AI Plugin IndexClaude skills list
Top Claude skills
The best Claude skills ranked by score, out of 89,423 skills found in public GitHub repositories. Copies of the same skill are merged, so each entry is an original.
Updated 21 October 2026 · ranked by score · how we rank
#1reverse-skill-routerzhaoxuya520
84Use the reverse-skill repository from Codex for authorized reverse engineering, security analysis, CTF, and defensive testing tasks. Requires the reverse-skill repository to be available as the current workspace or an explicitly supplied local path.
AAA
#2getting-startedwasp-lang
84Get started with your Open SaaS project — fetches docs, checks Wasp installation, and helps you start your database and app.
AAA
#3kind-clusterprojectcalico
84Create, deploy to, reload, and tear down a local kind cluster running Calico from locally-built images. Use when the user wants to bring up a test cluster, try a change on a real cluster, reload a rebuilt image onto kind, or destroy the cluster.
AAA
#4mobilebuildmcp-rendering-streaming-reviewgetsentry
84Use when reviewing MobileBuildMCP rendering, streaming fragment, next-step, and CLI output mode changes for boundary violations.
AAA
#5frontend-api-contractsOpenHands
84This skill should be used when the user asks to "add an API call", "change a backend", "update settings persistence", "change conversation events", "fix backend auth", "add Agent Server support", or changes src/api, backend registry, Cloud/runtime transport, settings, secrets, compatibility, or conversation resume behavior.
AAA
#6frb-debuggingfzyzcjy
84Use when generated code looks wrong, code generation fails, or you need to understand FRB internals
AAA
- 7remove-unused-includes chromium · Browser automationLook through a given folder to find and safely remove unused includes specifically for Clang-compiled code (using clang-include-cleaner), verifying that referencing targets compile.84
- 8scrape davila7 · Browser automationScrape any webpage as clean markdown via Bright Data Web Unlocker API. Bypasses bot detection and CAPTCHA. Requires BRIGHTDATA_API_KEY and BRIGHTDATA_UNLOCKER_ZONE environment variables.84
- 9critical-images thedaviddias · MediaUse when reviewing image assets, markup, and CDN or build transforms related to Prioritize loading critical images. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.84
- 10release-process fossasiaVersion bumping, release workflow, and PyPI publishing process for Visdom84
- 11image-cdn thedaviddias · MediaUse when reviewing image assets, markup, and CDN or build transforms related to Serve images from a CDN. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.84
- 12fix-members-short-description flet-dev · Developer toolsUse when asked to fix short descriptions of Python type members.84
- 13ego-browser citrolabs · Browser automationWhen you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is a Chromium browser designed for both human users and AI Agents. Agents can use the user's logged-in websites and personal context to complete tasks and collaborate smoothly with the user through the browser interface. Therefore, prefer ego-browser over built-in browsers or other web tools.84
- 14prowler prowler-cloud · Developer toolsMain entry point for Prowler development - quick reference for all components. Trigger: General Prowler development questions, project overview, component navigation (NOT PR CI gates or GitHub Actions workflows).84
- 15project-structure microsoft · AI and LLM toolsExplains the project structure of the agent-framework .NET solution84
- 16css-file-size thedaviddias · DesignUse when auditing slow page loads, heavy assets, or rendering delays related to Optimize CSS file size. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.84
- ADYour product hereThis row is seen by people browsing the Claude skills rankings. Book it from $249 a month.See prices →
- 17browser-caching thedaviddias · Browser automationUse when auditing slow page loads, heavy assets, or rendering delays related to Enable browser caching. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.84
- 18decompile-apk androguard · Developer toolsDecompile an APK (or one class/method) to Java with Androguard dex-decompiler bindings84
- 19conversion-issues openvinotoolkit · Developer toolsInvestigate and fix model conversion issues in OpenVINO Frontends (ONNX, PyTorch) — triage, debugging, accuracy comparison, and pre-submission verification.84
- 20changelog-scan cobusgreylingScan recent merges and commits since last release for changelog content.84
- 21css-order thedaviddias · DesignUse when reviewing stylesheets, component styles, and responsive behavior related to Order CSS files correctly. Check the rendered layout across breakpoints and interaction states before proposing a fix.84
- 22Shade imports TryGhostImport Shade from layer-specific subpaths (primitives, components, patterns, page-templates, utils), never the root barrel. Trigger when editing TSX/TS in Shade-consuming apps.84
