Development Claude Skills
8 673 development skills from 759 authors. They write and change code. Half of them fit into 1 830 tokens or less — that is what one costs your context window when the agent loads it. 1 213 ship runnable scripts rather than instructions alone. 42 of them cannot work without an MCP server, most often rube. We also found 1 239 copies of these same skills sitting in other people's repositories — counted once here, not 1 239 times.
8 673 unique 759 authors 10 updated this month 1 368 from vendors
Creates a pull request from current changes, monitors GitHub CI, and debugs any failures until CI passes. Activate when the user says "create pr", "make a pr", "open pull request", "submit pr", "pr for these changes", or wants to get their current work into a reviewable PR. Assumes the project uses git, is hosted on GitHub, and has GitHub Actions CI with automated checks (lint, build, tests, etc.). Does NOT merge - stops when CI passes and provides the PR link.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Research a codebase and create architectural documentation describing how features or systems work. Use when the user asks to: (1) Document how a feature works, (2) Create an architecture overview, (3) Explain code structure for onboarding or knowledge transfer, (4) Research and describe a system's design. Produces markdown documents with Mermaid diagrams and stable code references suitable for humans and AI agents.
Orchestrates implementation of a plan file by delegating work to subagents in parallel. Verifies git branch state, tracks progress, and ensures high-quality implementation. Invoke with a plan file path and optional model override: /implement plans/my-plan.md [--model sonnet]
> Comprehensive R package for command-line interface styling, semantic messaging, (1) Format console output with inline markup and colors, (2) Display errors, warnings, or messages with cli_abort/cli_warn/cli_inform, (3) Show progress indicators for long-running operations, (4) Create semantic CLI elements (headers, lists, alerts, code blocks), (5) Apply themes and customize output styling, (6) Handle pluralization in user-facing text, (7) Work with ANSI strings, hyperlinks, or custom containers. Also use when migrating from base R message/warning/stop, debugging cli code, or improving existing cli usage.
Help users write correct R code for async, parallel, and distributed computing using mirai. Use when users need to run R code asynchronously or in parallel, write mirai code with correct dependency passing, set up parallel workers, convert from future or parallel, use mirai_map, integrate with Shiny or promises, or configure cluster/HPC computing.
Build command-line apps in R using the Rapp package. Use when creating a CLI tool in R, adding argument parsing to an R script, turning an R script into a command-line app, shipping CLIs in an R package, or using Rapp (the alternative Rscript front-end). Also use for shebang scripts, exec/ directory in R packages, or subcommand-based R tools.
> Install, share, sync, and create AI agent skills across coding tools (Claude Code, Cursor, Codex, OpenCode, Copilot, Pi) using the agr CLI. Use skill ("install the pdf skill", "agr add ..."), sync agent resources across tools, share skills with their team, scaffold a new SKILL.md, run a skill ephemerally (agrx), set up a repo to manage AI agent dependencies, or configure tools/sources/instruction-syncing. Also use whenever an agr.toml or agr.lock is present in the project and the user is doing resource-management work.
> Release process for the agr package. Handles version bumping (major/minor/patch/beta), changelog updates, pre-release quality checks, git tagging, and monitoring the GitHub Actions publish pipeline. Use this skill whenever the user wants to cut a release, bump the version, publish to PyPI, or asks about the release process — even if they just say "let's ship it" or "time for a new version".
> Debrief an AI agent skill (SKILL.md) after using it — capture session feedback or a retrospective and fold it back into the skill. Use whenever X", "feedback on X skill", "improve the X skill", "update the X skill", "let's revise X based on what we just did", "the X skill should also handle Y", "X didn't trigger when it should have", or otherwise wants to capture lessons from a session back into the skill that drove it. Handles in-repo skills (under skills/) by editing the source, committing, and re-installing via `agr upgrade`. Handles remote/upstream skills by offering to fork them in-repo or to file a GitHub issue via `gh`. Do NOT use for greenfield skill authoring (a separate concern — see `anthropics/skills/skill-creator`) or for installing / syncing / removing skills (use the `agr` CLI directly).
> Multi-agent DAG orchestration for workflows where AI agents collaborate via dependency graphs, covering agent spawning, output merging, and quality evaluation. Use when a task needs multiple specialized agents or to parallelize AI work.
> This skill should be used when the user asks to "evaluate LLM output quality", "set up LLM-as-judge", "build an eval rubric", "compare model outputs pairwise", or "measure agent quality".
> Review REST API designs for quality, consistency, and breaking changes. Lints OpenAPI specs, generates scorecards, and detects breaking changes between versions. Use when designing APIs, reviewing contracts, or managing API versioning.
> This skill should be used when the user asks to "batch LLM requests", "should I use the batch API", "estimate batch vs realtime cost", "design a bulk LLM job", or "process thousands of prompts cheaply".
