good") as hard as bad news. Use whenever reporting status, finishing a task, or about to use a completion word over work that isn't fully verified.
gjbex/scientific-computing-skills/skills/scientific-documentation Skill
1★ repoWrite and improve documentation for scientific-computing and HPC software, especially when algorithms, assumptions, parameters, workflows, reproducibility expectations, and performance context must be explained clearly to technical users.
srahnama/Sina/skills/sina Skill
1★ repoApply rigorous scientific method as Dr. Atlas: frame precise questions, rank falsifiable hypotheses, classify evidence strength, retrieve and verify claims, design controlled experiments, analyze data, critique methods, improve academic writing, and report uncertainty. Use when the user says "sina", "Dr. Atlas", "scientific method", "evidence-based", "hypothesis", "verify", "reproduce", "root cause", "systematic analysis", asks for proof, validation, literature reasoning, experimental design, SOTA scientific AI workflows, statistical interpretation, or reproducible research.
HorizonBrute/Standardized_AI_Looping_Language-SAILL/skills/dirtree-check Skill
1★ repoWalk every tested_implementation directory that has a testing_nonce.md, collect each directory's agents.md inheritance chain and nonce via parallel haiku agents, render a directory tree showing context depth at every node, write it to documentation/lastrun_dirtree_check.md, and append the file's SHA256 hash. Use when asked to run the directory tree check, verify context inheritance, or audit nonce coverage.
jnMetaCode/skillet/skills/test-writing Skill
1★ repoWrite tests that catch real regressions — behavior-focused, minimal mocking, edge cases chosen from the code's actual branches. Use when adding tests for new code or backfilling tests for a fix.
celestialdust/achilles-skills/skills/comprehension-quiz Skill
1★ repoAgent-administered retrieval practice that makes understanding of code you did not write honest — about five medium-difficulty questions asked ONE at a time, the learner's answer graded BEFORE the correct answer is revealed, the session recorded as one line in the learning ledger. Reach for this right after a literate-explainer artifact (quiz that explainer) or standalone with no fresh explainer in view (the requiz over weak or stale durable concepts drawn from the ledger). It is the SOLE writer of the learning ledger; it is an honest self-check, never a gate — it blocks nothing. If you are about to dump every question at once, reveal an answer before grading it, or write a quiz's questions or answers into any file the learner can open, stop and load this.
celestialdust/achilles-skills/skills/documentation-and-adrs Skill
1★ repoThe repo's ADR and documentation STANDARD — capture the WHY (context, constraints, rejected alternatives), not just the what. Reach for this whenever you make a hard-to-reverse architectural decision, supersede an old one, change a public API, ship a user-facing feature, or record context a future engineer or agent will need. spec-grilling, codebase-design, api-design, and the Ship skills all defer to this format — do NOT hand-roll an ADR or invent your own doc layout.
celestialdust/achilles-skills/skills/incremental-implementation Skill
1★ repoBuilds one assigned slice as thin, individually-tested vertical increments — skeleton-first (stub→mock→wire→fill), simplicity-first, test-first. Use the moment you start writing code for a planned slice, and ESPECIALLY when you're tempted to write more than ~100 lines before running a test, land a whole feature in one pass, "clean up" code outside the slice, or weaken a test to get green. Runs inside the worktree the orchestrator hands you; it is not the place to plan or re-slice.
celestialdust/achilles-skills/skills/plan-breakdown Skill
1★ repoTHE planner — turns a signed prd.md + research.md into a concrete, agent-executable plan.md. Reach for it the moment Plan starts and someone says "plan this", "break it into tasks", "write the implementation plan", or is tempted to hand the build agent a prose sketch. Produces vertical tracer-bullet slices (each demoable, cross-layer, with an observable checkpoint) where every non-trivial step names its file, line range, code snippet, and test, plus a Blocked-by dependency DAG written into STATE.md. Refuses horizontal layer-by-layer plans and placeholder steps; references codebase-design + api-design, and escalates hard-to-reverse decisions to an ADR.
