Best Agent Skills for Developers

Developer skills cover the software lifecycle: understanding what "done" means before writing code, designing the shape of a change, implementing it in the codebase, verifying it works and will keep working, debugging when it does not, and operating live systems safely. Some skills focus on a single stage, such as turning a vague request into acceptance criteria or tracing a failure to its cause; others span several stages, like taking a change from design through verification. Use the ranked list by starting with the stage where your work is currently stuck, then compare the skills that address it. Read each entry for the stage it targets and the inputs it expects, and pick the one whose scope matches the task in front of you rather than the broadest option available.

8 to start with66 top options

Start with these.

A developer's job tracks the software lifecycle: understand, design, implement, verify, and keep the system healthy.

These are the closest matches for this work. Start with the first one and open it to install.

What "done" means before writing code.The shape of the change, not only the lines. A sub-problem of this domain with no skills yet.Make the change in the codebase.Evidence it works, and that it will keep working.When it does not work, find the cause.Live systems, and the courage to change them safely.

66 top options

  1. Rank 04
    Direct

    code-review

    Two-axis review of a diff against repo coding standards and the originating spec, run as parallel sub-agents and reported side by side.

    • Verify
    689,485 · popularity
    View Agent Skill
  2. Rank 05
    Direct

    api-and-interface-design

    Notable

    Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

    • Implement
    View Agent Skill
  3. Rank 06
    Direct

    vue-debug-guides

    Notable

    Vue 3 debugging and error handling for runtime errors, warnings, async failures, and SSR/hydration issues. Use when diagnosing or fixing Vue issues.

    • Debug
    View Agent Skill
  4. Rank 07
    Direct

    mcp-builder

    Official

    Guides creating high-quality MCP servers that let LLMs interact with external services through well-designed tools, in Python or TypeScript.

    • Understand the need
    • Implement
    123,822 · popularity
    View Agent Skill
  5. Rank 08
    Direct

    fastify-best-practices

    Guides development of Fastify Node.js backend servers and REST APIs, covering routes, plugins, JSON Schema validation, hooks, logging, and deployment.

    67,955 · popularity
    View Agent Skill
Explore 58 more Agent Skills
  1. Rank 09
    Direct

    spec-driven-development

    Creates structured specifications before coding, with a gated specify-plan-tasks-implement workflow and capability mapping for multi-module work.

    • Understand the need
    50,859 · popularity
    View Agent Skill
  2. Rank 10
    Direct

    golang-concurrency

    Golang concurrency design covering goroutine lifecycle, channels and select, sync primitives, errgroup, worker pools, and fan-out/fan-in pipelines.

    38,285 · popularity
    View Agent Skill
  3. Rank 11
    Direct

    golang-troubleshooting

    Troubleshoots Golang programs systematically, covering debugging methodology, common pitfalls, pprof, Delve, race detection, and production debugging.

    • Debug
    36,797 · popularity
    View Agent Skill
  4. Rank 12
    Direct

    karpathy-guidelines

    Notable

    Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

    • Operate
    View Agent Skill
  5. Rank 13
    Direct

    nx-workspace

    Notable

    Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.

    • Debug
    62,506 · popularity
    View Agent Skill
  6. Rank 14
    Direct

    figma-implement-design

    Official

    Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.

    Needs (stated): Node.js

    View Agent Skill
  7. Rank 15
    Direct

    vue-best-practices

    Notable

    MUST be used for Vue.js tasks. Strongly recommends Composition API with `<script setup>` and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires Options API.

    • Implement
    View Agent Skill
  8. Rank 16
    Direct

    receiving-code-review

    Guides receiving code review feedback with technical rigor: verify before implementing, ask before assuming, and push back with reasoning rather than performative agreement.

    • Implement
    • Verify
    208,088 · popularity
    View Agent Skill
  9. Rank 17
    Direct

    solana-dev

    End-to-end Solana development playbook covering wallet connection, Anchor/Pinocchio programs, testing, security review, and the v1 transaction format.

