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
Paldom/github-skills/skills/repo-protections Skill
1★ repoConfigures GitHub repository protections - rulesets (require PR, required checks, no force pushes), secret scanning and push protection, Dependabot, private vulnerability reporting, and Actions hardening. Use when the user asks to protect a branch, set up branch protection or rulesets, enable security features, or harden a repo. Not for writing SECURITY.md or fixing code vulnerabilities.
IvanGomezMartinez/MatStudyLab/.agents/skills/grill-with-docs Skill
1★ 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
IvanGomezMartinez/MatStudyLab/.agents/skills/research Skill
1★ 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
IvanGomezMartinez/MatStudyLab/.agents/skills/writing-great-skills Skill
1★ repoReference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
The same file is in 11 other repositories
2702207741-dev/agent-skills-pipeline/examples/end-to-end-maintenance/repository-after/skills/release-notes-review Skill
1★ repoReview release-note behavior, regression evidence, and package readiness for this repository before a release.
2702207741-dev/agent-skills-pipeline/examples/external-repos/documentation-site/skills/documentation-release-review Skill
1★ repoReview documentation releases for navigation, command accuracy, evidence links, and compatibility notes.
iurysza/agent-skills/skills/strunk-writing-quality Skill
1★ repoApplies concrete checks for clarity, concision, structure, grammar, and plain English. Use when editing prose, reviewing drafts, writing longer pieces, or teaching clear writing.
Blackajiro/Purrfectionist/skills/purrfectionist Skill
1★ repoAudit, art-direct, and safely repair vibe-coded user interfaces. Use when creating, redesigning, styling, reviewing, or de-slopping web or app UI; changing layout, hierarchy, typography, color, components, imagery, responsive behavior, accessibility, or interaction motion; or fixing generic, inconsistent, broken, or unfinished frontend work. Inspect and implement on editable frontends unless the user asks for report-only analysis. Do not use for non-visual backend, infrastructure, documentation, or business-logic work.
ksed8/cc-loopkit/.claude/skills/docs Skill
1★ repoGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
munzzyy/skillxray/tests/corpus/malicious/prose-installer Skill
1★ repoGuides the agent through a quick one-line install.
lilabrooks/lila-agent-skills/skills/write-repository-readme Skill
1★ repoCreate, rewrite, audit, and polish repository README.md files for new or existing projects with Codex, Claude Code, or another Agent Skills-compatible host. Use when asked to draft a README, assess its structure or professional presentation, improve onboarding and scanning, add or repair a table of contents, verify Markdown links and documented commands, reduce README length by linking repository docs, or reconcile README claims with code, configuration, CI, licenses, and project status.
Deadlymind/nanolama/skills/ai-integration Skill
1★ repoWires Anthropic Claude into a Django/DRF backend — the agentic tool-use loop (model proposes tool_use, app runs it, returns tool_result, repeat), a write-tool safety contract for data-mutating tools, capability limits against prompt injection, an OCR/structured-extraction pipeline validated against a schema before persist, Tavily search, and per-tenant metering. Use when adding a Claude agent or tool loop, exposing a tool that mutates data, doing document OCR extraction, calling the anthropic SDK, choosing a model id, or capping AI spend per tenant. Not for regression-testing agent behaviour, golden sets or LLM-as-judge scoring (see ai-evals), the Celery worker that runs a long call (see celery-tasks), or auditing a tool's blast radius (see security-review).
Deadlymind/nanolama/skills/architecture-decisions Skill
1★ repoRecords an architecture decision as a numbered, immutable ADR under docs/adr — Status, Date, Context, Decision, Consequences, and the alternatives that lost — so the reasoning outlives the people who held it. Use when a choice is expensive to reverse or cross-cutting (Celery versus a cron, cookie JWT versus bearer tokens, one shared DB with a tenant FK versus schema-per-tenant), when a settled trade-off is being re-litigated in review, when superseding an earlier ADR, or when a PR needs a link to the reasoning behind it. Not for the commit message that carries the change (see commit-message) or the user-facing release notes (see changelog).