- 23highlights pierrecomputer · DesignUse when an app uses @pierre/highlights to generate syntax-highlighted HTML or tokens, stream code, incrementally tokenize edits, or apply Zed-compatible themes and CSS variables.84
- 24update-deps pydanticCreate a PR in which all dependencies are updated to their latest versions and CI is passing. Only user initiated.84
- 25tidb-bazel-prepare-gate pingcap · Developer toolsUse when deciding whether make bazel_prepare is required before build or test commands based on local file changes in TiDB.84
- 26draft-release-notes cobusgreyling · ProductivityGenerate categorized release notes draft from scan data. Human must approve before publish.84
- 27code2prompt-conventions mufeedvhFollow code2prompt architecture and implementation conventions when changing or reviewing code.84
- 28error-handling thedaviddias · Browser automationUse when reviewing scripts, client components, bundles, or runtime behavior related to Implement proper error handling. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.84
- 29triage-ticket agentscope-ai · CommunicationFirst-response playbook for an inbound customer message — classifies the ticket, restates the issue, gathers missing context, and routes the reply.84
- 30mobilebuildmcp-cli getsentry · Cloud and DevOpsOfficial skill for the MobileBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).84
- 31third-party-scripts thedaviddiasUse when auditing slow page loads, heavy assets, or rendering delays related to Optimize third-party script loading. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.84
- 32file-upload-accessibility thedaviddias · Browser automationUse when reviewing templates, rendered HTML, or shared components related to Make file uploads accessible. Validate the final browser-facing markup, not just the source framework abstraction.84
- 33build-game-inventory MengTo · Developer toolsBuild or repair game inventory, loot, equipment, tooltips, drag-and-drop, persistence, and progression systems. Use for item schemas, pickup flows, stack rules, equipment slots, atomic swaps, save migration, and no-loss regression testing.84
- 34telecrawl steipete · Search and webTelegram archive: chats, messages, contacts, folders, search; import from Telegram Desktop/macOS.84
- 35advogado-especialista sickn33Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.84
- 36accessible-tooltips thedaviddias · Browser automationUse when reviewing templates, rendered HTML, or shared components related to Create accessible tooltips. Validate the final browser-facing markup, not just the source framework abstraction.84
- 37carousel-accessibility thedaviddias · Browser automationUse when reviewing templates, rendered HTML, or shared components related to Make carousels accessible. Validate the final browser-facing markup, not just the source framework abstraction.84
- 38discussion samchon · Search and webRuns structured multi-agent discussions for open-ended typia topics. Use only when the user explicitly asks for Discussion or a team debate with transcripts and conclusions; do not use for Self-Review, a solo or multi-agent review, research review, or issue discovery.84
- 39unique-id thedaviddias · Browser automationUse when reviewing templates, rendered HTML, or shared components related to Ensure all IDs are unique. Validate the final browser-facing markup, not just the source framework abstraction.84
- 40js-libraries thedaviddiasUse when auditing slow page loads, heavy assets, or rendering delays related to Use secure and up-to-date JS libraries. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.84
- 41tabindex thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Use appropriate tabindex values. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 42dagger-chores dagger · Developer toolsHandle quick, repeatable Dagger repository maintenance chores. Use when the user asks for small operational changes and wants the same established edits and commit style applied quickly.84
- 43slack-bot-builder sickn33 · SecurityBuild Slack apps using the Bolt framework across Python, JavaScript, and Java. Covers Block Kit for rich UIs, interactive components, slash commands, event handling, OAuth installation flows, and Workflow Builder integration.84
- 44ov-ensure-coding-style openvinotoolkit · Developer toolsDetect and fix clang-format, clang-tidy, and copyright header violations in an OpenVINO C++ codebase. Use when the user complains about code style or formatting, asks to clean up changes, fix linting, add a copyright header, or when a style check or linting CI job is failing. Do not use for build errors, compilation failures, linker errors, test failures, runtime crashes, accuracy issues, or CMake config problems.84
- 45first-contentful-paint thedaviddiasUse when auditing slow page loads, heavy assets, or rendering delays related to Optimize first contentful paint. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.84
- 46advogado-criminal sickn33Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.84
- 47accordion-accessibility thedaviddias · Browser automationUse when reviewing templates, rendered HTML, or shared components related to Make accordions keyboard navigable. Validate the final browser-facing markup, not just the source framework abstraction.84
