Most popular Claude skills · page 107

Agent skills for Claude Code, Claude.ai and other agents, ranked by popularity: GitHub stars, forks, and how many curated lists and repos include them.

22,429 skills · showing 5089–5136

  1. 5089Broll Assetserduo1998-cell/erduo-broll-loop-engineeringFreeze known shared media, fonts, provenance, licenses, and reusable derivatives while keeping shot-specific provided, search, generation, and mixed material routes open for Chapter Builders.253
  2. 5090Broll Directorerduo1998-cell/erduo-broll-loop-engineeringTurn a complete original SRT and design into immutable shot truth, revisable creative proposals, semantic chapters, a shared visual world, a compact motion map, and three representative-scene choices.253
  3. 5091Broll Hybrid Integrateerduo1998-cell/erduo-broll-loop-engineeringRead and verify legacy hybrid Integrator records for a pre-v0.9 task. Never dispatch this stage in a new v1 production; the Parent validates and assembles frozen Builder media directly.253
  4. 5092Broll Hybrid Rendererduo1998-cell/erduo-broll-loop-engineeringRead and verify legacy hybrid Render records for a pre-v0.9 task. Never dispatch this stage in a new v1 production; the Parent runs deterministic preview and delivery scripts.253
  5. 5093Broll Master Builderduo1998-cell/erduo-broll-loop-engineeringBuild three HyperFrames representative samples and shared creative capabilities as Lead, or own the complete design-build-view-revise loop for one contiguous 5–8-shot chapter.253
  6. 5094Broll Master Integrateerduo1998-cell/erduo-broll-loop-engineeringRead and verify legacy HyperFrames Integrator records for a pre-v0.9 task. Never dispatch this stage in a new v1 production; the Parent assembles verified Builder media directly.253
  7. 5095Broll Onboardingerduo1998-cell/erduo-broll-loop-engineeringDiagnose and repair installation readiness only when the cached first-run evidence is missing or a real machine/tool fact changed.253
  8. 5096Broll Remotion Builderduo1998-cell/erduo-broll-loop-engineeringBuild explicit Remotion canary representative samples as Lead, or own one explicitly assigned contiguous chapter through design, deterministic Composition authoring, viewing, and revision.253
  9. 5097Broll Remotion Integrateerduo1998-cell/erduo-broll-loop-engineeringRead and verify legacy Remotion Integrator records for a pre-v0.9 task. Never dispatch this stage in a new v1 production; the Parent assembles verified Builder media directly.253
  10. 5098Broll Remotion Rendererduo1998-cell/erduo-broll-loop-engineeringRead and verify legacy Remotion Render records for a pre-v0.9 task. Never dispatch this stage in a new v1 production; the Parent runs deterministic preview and delivery scripts.253
  11. 5099Broll Rendererduo1998-cell/erduo-broll-loop-engineeringRead and verify legacy HyperFrames Render records for a pre-v0.9 task. Never dispatch this stage in a new v1 production; the Parent runs deterministic preview and delivery scripts.253
  12. 5100Broll Runtime Planerduo1998-cell/erduo-broll-loop-engineeringRead and verify legacy Runtime Planner handoffs from production records created before v0.9. Do not use or dispatch this stage in the normal v1 workflow; the Parent runs deterministic planning and assignment gates directly.253
  13. 5101Broll Shot Exporterduo1998-cell/erduo-broll-loop-engineeringLegacy compatibility export for requested windows from a verified pre-v1.0.1 Master. Do not use for new shot-native productions.253
  14. 5102Build Figma Librarysuperhero-tech/superhero-skillsBuild or extend a Figma token and component library from product documentation, code, or an existing UI. Prepare it for another agent by checking component properties, composition examples, and handoff, including publishing when reuse spans files. Use for reconstructing design systems and making libraries reusable; screen-only design and documentation of existing components have separate workflows.298