Deadlymind/nanolama/skills/changelog Skill
1★ repoMaintains a Keep a Changelog CHANGELOG.md with an Unreleased section, SemVer version headings, and grouped human-readable entries (Added, Changed, Fixed, Removed, Security, Deprecated) with compare-URL links. Use when adding a changelog entry, cutting a release, rolling Unreleased into a dated version, turning Conventional Commits into release notes, or asking "what changed in this version". Not for writing the git commit messages themselves (see commit-message) or the pipeline that publishes a release (see ci-cd).
Deadlymind/nanolama/skills/commit-message Skill
1★ repoWrites a Conventional Commits message from the staged git diff — type(scope) subject in the imperative under 72 chars, a body explaining WHY, and footers for BREAKING CHANGE and issue refs. Use when asked to write a commit message, "commit this", "conventionalize", or when deriving the type (feat, fix, chore, refactor, docs, test, perf, build, ci) and scope from what the diff actually changed. Not for the release-facing CHANGELOG rollup across many commits (see changelog) or judging whether the diff is correct (see code-review).
Deadlymind/nanolama/skills/db-concurrency Skill
1★ repoKeeps money and counter writes correct under concurrent access on Django 5.2 / PostgreSQL — transaction.atomic plus select_for_update to lock the row, F() expressions for read-modify-write counters, and Decimal with quantize for money. Use when writing a debit/credit or balance update, an inventory/stock decrement, a "spent count" or quota counter, a Celery task that mutates shared rows, or when fixing a lost-update, oversell, or race-condition bug. Not for schema changes and adding constraints (see migrations) or async task orchestration itself (see celery-tasks).
Deadlymind/nanolama/skills/design-system Skill
1★ repoDefines and governs the reusable design language of a Next.js B2B SaaS or ERP product — design principles, semantic token roles, typography and spacing scales, color semantics, component taxonomy, anatomy, variants and states, shared UX patterns, naming, documentation, contribution rules, deprecation and migration. Use when creating or evolving one design language across modules, standardizing modules that have drifted apart, stopping duplicate buttons/cards/tables, defining component variants and status semantics, or writing component usage contracts. Not for one workflow's UX (see product-ux-design), one screen's composition (see visual-ui-design), dashboard KPI and chart decisions (see dashboard-data-design), or the Tailwind v4 @theme variables and cva code that implement the system (see tailwind-shadcn).
Deadlymind/nanolama/skills/i18n-rtl Skill
1★ repoInternationalizes a Next.js 16 App Router app with next-intl for fr/en/ar — every user string via t() and present in all three message files, locale routing, and Arabic RTL that mirrors via dir="rtl" plus logical Tailwind classes (ms-/me-, ps-/pe-, text-start) instead of physical left/right. Use when adding a translated string, wiring next-intl routing/middleware, fixing hardcoded text, making a layout mirror for Arabic, or converting ml-/mr-/text-left to logical properties. Not for Zod form schemas and field messages (see zod-forms) or the Tailwind theme and shadcn setup itself (see tailwind-shadcn).
Deadlymind/nanolama/skills/verify Skill
1★ repoDrives a change end to end and observes real behavior — exercising the actual flow through the API, UI, or logs, not just tests or typecheck — before it is called done. Use when about to claim a task is finished, working, or fixed, when the user asks to verify or confirm a change, or before opening a PR. Enforces a gate — no completion claim without a fresh proving-command run and its pasted output. Not for writing the tests themselves (see write-tests) or root-causing a failure (see debug).
Deadlymind/nanolama/skills/write-tests Skill
1★ repoWrites tests for this Django/DRF plus Next.js stack — Django TestCase with a tenant fixture factory, APIClient carrying the cookie JWT, a mandatory tenant-isolation test (user B gets 404/empty for user A's row), RBAC denial tests, and vitest that mocks the shared fetch-client to test hooks and Zod parsing. Use when adding tests, writing a TestCase or vitest spec, testing a ViewSet or React Query hook, covering tenant isolation or a permission denial, or asking what to test here. Not for real-browser end-to-end specs — fixtures, storage-state auth, tenant seeding, flake control (see browser-e2e-testing) — driving a change end to end before calling it done (see verify), or wiring the CI that runs the suite (see ci-cd).