    • Debug

    Needs (stated): Node.js

    84,230 · popularity
    View Agent Skill
  10. Rank 18
    Direct

    ai-sdk

    Answers questions about the Vercel AI SDK and helps build AI-powered features like agents, chatbots, RAG, and text generation with version-matched docs.

    64,619 · popularity
    View Agent Skill
  11. Rank 19
    Direct

    incremental-implementation

    Delivers changes in thin, verifiable vertical slices, implementing, testing, verifying, and committing one piece at a time with simplicity and scope discipline.

    • Understand the need
    • Implement
    48,577 · popularity
    View Agent Skill
  12. Rank 20
    Direct

    source-driven-development

    Grounds every implementation decision in official documentation, detecting stack versions, fetching relevant docs, and citing sources for framework-specific code.

    • Understand the need
    • Implement

    Needs (stated): Python

    44,922 · popularity
    View Agent Skill
  13. Rank 21
    Direct

    golang-code-style

    Golang code style conventions covering line length and breaking, variable declarations, control flow clarity, and when comments help or hurt.

    40,550 · popularity
    View Agent Skill
  14. Rank 22
    Direct

    golang-safety

    Defensive Golang coding against bugs like nil panics, typed-nil interfaces, append aliasing, integer truncation, and defer-in-loop issues.

    37,266 · popularity
    View Agent Skill
  15. Rank 23
    Direct

    azure-diagnostics

    Official

    description: "Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, troubleshoot functions, troubleshoot AKS, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM passwor

    • Debug
    516,714 · popularity
    View Agent Skill
  16. Rank 24
    Direct

    retrieving-developer-knowledge

    Official

    >- Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI/Gemini, Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms. Integrates with the Developer Knowledge MCP server (search_documents, get_documents, answer_query) or the Developer Knowledge REST API fallback. Use when searching for gcloud CLI commands, API syntax, IAM permissions, official documentation, architectural comparisons, or product choice overviews. Don't use for local filesystem lookups or non-Google documentation.

    View Agent Skill
  17. Rank 25
    Direct

    subagent-driven-development

    Executes implementation plans by dispatching a fresh implementer subagent per task with task review and a broad final review, preserving coordinator context.

    • Implement
    220,801 · popularity
    View Agent Skill
  18. Rank 26
    Direct

    finishing-a-development-branch

    Completes a development branch by verifying tests, detecting the git environment, presenting merge/PR/keep options, executing the choice, and cleaning up.

    • Implement
    201,717 · popularity
    View Agent Skill
  19. Rank 27
    Direct

    wrangler

    Runs and troubleshoots Wrangler CLI commands and configures Worker projects for local development, deployment, and Cloudflare resource management.

    110,097 · popularity
    View Agent Skill
  20. Rank 28
    Direct

    developing-genkit-js

    Develops AI-powered applications using Genkit in Node.js/TypeScript, covering flows, tools, agents, prompts, middleware, and generative UI.

    58,839 · popularity
    View Agent Skill
  21. Rank 29
    Direct

    deprecation-and-migration

    Manages deprecation and migration of old systems, APIs, and features, covering the deprecation decision, advisory vs compulsory, and safe migration processes.

    • Implement
    44,095 · popularity
    View Agent Skill
  22. Rank 30
    Direct

    golang-naming

    Go naming conventions covering packages, constructors, structs, interfaces, constants, errors, receivers, and acronyms with a quick reference table.

    • Implement
    37,540 · popularity
    View Agent Skill
  23. Rank 31
    Direct

    golang-benchmark

    Golang benchmarking, profiling, and performance measurement covering writing benchmarks, pprof, benchstat comparison, and CI regression detection.

    36,389 · popularity
    View Agent Skill
  24. Rank 32
    Direct

    brainstorming

    Notable

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

    • Understand the need
    • Implement
    View Agent Skill
  25. Rank 33
    Direct

    azure-prepare

    Official

    description: "Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (

    516,178 · popularity
    View Agent Skill
  26. Rank 34
    Direct

    agent-browser

    Browser automation CLI for AI agents to navigate pages, fill forms, click, screenshot, extract data, and test web apps, with specialized skills for Electron and QA.