celestialdust/achilles-skills/skills/project-setup Skill
1★ repoScaffolds the repo ecosystem every achilles skill assumes — a one-time bootstrap that creates the STATE.md board, the CONTEXT.md glossary, docs/adr/, and docs/features/, and — when the repo has neither a CLAUDE.md nor an AGENTS.md and you opt to create CLAUDE.md — seeds it from a bundled behavioral template. Run this ONCE before the first feature, before interview-me or spec-grilling. The pipeline skills read these files cold and will have nowhere to write without it, so do this first.
celestialdust/achilles-skills/skills/source-driven-development Skill
1★ repoGround every framework- or library-specific decision in official docs you actually fetched — never in training-data memory. Use the moment you are about to write version-sensitive code (routing, forms, data fetching, auth, state, config, build setup): detect the installed version from the dependency file, deep-link the matching doc page, follow it exactly, and cite the full URL. Use whenever correctness depends on a version and "I think the API is…" is about to happen, or when reviewing framework-specific code for stale/deprecated patterns.
celestialdust/achilles-skills/skills/test-driven-development Skill
1★ repoRigid RED-GREEN-REFACTOR test-first loop. Use when implementing ANY feature or bugfix inside a slice, before writing one line of production code — turns each signed acceptance.md scenario into a test you watch fail first. If you're about to write impl, or about to "just relax a failing test so it passes," stop and load this.
motao123/dev-workflow-kit/docs-writer Skill
1★ repoUse when completed or in-progress work needs documentation such as README updates, migration notes, release notes, usage examples, or developer-facing operational guidance. This skill writes docs grounded in the current code and verified behavior.
codexskills/agent-forge/skills/documentation-and-adrs Skill
no license1★ repoProduction-grade AI agent skills — enhanced alternative to addyosmani/agent-skills. 23 lifecycle skills for Define, Plan, Build, Verify, Review, Ship. Works with OpenCode, Claude Code, Codex, Cursor, Gemini CLI.
shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/documentation-and-adrs Skill
1★ 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
zcccc-mxc/codex-skill-router/examples/skills/docs-authoring Skill
1★ repoUse when writing or editing README files, installation docs, documentation pages, changelogs for repository changes, notes, and usage guides. Do not use for database migration, browser rendering checks, or image generation.
spacemata/codex-plugins-for-claude-code/plugins/data-analytics/skills/build-report Skill
1★ repoBuild polished analytical reports for executive, product, business, and technical audiences, and act as the completion contract for Data Analytics report runs. Use when the final artifact needs an answer-first narrative, evidence-backed findings, charts/tables, caveats, source metadata, and either an MCP app report or an HTML report with Seaborn-generated charts.
spacemata/codex-plugins-for-claude-code/plugins/data-analytics/skills/build-report/report-to-google-doc Skill
1★ repoNarrow conversion skill. Invoke only when the user explicitly asks to convert an existing local or blob-hosted HTML analytics report into a Google Doc, DOCX, or shareable document.
spacemata/codex-plugins-for-claude-code/plugins/data-analytics/skills/build-report/report-to-google-slides Skill
1★ repoNarrow conversion skill. Invoke only when the user explicitly asks to convert an existing HTML analytics report into a native Google Slides deck.
spacemata/codex-plugins-for-claude-code/plugins/data-analytics/skills/build-report/report-to-pdf Skill
1★ repoNarrow conversion skill. Invoke only when the user explicitly asks to convert an existing Data Analytics report, dashboard, or inline chart export into a PDF artifact.
spacemata/codex-plugins-for-claude-code/plugins/data-analytics/skills/kpi-reporting Skill
1★ repoProduce leadership-ready KPI updates, scorecards, WBR/MBR/QBR summaries, target and pacing readouts, operating status narratives, and performance updates for known KPIs. Use when the work is to define KPI reporting context, validate metric definitions, present actuals versus comparison or plan, summarize validated drivers, and state implications or next actions.