RudrenduPaul/skillguard/examples/skill-set-cross-privilege/report-uploader Skill
1★ repoA synthetic fixture skill bundled with SkillGuard's SG09 (cross-skill privilege chaining) tests. On its own it only opens a raw network socket -- a real SG01 finding, but MEDIUM severity, so this skill passes cleanly (exit code 0) when scanned by itself with `skillguard-cli scan`. It is inert: no real network connection is ever made. Do not install or run this in a real agent.
maojiebc/majia-siyu-team/plugins/siyu-core/skills/siyu-report Skill
1★ repo合并同一客户的多份本地存档,生成经过合规扫描的可交付 markdown 私域咨询报告。 触发方式:/siyu-report、/出报告、「打包」「整理一份」「给老板或客户看」;支持 --client 和 --since。
yigityildiz0/universal-ai-skill-library/skills/archive-variants/setup-writing-style Skill
no license1★ repoBuild a private, evidence-based writing-style profile from text the user explicitly provides, then test it on drafts without copying distinctive passages or.
yigityildiz0/universal-ai-skill-library/skills/common/api-documentation Skill
no license1★ repoCreate OpenAPI/Swagger specifications, API reference documentation, endpoint descriptions, and usage examples. Use when documenting REST APIs, GraphQL.
yigityildiz0/universal-ai-skill-library/skills/common/bug-localization Skill
no license1★ repoPinpoint bug locations using stack traces, error logs, code flow analysis, spectrum-based fault localization, and bisection techniques. Use when debugging.
yigityildiz0/universal-ai-skill-library/skills/common/caveman-compress Skill
no license1★ repoSafely compress prose in Markdown or plain-text memory and instruction files through a provider-neutral candidate, invariant validation, unified-diff preview, explicit user approval, atomic replacement, and timestamped backup. Use only when the user explicitly invokes $caveman-compress or asks for Caveman memory-file compression. Never overwrite during the default preview.
yigityildiz0/universal-ai-skill-library/skills/common/code-translation Skill
no license1★ repoTranslate code between programming languages while preserving logic, idiomatic style, and test coverage. Use when porting code between languages, migrating.
yigityildiz0/universal-ai-skill-library/skills/common/content-research-writer Skill
no license1★ repoAssists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
yigityildiz0/universal-ai-skill-library/skills/common/doc-coauthoring Skill
no license1★ repoGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision.
yigityildiz0/universal-ai-skill-library/skills/common/documentation-consistency Skill
no license1★ repoVerify documentation is up-to-date and consistent across all files. Check for broken links, outdated references, deprecated content, and mismatched.
yigityildiz0/universal-ai-skill-library/skills/common/documentation Skill
no license1★ repoWrite and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or.
yigityildiz0/universal-ai-skill-library/skills/common/final-report Skill
no license1★ repoConsolidate all review findings into a structured 4-section report with codebase overview, executive summary, dual-view detailed findings (by feature and by.
yigityildiz0/universal-ai-skill-library/skills/common/find-docs Skill
no license1★ repoRetrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific.
yigityildiz0/universal-ai-skill-library/skills/common/knowledge-base Skill
no license1★ repoCreate, organize, audit, or maintain a durable Markdown knowledge base with an index, atomic notes, stable identifiers, links, tags, and maintenance checks. Use for a personal or team knowledge base, research vault, documentation library, MOC, note organization, broken links, or knowledge-base cleanup; do not confuse it with short-term agent memory.