    • Verify
    • Operate
    985,975 · popularity
    View Agent Skill
  27. Rank 35
    Direct

    retro

    Conducts a retrospective on a coding session, suggesting environment improvements like navigation pointers, automated checks, coding standards, and tool economy.

    • Implement
    • Debug
    196,301 · popularity
    View Agent Skill
  28. Rank 36
    Direct

    azure-validate

    Official

    description: "Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prerequisites before deploying. WHEN: validate my app, check deployment readiness, run preflight checks, verify configuration, check if ready to deploy, validate azure.yaml, validate B

    515,898 · popularity
    View Agent Skill
  29. Rank 37
    Possible

    frontend-design

    Official

    Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

    765,703 · popularity
    View Agent Skill
  30. Rank 38
    Possible

    frontend-design-review

    Official

    > Review and create distinctive, production-grade frontend interfaces with high design quality and design system compliance. Evaluates using three pillars: frictionless insight-to-action, quality craft, and trustworthy building. USE FOR: PR reviews, design reviews, accessibility audits, design system compliance checks, creative frontend design, UI code review, component reviews, responsive design checks, theme testing, and creating memorable UI. DO NOT USE FOR: Backend API reviews, database schema reviews, infrastructure or DevOps work, pure business logic without UI, or non-frontend code.

    • Understand the need
    • Implement
    • Verify
    View Agent Skill
  31. Rank 39
    Possible

    penpot-design-to-code-review

    Official

    Review a Penpot design against its implemented code (a source component or Storybook story) and emit a structured DRIFT report. Use when an engineer needs to confirm the build matches the design: extract HTML/CSS from a selection, map its tokens/structure/states to the code component, diff them, and list what each side is missing with severity and a reconciliation. Degrades gracefully to a design-system-token check when no code source is supplied. Triggers: 'design to code review', 'does my code match the design', 'design code parity', 'compare Penpot to my component', 'check this against Storybook', 'extract HTML/CSS from this selection', 'find design drift', 'design implementation diff'.

    • Implement
    • Verify
    View Agent Skill
  32. Rank 40
    Possible

    web-design-guidelines

    Official

    Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

    View Agent Skill
  33. Rank 41
    Possible

    google-agents-cli-workflow

    Entrypoint for building ADK agents on Google Cloud, covering scaffold, build, evaluate, deploy, publish, and observe phases with coding guidelines.

    • Debug
    • Operate
    481,876 · popularity
    View Agent Skill
  34. Rank 42
    Possible

    emil-design-eng

    Encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

    334,004 · popularity
    View Agent Skill
  35. Rank 43
    Possible

    improve-animations

    Surveys a codebase's animation and motion code as a senior advisor, producing a prioritized audit and self-contained implementation plans.

    • Implement
    179,500 · popularity
    View Agent Skill
  36. Rank 44
    Possible

    chatgpt-apps

    Official

    Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

    • Implement
    • Operate
    View Agent Skill
  37. Rank 45
    Possible

    figma-create-design-system-rules

    Official

    Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.

    • Implement

    Needs (stated): MCP server

    View Agent Skill
  38. Rank 46
    Possible

    firecrawl

    Notable

    Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site URLs, bulk extraction, downloading a site, change alerts, or pages needing clicks/login — web only; local files route to firecrawl-parse. For papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.

    View Agent Skill
  39. Rank 47
    Possible

    microsoft-foundry

    Official

    Builds, deploys, evaluates, and manages Microsoft Foundry agents, models, and resources end to end, including fine-tuning and CI/CD.

    • Understand the need
    556,103 · popularity
    View Agent Skill
  40. Rank 48
    Possible

    expo-dev-client

    Builds and distributes Expo development clients locally or via TestFlight for internal testing of native code changes on physical devices.

    65,254 · popularity
    View Agent Skill
  41. Rank 49
    Possible

    antfu-design

    Notable

    antfu-style design conventions, broadened. UnoCSS-first, class-based semantic tokens with dual light/dark for tooling and devtools UIs, plus design-read, anti-slop, and micro-interaction polish for landing pages and product surfaces. Use when building or refactoring any interface with UnoCSS.