> Code review automation for TypeScript, JavaScript, Python, Go, Swift, and Kotlin. Analyzes PRs for complexity, risk, SOLID violations, and code smells. Use when reviewing PRs, analyzing code quality, or generating review checklists.
> Build ordered, annotated tours of an unfamiliar codebase and keep the anchors from rotting. Use when onboarding an engineer, handing off a service, or explaining a subsystem before a review.
> OpenAI Codex CLI and cross-platform skill authoring. Use when setting up Codex CLI, converting or syncing skills between Claude Code and Codex, configuring agents/openai.yaml, or validating cross-platform skill compatibility.
> guides, runbooks, and debugging guides. Use when onboarding new team members, open-sourcing, or documenting after a major refactor.
> Detect documentation drift against code changes, score staleness, validate API docs via AST parsing, and audit link integrity. Use when docs fall out of sync with code, preparing releases, running CI doc gates, or auditing doc accuracy.
> Scan project dependencies for vulnerabilities, license issues, and upgrade opportunities across Python, Node.js, Go, and Rust. Use when auditing dependencies, checking licenses, planning upgrades, or assessing supply chain security.
> sync, branch isolation, and cleanup. Use when working multiple branches at once, running parallel CI validations, or isolating agent workspaces.
> Generate SaaS boilerplate with auth, database schemas, Stripe billing, multi-tenancy, API routes, and dashboard UI on a Next.js/TypeScript/Tailwind stack. Use when starting a new SaaS product, subscription app, or multi-tenant platform.
> Fullstack development toolkit with project scaffolding for Next.js/FastAPI/MERN/Django stacks and code quality analysis. Use when scaffolding new projects, analyzing codebase quality, or implementing fullstack architecture patterns.
> Frontend development for React, Next.js, TypeScript, and Tailwind CSS. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding projects, implementing accessibility, or reviewing frontend code.
> Validate and score Claude Code skill packages for quality, completeness, and best-practice compliance. Tests Python scripts, checks YAML frontmatter, and generates reports. Use when creating, validating, or auditing skill packages.
> Evaluate and compare technology stacks with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.
> Product manager toolkit covering RICE prioritization, customer interview analysis, PRDs, and discovery frameworks. Use for feature prioritization, user research synthesis, requirement documentation, or product strategy.
> ticket decomposition, branch strategy, and PR sequencing. Use when breaking a PRD into tickets or designing the branch/PR sequence.
|
| Discover and list all URLs on a website without extracting content, via the Tavily CLI. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where something is on a domain, or says "map the site", "find the URL for", "what pages are on", "list all pages", or "site structure". Faster than crawling — returns URLs only. Essential when you know the site but not the exact page. Combine with extract for targeted content retrieval.
| Extract clean markdown or text content from specific URLs via the Tavily CLI. Use this skill when the user has one or more URLs and wants their content, says "extract", "grab the content from", "pull the text from", "get the page at", "read this webpage", or needs clean text from web pages. Handles JavaScript-rendered pages, returns LLM-optimized markdown, and supports query-focused chunking for targeted extraction. Can process up to 20 URLs in a single call.
Build and maintain a Markdown guide that helps humans understand a repository through real behavior, concepts, and evidence. Use when a user asks to understand a repo, generate or update repo-docs, answer repo-architecture/onboarding questions, seed docs for a new project, sync docs after code changes, or delete generated repo docs.
When you want to brainstorm and check available .com domains for a new project — brand naming, aftermarket pricing (HugeDomains / Afternic / Sedo / Dan), USPTO trademark screening, and social handle availability. Built on Laura Roeder's \"work backwards from availability, not from a name you fell in love with\" methodology. Uses Vercel CLI + whois + Domainr API + Namecheap API + agent-browser for the pieces each tool actually reliably supports (multi-tool ensemble because no single tool covers everything cleanly). 11-step workflow: budget → brainstorm → primary availability check → whois cross-check → Domainr aggregation → Namecheap price → aftermarket sweep → bucket → negotiate → NAME research (trademark + socials) → buy. Triggers on \"/domain,\" \"find a domain,\" \"check domain availability,\" \"brainstorm a domain,\" \"what .com is available for X,\" \"domain hunt,\" \"name my project,\" \"is X.com available,\" \"aftermarket price on X.com,\" \"trademark check for X.\
When you want to manage projects across your businesses using a kanban + Eisenhower methodology. One kanban per business (whatever portfolio of businesses, projects, or initiatives you run). Tool-agnostic — connects via API/MCP to whatever PM tool each business uses (Notion, GitHub Projects, Plane, Linear, Obsidian file-based, or manual mode). Async-first output. Six modes — setup (scaffold a new board for a business), triage (Eisenhower-sort the backlog), next (pick the next thing to work on, single board or across all), status (paste-ready async snapshot), unblock (diagnose Review/Blocked column), weekly (Friday pulse + week planning). Triggers on "/pm," "/pm setup," "/pm triage," "/pm next," "/pm status," "/pm unblock," "/pm weekly," "what should I work on next," "kanban status," "Eisenhower this," "triage my backlog," "what's blocked.