The same file is in 1 other repository
yigityildiz0/universal-ai-skill-library/skills/common/local-docs-lookup Skill
no license1★ repoGround agent answers in local library documentation (pydoc, go doc, vendored READMEs, help() in REPLs) rather than routing queries through a third-party.
yigityildiz0/universal-ai-skill-library/skills/common/notion-research-documentation Skill
no license1★ repoResearch across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or.
yigityildiz0/universal-ai-skill-library/skills/common/operations-runbook Skill
no license1★ repoCreate or improve an operational runbook for recurring operations, incidents, maintenance, onboarding, or controlled recovery. Use for runbook, operational procedure, escalation guide, recovery steps, or on-call documentation.
yigityildiz0/universal-ai-skill-library/skills/common/pdf-document-generation Skill
no license1★ repoGenerate professional PDF documents programmatically using Python and JavaScript libraries with precise layout control, typography, and multi-format.
yigityildiz0/universal-ai-skill-library/skills/common/process-documentation Skill
no license1★ repoDocument a repeatable process, SOP, run sequence, ownership model, or handoff with inputs, steps, decisions, exceptions, and verification. Use for SOP, process document, workflow documentation, operating procedure, or handoff guide.
yigityildiz0/universal-ai-skill-library/skills/common/release-notes-writer Skill
no license1★ repoGenerates professional release notes from git history, pull requests, and issues with conventional commit parsing and audience-specific formatting. Use when.
yigityildiz0/universal-ai-skill-library/skills/common/setup-writing-style Skill
no license1★ repoBuild a private, evidence-based writing-style profile from text the user explicitly provides, then calibrate it against drafts without copying distinctive passages or silently persisting personal data. Use when the user asks to capture their voice or make drafts sound like them; never scan unrelated messages, email, or files automatically.
yigityildiz0/universal-ai-skill-library/skills/common/sql-analytics Skill
no license1★ repoDesign, review, debug, or explain analytical SQL with correct grain, joins, filters, time logic, performance awareness, and validation. Use for SQL analysis, write a query, debug a query, metric SQL, warehouse query, cohort query, or database reporting.
yigityildiz0/universal-ai-skill-library/skills/common/stakeholder-update Skill
no license1★ repoWrite a concise, evidence-based stakeholder update for product, engineering, operations, research, or program work. Use for weekly update, status report, executive summary, project update, risk update, or leadership communication.
yigityildiz0/universal-ai-skill-library/skills/common/technical-documentation Skill
no license1★ repoGenerate architecture documentation, ADRs (Architecture Decision Records), design documents, and technical specifications. Use when documenting system.
yigityildiz0/universal-ai-skill-library/skills/common/technical-writer Skill
no license1★ repoProfessional technical writing expertise for clear, audience-appropriate documentation. Use when producing user-facing docs, API guides, onboarding.
yigityildiz0/universal-ai-skill-library/skills/common/test-writer Skill
no license1★ repoWrites unit and integration tests for new or changed code. Use when asked to "write tests", "add tests", "test coverage", "test this function".
yigityildiz0/universal-ai-skill-library/skills/common/user-documentation Skill
no license1★ repoCreate README files, installation guides, tutorials, quick starts, and user-facing documentation. Use when creating project documentation, onboarding.
yigityildiz0/universal-ai-skill-library/skills/common/writing-editing Skill
no license1★ repoProfessional writing and editing principles for clear, concise documentation and prose. Use when asked to write, edit, rewrite, or review documents, README.
yigityildiz0/universal-ai-skill-library/skills/common/writing-plans Skill
no license1★ repoUse when you have a spec or requirements for a multi-step task, before touching code
The same file is in 12 other repositories
yigityildiz0/scientific-agent-skills/skills/common/bioscience-research-router Skill
no license1★ repoRoutes life-science work across scientific strategy, literature review, experimental design, molecular-genetics assay planning, RStudio reproducible analysis, R data wrangling, R biostatistics, bulk RNA-seq differential expression (DESeq2), ggplot2 figures, Quarto reporting, academic presentations, research synthesis, knowledge organization, single-cell QC, scvi-tools, and nf-core/Nextflow workflows. Use for wet-lab, molecular genetics, bioinformatics, omics, laboratory data, R or RStudio analysis, statistics and modeling, data cleaning and joins, publication figures, scientific report writing, thesis or conference talks, research planning, evidence synthesis, or U.S. research-compliance questions where reproducibility, provenance, privacy, biosafety, IRB/IBC, GLP, or GMP boundaries matter.
yigityildiz0/scientific-agent-skills/skills/common/knowledge-base Skill
no license1★ repoCreate, organize, audit, or maintain a durable Markdown knowledge base with an index, atomic notes, stable identifiers, links, tags, and maintenance checks. Use for a personal or team knowledge base, research vault, documentation library, MOC, note organization, broken links, or knowledge-base cleanup; do not confuse it with short-term agent memory.