- 48clean-up-comments thedaviddias · Browser automationUse when reviewing templates, rendered HTML, or shared components related to Remove comments and debug code in production. Validate the final browser-facing markup, not just the source framework abstraction.84
- 49loading-indicators thedaviddiasUse when auditing slow page loads, heavy assets, or rendering delays related to Show loading indicators. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.84
- 50fal-platform sickn33 · AI and LLM toolsPlatform APIs for model management, pricing, and usage tracking84
- 51list-structure thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Use correct list structure. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 52agentation-watch-mode latitude-devContinuous Agentation annotation handling. Use when the user says "watch mode", asks you to watch for Agentation annotations, process feedback as it arrives, or keep fixing annotation-driven changes until told to stop or a timeout is reached.84
- 53handle-pr-comments storybookjs · Developer toolsTriage and resolve GitHub PR review comments one by one, interactively. Use when the user asks to handle, address, respond to, or resolve PR review comments, or mentions reviewer feedback on a pull request.84
- 54code-review langchain-ai · Developer toolsPerform a structured code review of changes, checking for correctness, style, tests, and potential issues.84
- 55office-export-pdf deepseek-ai · Documents and filesConvert an Office document to a requested PDF with LibreOffice Kit.84
- 56aria-deprecated-role thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Avoid using deprecated ARIA roles. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 57channels-setup CopilotKit · Documents and filesUse when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams: "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding the project, building the AG-UI agent, creating and reconciling the managed Channel with the public CopilotKit CLI, running the long-running host, and proving a real provider mention gets a reply. The workflow is not in this file. Run `npx --yes copilotkit@latest onboard start` and follow the graph it prints.84
- 58css-critical thedaviddias · DesignUse when reviewing stylesheets, component styles, and responsive behavior related to Inline critical CSS for faster rendering. Check the rendered layout across breakpoints and interaction states before proposing a fix.84
- 59interaction-to-next-paint thedaviddiasUse when auditing slow page loads, heavy assets, or rendering delays related to Optimize interaction to next paint. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.84
- 60paste-inputs thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Allow pasting into form inputs. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 61sergo-examples github · Developer toolsOptional Sergo examples for cache formats and reporting templates.84
- 62Format numbers TryGhost · Documents and filesFormat numbers using the formatNumber function from Shade whenever someone edits a TSX file.84
- 63firebase davila7 · DatabasesFirebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I84
- 64openclaw-brand openclaw · Documents and filesApply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials. Use when the task changes brand identity rather than ordinary product UI or public-page composition.84
- 65definition-list thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Use correct definition list structure. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 66unit-testing NativeScript · Developer toolsHow to run and write unit tests in this workspace (Vitest, colocated .spec.ts files, mocked native globals). Use when writing, changing, or running tests.84
- 67form-field-multiple-labels thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Use a single label for each form field. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 68aria-allowed-attr thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Use only allowed ARIA attributes for each role. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 69claude-win11-speckit-update-skill sickn33 · Developer toolsReview updates to GitHub SpecKit on Windows 11 with PowerShell, preserving local templates and customizations84
- 70memcode ThinkInAIXYZ · Knowledge and memoryUse the enabled Memcode MCP connection to explicitly save approved facts and recall relevant memories across DeepChat conversations. Never save a transcript or retrieve memory automatically.84
- 71heading-order thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Maintain logical heading order. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 72omni-db-backups diegosouzapw · DatabasesTrigger system backups, restore from backup files, and manage the SQLite database lifecycle. Supports export, import, and incremental snapshot strategies.84
- 73triage aaddrickTrigger the issue triage workflow for a specific issue. Usage: /triage {issue_number}84