spacemata/codex-plugins-for-claude-code/plugins/financial-markets/skills/deck-report-qc Skill
1★ repoUse when running first-pass QC on Public Equity Investing decks or reports. Do not use as external-circulation certification.
spacemata/codex-plugins-for-claude-code/plugins/financial-markets/skills/economic-impact-report Skill
1★ repoUse when translating a specific event, policy change, macro shock, or industry development into public-equity issuer, sector, earnings, valuation, positioning, and portfolio implications. Do not use for standalone macro strategy, rates, FX, credit, futures, or generic market commentary.
spacemata/codex-plugins-for-claude-code/plugins/financial-markets/skills/memo-builder Skill
1★ repoUse when drafting or reviewing formal public-equity investment memos. Do not use for live trade construction or credit-first memos; use long-short-pitch or Credit Markets as appropriate.
tuannv0069/claude-doc-genome/skills/init-project/portable/skills/skill-writer Skill
1★ repoUse when the user wants to write, create, or review a SKILL.md (slash-command skill definition) — simple skills, orchestration (Model B/C/D), dynamic workflow scripts, incl. per-subagent agent files. Trigger: "write/create a skill", "tạo skill", "review skill", "/skill-writer". Do NOT use for project rules (rule-writing-standards) or non-skill markdown.
LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/excel-xlsx Skill
1★ repoCreate Microsoft Excel .xlsx spreadsheets from tables, CSV/TSV, Markdown tables, or JSON data. Use when the user asks for Excel, spreadsheet, .xlsx, tabla editable, budget, inventory, report table, calculations, or data they need to open/edit in Microsoft Excel.
LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/human-writing-style Skill
1★ repoWrite in a direct, human, practical style with short sentences, active voice, and strict phrasing bans.
LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/word-docx Skill
1★ repoCreate Microsoft Word .docx documents from a title and body text. Use when the user asks for a Word file, .docx, formal letter, proposal, quote, report, or document to edit/share in Microsoft Word.
0xkangl/skills/skills/code-conventions Skill
no license1★ repoUse when writing or modifying code - designing HTTP APIs, adding structured logging/observability, writing tests, formatting commit messages, defining error codes, designing error-handling flow, naming config/env vars or handling secrets/keys, writing Dockerfiles/containerizing services, applying the security baseline, naming/code-style or design patterns, or building services in Go, Python, TypeScript/JavaScript, Rust, React, or Flutter/Dart. Routes to the matching convention document before implementing.
jimtin/production-ai/skills/repo-technical-documentation Skill
1★ repoExhaustively document an existing repository's technical architecture and implementation details. Use when asked to work through a whole repo and create, update, reconcile, or refresh technical docs covering API endpoints, UI routes and choices, frameworks, libraries and rationale, data models, integrations, jobs, testing, deployment, observability, operational scripts, or stale documentation.
sumitaich1998/slavex/.cursor/skills/sign-a-document Skill
1★ repoMimes signing a document, leaning over a desk and signing with a flourish, then setting the pen down. Use when the command mentions sign here, sign the document, sign your name, autograph, or sign the form.
sumitaich1998/slavex/.cursor/skills/swagger Skill
1★ repoSwaggers forward with a cocky shoulder-rolling side-to-side sway via a translating sequence. Use when a command mentions swagger, strut cockily, walk with attitude, shoulder roll walk, or a confident swaying walk.
sumitaich1998/slavex/.cursor/skills/write-on-whiteboard Skill
1★ repoMimes writing on a whiteboard, arm raised writing across a vertical board, on a loop. Use when the command mentions write on the board, whiteboard, write on the wall, or jot it on the board.
sumitaich1998/slavex/.cursor/skills/write Skill
1★ repoMimes writing at a desk, leaning over with the right hand moving across an imaginary page, on a loop. Use when the command mentions write, writing, take notes, sign something, or scribble.
josezuma/ai-visibility-geo-toolkit/.claude/skills/report Skill
no license1★ repoGEO reporting and analytics — weekly/delta reports.