The same file is in 1 other repository
yigityildiz0/scientific-agent-skills/skills/common/r-biostatistics-workflow Skill
no license1★ repoPlan, fit, diagnose, interpret, and report statistical analyses in R for laboratory, genetics, and bioscience data. Use when choosing among linear, generalized-linear, mixed-effects, paired, nonparametric, permutation, survival, repeated-measures, or multiple-testing workflows; when writing R model formulas and contrasts; or when checking assumptions, effect sizes, confidence intervals, missing data, batch effects, and pseudoreplication. Require a defensible study design before modeling.
whatsmars/skills/skills/hongxi-tech-blog-writer Skill
no license1★ repo基于 javahongxi 博文风格的技术博客写作助手。擅长开源项目推广、技术深度解读、项目全景介绍、升级公告等类型的技术博文,输出结构清晰、代码丰富、风格统一的高质量 Markdown 文章。
M0rtalPhe0nix/dotfiles/.agents/skills/grill-with-docs Skill
1★ 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
M0rtalPhe0nix/dotfiles/.agents/skills/writing-great-skills Skill
1★ repoReference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
The same file is in 11 other repositories
motiful/ctx/skills/ctx-report Skill
1★ repoProduces a disposable HTML report laid out for a human to read, comment on, and decide from — then distills the keep-worthy conclusions into the source of truth and archives the report. Use when writing a report, a review doc, or an options-for-a-decision document for a human to weigh in on in a ctx knowledge base, when a human has commented on a report and it needs distilling, or when un-merged reports are piling up. Not for converging a pile of raw notes or subagent outputs straight into the source of truth — use ctx-merge for that.
motiful/ctx/skills/ctx-spec Skill
1★ repoWrites specs, ADRs, architecture and design docs that an AI coding agent can build directly from — the right granularity (constraints, not hand-written implementation), testable EARS acceptance criteria, and ADR discipline (record only decided choices, supersede in place). Use when writing or restructuring a spec, a decision record (ADR), an architecture doc, or a design doc in a ctx knowledge base, or when deciding how detailed a spec needs to be.
motiful/ctx/skills/ctx Skill
1★ repoSets up and orchestrates a ctx knowledge base — a lean, living single source of truth for multi-session AI-agent work — and classifies any doc or finding by its lifetime, routing the work to the right companion skill. Use when starting or scaffolding ctx on a new project, when unsure where a finding belongs (spec vs decision vs progress vs scratch), when unsure which ctx skill handles a task, or when docs have sprawled into redundant, contradictory piles that need converging. Entry point for the collection; routes to ctx-adopt (existing repos), ctx-merge (converge sources), ctx-spec (specs and ADRs), ctx-progress (work tracking), ctx-report (reports for a human), ctx-serve (host processes across sessions), ctx-compact (pre-reset checkpoint). For an existing/brownfield repo, use ctx-adopt instead.
JunfengRan/dev-env/skills/interpret-tech-notes Skill
1★ repo将论文、博客、前沿应用技术解读为 dev-env 知识库笔记(Markdown 或 HTML)。 触发:用户要求解读/精读/摘录论文、博客、开源 Agent 项目或应用技术; 写到 docs/knowledge/;或提到「写笔记」「技术深挖」「学习手册」「会话整合」。
JunfengRan/dev-env/skills/write-idea-docs Skill
1★ repo在 dev-env 撰写或修订开源设计文档(架构 / 技术栈 / 工作流 / 选型决策)。 触发:用户要求写架构设计、技术栈总览、方案取舍、选型决策; 新建或修改 docs/design/ 下 *-architecture.md、*-tech-stack.md、*-workflow.md、*-selection.md。