- 74run-on-3v4l phpstan · Developer toolsExecute PHP code on 3v4l.org to test runtime behavior across multiple PHP versions. Use when you need to verify what PHP actually does with a piece of code.84
- 75segment-cdp sickn33 · Data and analyticsExpert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols, identity resolution, destinations configuration, and data governance best practices.84
- 76rewrite-commit-message penpot · DesignRewrite HEAD's commit message (typically a squash that concatenated old messages) into one proper title plus description following Penpot commit conventions, preserving every distinct AI-assisted-by attribution. Amends in place, never pushes.84
- 77iac-scan andrewyng · Cloud and DevOpsScan Terraform/IaC with trivy config and fix what matters in code84
- 78a2ui-blueprint-maintenance a2ui-projectManage the evolution, merging, archiving, and cleanup of specifications and blueprints across the workspace.84
- 79python-repl gptme · Developer toolsInteractive Python REPL automation with common helpers and best practices84
- 80aria-tooltip-name thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Provide accessible names for tooltips. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 81focus-management thedaviddiasUse when reviewing rendered HTML, interactive components, or design-system patterns related to Manage focus during dynamic interactions. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.84
- 82concise-planning sickn33 · ProductivityUse when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.84
- 83gsd-review open-gsd · AI and LLM toolsRequest cross-AI peer review of phase plans from external AI CLIs84
- 84plaid-fintech sickn33Expert patterns for Plaid API integration including Link token flows, transactions sync, identity verification, Auth for ACH, balance checks, webhook handling, and fintech compliance best practices.84
- 85const-let thedaviddias · Browser automationUse when reviewing scripts, client components, bundles, or runtime behavior related to Prefer const and let over var. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.84
- 86organization agentscope-ai · CommunicationUse only when you need to look up team topology, worker phase, runtime state, or identity that is NOT available from the current message context. Do not use for standard task flows — the coordinator is the message sender, and the task room is in meta.json.room_id.83
- 87refactor-plan BuilderIO · Developer toolsJudge whether a system is fragile or just fast-moving, and write a ticket-ready refactor plan for one root problem, with measured evidence and a stable fingerprint. Use after system history (or a bug trace) points at a systemic problem worth fixing at the root.83
- 88commonroom BuilderIOLook up community member engagement and signals via Common Room. Use this skill when the user asks about community activity, member engagement, or community signals.83
- 89fix-board FastLEDAutomatically diagnose and fix board upload/monitor issues. Runs three-phase device workflow (Compile, Upload, Monitor) and applies fixes.83
- 90find-package-skill Azure · Cloud and DevOps**UTILITY SKILL** — Must be consulted before making any changes to packages under sdk/. Discovers and loads package-specific domain knowledge that prevents common mistakes. WHEN: add feature to package; fix bug in package; modify package code; regenerate from typespec; change client library.83
- 91booker BuilderIOPublic booking flow — the state machine, animations, and URL/app-state sync.83
- 92update-pr-body allenai · Developer toolsUpdate the body of a GitHub pull request. Use when the user asks to update, edit, or modify a PR description/body.83
- 93expert-rmt5 FastLEDESP-IDF v5.x RMT5 API expert for LED protocols, encoders, and multi-channel control. Use when working with RMT peripheral programming, LED strip control, or migrating from RMT4 to RMT5.83
- 94peon-ping-toggle PeonPing · AI and LLM toolsToggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.83
- 95build-release-maintenance NewFuture · Cloud and DevOpsMaintain DDNS GitHub Actions, Docker and Nuitka builds, packaging, installer validation, and release preparation while preserving matrices, caches, and protected publishing.83
- 96teamharness-organization agentscope-ai · ProductivityUse to understand TeamHarness team roles, responsibility boundaries, and who owns project, task, runtime, and control-plane work.83
- 97dev-rules kubernetes-sigs · Cloud and DevOpsEnforces project-specific development rules and conventions.83
- 98plan-hosted-writes BuilderIOPreconditions and protocol for writing hosted plans: real user session, `expectedUpdatedAt` revision guard on destructive writes, post-write verification, and when feedback may be resolved or consumed. Use when performing any hosted plan write.83
- 99parse-document superlinked · Documents and filesConvert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.83
- 100devtools-imports ChromeDevToolsConventions for importing code in Devtools to avoid build errors. Covers cross-module imports, internal imports, and the "import * as" requirement.83