SylphxAI/skills/skills/documentation-standard Skill
1★ repoDocumentation scope, minimal sufficient docs, generated references, and freshness without prose drift. Use when deciding what durable documentation to create, update, generate, or retire. Do not use for changing product behavior without documentation ownership questions.
SylphxAI/skills/skills/high-signal-communication Skill
1★ repoCompress or restructure an agent communication into a concise, decision-complete, high-signal artifact. Use when the user explicitly asks to shorten, de-duplicate, hand off, summarize progress, reduce context cost, or repair a verbose/slow-to-understand reply, report, commit, PR, ADR, spec, incident note, or agent record. Do not inject by default for every ordinary reply or document.
SylphxAI/skills/skills/source-to-skill-distiller Skill
1★ repoCreate or repair one installable Agent Skill package from supplied source material. Use only when the requested output is a SKILL.md or Skill package and the job needs mechanism extraction, evidence/publication boundaries, workflow, output contract, references, multilingual handling, evals, or validation. Do not use for ordinary summarization, translation, documentation, repository review, or code work.
SylphxAI/skills/skills/voice-preserving-editor Skill
1★ repoPreserve a requested natural human voice, locale, dialect, and non-AI style without changing facts. Use for explicit conversational, non-ChatGPT, less-templated, voice-preserving, locale-natural, dialect-aware, translationese-cleanup, or authorized sample-matching edits in Cantonese, Chinese, English, or multilingual text. Keep citations, technical terms, uncertainty, and judgment intact. A language name or ordinary translation request alone is not a trigger.
zhiming33416/top-cs-paper-skills/skills/top-cs-polishing Skill
1★ repoPolish, translate, tighten, structurally revise, or diagnose existing computer-science manuscript prose and LaTeX for WWW, ICLR, ICML, or a generic venue while preserving evidence. Use for Chinese-to-English academic rewriting, paragraph flow, section-level revision, claim calibration, concision, terminology consistency, reducing generic AI prose, revision ledgers, and LaTeX layout or float-placement problems. Do not use to invent a paper from sparse notes, simulate peer review, or write a reviewer response.
zhiming33416/top-cs-paper-skills/skills/top-cs-writing Skill
1★ repoDraft, restructure, or plan evidence-grounded computer-science conference papers for WWW, ICLR, ICML, or a generic venue. Use for paper outlines, titles, abstracts, introductions, related work, methods, experiments, discussions, limitations, conclusions, full manuscript arguments, Chinese research notes to English drafting, and LaTeX or Markdown section writing. Do not use for sentence-only polishing of a finished draft, reviewer-style auditing, or rebuttal writing.
14BryanEspinoza/agent-stack/skills/docs Skill
1★ repoReglas de documentación - Markdown, README, JSDoc, TypeDoc, changelogs, convenciones de escritura técnica
Paldom/github-skills/skills/docs-author Skill
1★ repoPlans, writes, or restructures project documentation - Diátaxis structure (tutorials, how-to guides, reference, explanation), minimal doc set, runnable examples, README-to-docs graduation, drift prevention. Use when the user asks to write, improve, or reorganize docs, guides, or tutorials. Not for the README itself, deploying a docs site, or community files.
Paldom/github-skills/skills/docs-site Skill
1★ repoStands up, deploys, or fixes a documentation site on GitHub Pages - generator choice (MkDocs, Sphinx, Docusaurus, Starlight), the official Actions workflow, base-path/.nojekyll/custom-domain pitfalls, docs CI, versioning. Use for publishing docs to github.io or debugging a broken/unstyled Pages deploy. Not for writing the docs content, the README, or branch protections.
Paldom/github-skills/skills/readme-author Skill
1★ repoWrites, restructures, or syncs a professional GitHub project README - front-loaded value prop, minimal badges, copy-pasteable quick start, scannable structure for a library, CLI, or web app. Use when the user asks to write, improve, restructure, or review a README, or calls it bloated, stale, or outdated. Not for repo topics/social-preview, community files, profile READMEs, or docs sites.