    View Agent Skill
  42. Rank 50
    Possible

    application-design-center-design-deploy

    Official

    >- Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting deployment failures. Boundaries: - Only use for GCP-specific cloud infrastructure. - Only use for Terraform coding within the ADC context.

    • Understand the need
    View Agent Skill
  43. Rank 51
    Possible

    declarative-agent-developer

    Official

    > Create, build, deploy, and localize declarative agents for M365 Copilot and Teams. USE THIS SKILL for ANY task involving a declarative agent — including localization, scaffolding, editing manifests, adding capabilities, and deploying. Localization requires tokenized manifests and language files that only this skill knows how to produce. Triggers: "create agent", "create a declarative agent", "new declarative agent", "scaffold an agent", "new agent project", "add a capability", "add a plugin", "configure my agent", "deploy my agent", "fix my agent manifest", "edit my agent", "localize my agent", "add localization", "translate my agent", "multi-language agent", "add an API plugin", "add an MCP plugin", "add OAuth to my plugin", "review instructions", "improve instructions", "fix my instructions"

    View Agent Skill
  44. Rank 52
    Possible

    doc-coauthoring

    Official

    Guide 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.

    View Agent Skill
  45. Rank 53
    Possible

    figma-generate-design

    Official

    Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the Figma screen to match code'. This is the preferred workflow skill whenever the user wants to build or update a full page, screen, or view in Figma from code or a description. Discovers design system components, variables, and styles via search_design_system, imports them, and assembles screens incrementally section-by-section using design system tokens instead of hardcoded values.

    View Agent Skill
  46. Rank 54
    Possible

    penpot-design-md

    Official

    Extract a DESIGN.md design-documentation file from a Penpot file: a portable markdown spec (YAML frontmatter with colors/typography/rounded/spacing/components token maps + prose sections: Overview, Colors, Typography, Layout, Shapes, Components, Do's & Don'ts, Iteration Guide, Known Gaps) in the design-md format, grounded in the file's real tokens, library assets, and sampled component styles — never invented. Read-only on the canvas; writes one local markdown file. Triggers: 'generate DESIGN.md', 'create a design.md', 'document the design system as markdown', 'export design guidelines', 'extract design documentation', 'design system spec file', 'make a style guide file from this design'.

    View Agent Skill
  47. Rank 55
    Possible

    teams-app-developer

    Official

    Builds, tests, and deploys Microsoft 365 apps and agents for Teams and Copilot. Includes sub-skills for project creation, local testing, cloud deployment, troubleshooting, and Slack-to-Teams migration. USE FOR: Teams agent, bot, tab, message extension, Declarative Agents, Custom Engine Agents, local testing, Agents Playground, Azure resource provision, remote deployment, Slack to Teams migration, cross-platform bot development, Block Kit to Adaptive Cards conversion. DO NOT USE FOR: general web development, non-bot/non-Teams projects.

    View Agent Skill
  48. Rank 56
    Possible

    analyze-project

    Read-only skill for deep learning research repositories, mapping model structure, training and inference entrypoints, configs, and suspicious patterns.

    • Implement
    • Debug
    311,205 · popularity
    View Agent Skill
  49. Rank 57
    Possible

    obsidian-cli

    Interacts with Obsidian vaults via the Obsidian CLI to read, create, search, and manage notes, and to develop and debug plugins and themes.

    • Debug
    77,826 · popularity
    View Agent Skill
  50. Rank 58
    Possible

    herdr

    Controls Herdr, a terminal multiplexer for coding agents, to inspect and control panes, tabs, workspaces, commands, and other agents.

    63,378 · popularity
    View Agent Skill
  51. Rank 59
    Possible

    replicas-agent

    Guide for background coding agents running inside Replicas cloud workspaces, covering previews, Slack, Linear, GitHub, Google Workspace, Docker, and media.