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDE_DECK_REPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand gradients, optional sections for "where am I" context, and speaker notes. Inspired by zarazhangrui/frontend-slides — "show, don't tell" applied to narrative (presents 3 angles, you pick) plus density modes (speaker-led vs reading-first). Four modes — new (draft from brief), update (modify existing, with overflow guards), ppt (convert legacy PPTX → React deck), export (Playwright snapshot existing React deck to standalone HTML, PDF, or Vercel URL — keeps brand). Triggers on "/slide-deck," "/slides new," "/slides export," "/slides update," "/slides ppt," "draft a deck," "deck for [topic]," "talk on [topic]," "keynote on [topic]," "internal deck for [audience]," "convert this pptx," "export this deck.
When you want to integrate an external tool, API, MCP server, or service into a project — the wizard walks you through auth, config, env vars, client wrapper code, example usage, and (optionally) a smoke-test. Scoped to Next.js and Rails projects (the two primary stacks). Interactive Q&A pattern — starts with the tool name, asks structured questions until the integration is fully specified, then scaffolds files. Examples of tools to toolify — Stripe, Kit, Sanity, Notion, Neon, Supabase, Fathom, Rewardful, SavvyCal, Riverside, ScrapeCreators, Anthropic, OpenAI, Gemini, Twilio, Resend, Postmark, Vercel Blob, custom internal APIs. For MCP servers specifically, also handles the .mcp.json wiring. Triggers on "/toolify," "integrate X," "add X to this project," "wire up X," "set up the X integration," "hook up X," "connect X," "add MCP for X." Part of the -ify trifecta (skillify / toolify / loopify) for extending Claude Code. NOT for adding new SKILL.md files — that's skillify. NOT for cron/agent loops — that's loopify.
Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing, hanging, slow, producing weird metrics, has crashed, or asks to debug, diagnose, troubleshoot, or investigate a training issue.
Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring setup, and restart-cleanup. Use when the user asks to launch, kick off, start, restart, or kill a training run, or mentions launching a multi-hour or multi-day GPU job (python train, accelerate launch, torchrun, deepspeed, sbatch, tmux training).
A comprehensive guide and reference for building agents using LangGraph 1.0, including ReAct agents, state graphs, and tool integrations.
This skill should be used when the user requests brand analysis, brand guidelines creation, brand audits, or establishing brand identity and consistency standards. It provides comprehensive frameworks for analyzing brand elements and creating actionable brand guidelines based on requirements.
This skill should be used when writing documentation for codebases, including README files, architecture documentation, code comments, and API documentation. Use this skill when users request help documenting their code, creating getting-started guides, explaining project structure, or making codebases more accessible to new developers. The skill provides templates, best practices, and structured approaches for creating clear, beginner-friendly documentation.
This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability. Use this for identifying code smells, architectural issues, dependency problems, missing documentation, security vulnerabilities, and creating comprehensive technical debt documentation.
Go interface design, dependency direction, and package coupling patterns. Use when defining interfaces, choosing where to place them, designing constructors, injecting dependencies, or reviewing import graphs. Trigger on exported interfaces in provider packages, interfaces matching a single type, backwards imports (server importing client), or functions accepting entire config structs when they need one field. Supersedes generic Go interface guidance with stronger opinions on consumer-side interfaces and coupling.
Go type safety, standard library type preferences, and the 'parse don't validate' principle. Use when handling IP addresses, MAC addresses, network types, or any string-typed domain data. Trigger on net.IP usage (prefer netip.Addr), string MAC addresses (prefer net.HardwareAddr), stringly-typed variables that should be custom types, or reflect.DeepEqual where == suffices. Also trigger on 'parse don't validate' discussions or type conversion at boundaries.
Go platform/OS-specific code patterns for cross-platform projects. Use when writing or reviewing code that must work on multiple OSes (Linux, Windows), when you see noop stubs in _<os>.go files, runtime.GOOS checks, or OS-specific build tags. Supersedes generic Go guidance on build tags and OS-specific code. Trigger on any code that branches by operating system.
Go context propagation, goroutine lifecycle, and process shutdown discipline. Use when writing or reviewing code that spawns goroutines, manages process lifecycle, passes context through call chains, or handles graceful shutdown. Trigger on context.Background() outside of main/tests, fire-and-forget goroutines, custom exit channels where context would suffice, or missing context in function signatures. Also trigger when reviewing init/startup code that creates its own contexts instead of accepting one.
Go control-plane contract design for Azure/azure-container-networking. Use when changing CRD Go types, status/condition fields, response-code mapping, controller/reconciler bootstrap logic, or generated contract artifacts such as CRD manifests and rendered Dockerfiles. Trigger on edits under crd/, API type packages, response/status code enums, reconciler init or migration code, or any change that affects externally consumed state.