    Needs (stated): Docker

    36,121 · popularity
    View Agent Skill
  52. Rank 60
    Possible

    ui-widget-developer

    Official

    | Build MCP servers for Copilot Chat using the OpenAI Apps SDK or MCP Apps SDK widget rendering support (any language). Use this skill when: - Creating MCP servers that integrate with M365 Copilot declarative agents - Building rich interactive widgets (React + Fluent UI) that render in Copilot Chat - Implementing tools that return structuredContent for widget rendering - Adapting an existing MCP server to support Copilot widget rendering - Setting up devtunnels for localhost MCP server exposure - Configuring mcpPlugin.json manifests with RemoteMCPServer runtime Do NOT use this skill for general agent development (scaffolding, manifests, deployment) — use declarative-agent-developer instead. This skill is ONLY for MCP server + widget development. Triggers: "MCP server for Copilot", "OpenAI Apps SDK", "Copilot widget", "structuredContent", "MCP plugin", "devtunnels MCP", "OAI app", "widget rendering", "UI widget"

    View Agent Skill
  53. Rank 61
    Possible

    developer-device-platform-basics

    Official

    >- Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.

    View Agent Skill
  54. Rank 62
    Possible

    google-cloud-recipe-onboarding

    Official

    >- Guides a developer's first steps on Google Cloud, covering account creation, billing setup, project management, and deploying a first resource. Use when a new developer wants to initialize their first Google Cloud project, configure billing, and verify deployment. Don't use for enterprise organization setup (use Google Cloud Setup guided flow for that instead). Don't use for complex multi-project architectures.

    View Agent Skill
  55. Rank 63
    Possible

    slack-to-teams

    Official

    Sub-skill of microsoft-365-agents-toolkit. Routed expert system with 100+ micro-expert files for migrating Slack bots to Teams, cross-platform bridging, and dual-platform bot development. USE FOR: migrating Slack bot to Teams, adding Teams support to Slack bot, building dual-platform bots, converting Block Kit to Adaptive Cards, identity/OAuth bridging, deploying bots to Azure or AWS, configuring AI model providers. DO NOT USE FOR: general web development, non-bot projects, standalone Teams development without Slack (use parent skill instead).

    • Understand the need
    • Implement

    Needs (stated): Python

    View Agent Skill
  56. Rank 64
    Possible

    explore-code

    Implementation leaf skill for auditable candidate changes in deep learning research repos, transplanting modules, adapting backbones, and adding LoRA layers.

    • Implement
    • Operate
    310,750 · popularity
    View Agent Skill
  57. Rank 65
    Direct

    using-superpowers

    Notable

    Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

    View Agent Skill
  58. Rank 66
    Possible

    ui-taste

    Gives coding agents better UI taste with anti-ui-slop playbooks for web and iOS interfaces, covering design, implementation, redesign, and critique.

    • Implement
    452,376 · popularity
    View Agent Skill
What this topic covers

What this topic covers

Each sub-topic groups Agent Skills for a specific situation.

Understand the need
What "done" means before writing code.
Design
The shape of the change, not only the lines.
Implement
Make the change in the codebase.
Verify
Evidence it works, and that it will keep working.
Debug
When it does not work, find the cause.
Operate
Live systems, and the courage to change them safely.
Frequently asked questions

Frequently asked questions

How is this list ordered?
The list is ranked by observed search demand. Direct matches for the topic appear first, and the ranking caps how many skills any single publisher can place.
Should I pick a skill that covers the whole lifecycle or one stage?
Match the skill's scope to the task. A skill aimed at understanding the need or designing the change fits early work, while implementation, verification, debugging, and operations skills fit the later stages.
What does a developer skill actually take as input?
It depends on the stage. Skills for understanding the need work from a request or requirement, design skills from that understanding, and debugging skills from a failure or unexpected behavior in the codebase.
Can I use more than one developer skill on the same task?
Yes. The lifecycle stages are distinct, so a task can move from a skill that defines what done means to one that implements the change and another that verifies it.

How to install an Agent Skill

Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:

  • Claude Code — copy the SKILL.md for firecrawl-developer-index into ~/.claude/skills/firecrawl-developer-index/ for yourself, or .claude/skills/firecrawl-developer-index/ to share it with a project.
  • From the registry — run npx skills add firecrawl/skills@firecrawl-developer-index.
  • Or download firecrawl-developer-index from its source and place that SKILL.md in the directory above.

How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.