  15. 5103Capability EvaluationLanqiao-Luca/ai-java-workflow在固定任务与明确标签下对照能力策略,记录正确率、漏检、误报、脚本纠正与耗时;不把微型离线实验当真实模型或工程收益。339
  16. 5104Cc Cost Analysisintercom/2x-skillsAnalyze Claude Code usage costs from OpenTelemetry data — per-user spend, expensive sessions, context bloat, and model/token cost breakdowns — with a structured framework, ready-to-use query shapes, and cost-model formulas. Triggers on "analyze Claude Code costs", "break down the Claude Code bill", "find expensive sessions", "identify context bloat".280
  17. 5105Code Event Stormingsuperhero-tech/superhero-skillsReconstruct an EventStorming board from business behavior evidenced in an existing codebase. Use to map current processes, commands, domain events, read models, and open questions in a self-contained HTML board.298
  18. 5106Code ImplementationLanqiao-Luca/ai-java-workflow将已确认需求适配为最小代码候选、行为保留映射与可复核证据;用于功能开发、修复或受控重构,不自动发布。339
  19. 5107Conclusion ChallengeLanqiao-Luca/ai-java-workflow复核已形成的高影响技术根因或修复判断,组织竞争解释、共同证据矩阵、主动反证和敏感性分析;不因普通格式质疑触发,不自动取证或改业务。339
  20. 5108Create PRintercom/2x-skillsOpen or update a GitHub pull request for the current branch — use when asked to create a PR, open a pull request, push and PR, or submit a PR.280
  21. 5109Customer Researchsuperhero-tech/superhero-skillsUse when researching customer experiences published online about a product, service, or problem, using reviews, comments, or community discussions.298
  22. 5110Data Analysissuperhero-tech/superhero-skillsGuide a full data-analyst workflow from business question to recommendation. Use when the user says "analyze this data/CSV", wants EDA on a fresh dataset, asks to find patterns in this dataset (segmentation, cohorts, correlations), or wants SQL queries over files or databases via DuckDB.298
  23. 5111Desk Researchsuperhero-tech/superhero-skillsUse when the user wants desk research, a literature review, competitive evidence, or to test a hypothesis. Search live sources, challenge assumptions, and explain what the evidence means in a concise report with a separate evidence file.298
  24. 5112Docker Build IsolationLanqiao-Luca/ai-java-workflow显式选择Docker构建后端,核白名单输入、容器限制、候选身份与资源停止,不继承私人Docker状态。339
  25. 5113Document Design System Componentssuperhero-tech/superhero-skillsTwórz dokumentację komponentów design systemu dla designerów na podstawie dokumentacji wizualnej istniejącego projektu strony: zrzutów ekranów, makiet, plansz lub specyfikacji wizualnej. Analizuj widoczne warianty, właściwości, anatomię, tokeny, odległości, typografię, zastosowania i dostępność. Pokaż pełny wynik do oceny. Używaj przy dokumentowaniu istniejącego interfejsu. Po ukończeniu dokumentacji dla designerów zaproponuj opcjonalny pakiet dla agenta: design.md, style lub komponenty oraz przykłady użycia; przygotuj go po zgodzie.298
  26. 5114Document MaintenanceLanqiao-Luca/ai-java-workflow在已确认写集内创建和更新本地 Markdown,核目的、适用对象、原件保全与接续;不负责业务事实判定、外部发布或自动清理。339
  27. 5115Erduo Broll Loop Engineeringerduo1998-cell/erduo-broll-loop-engineeringTurn original SRT and design into editable B-roll through an independent Director, focused chapter creators, and visual review. Use for SRT-to-video production or revisions; preserve existing legacy projects and explicit Remotion choices.253
  28. 5116Evidence CollectionLanqiao-Luca/ai-java-workflow在明确来源许可与质量目标下取得事实或核页观察覆盖,区分sample、complete、零命中和缺证;不提供真实服务连接器或业务写入。339
  29. 5117Experiment Designsuperhero-tech/superhero-skillsDesign concrete assumption tests using prototypes, demand tests or commitment tests. Use when turning research or selected ideas into experiments, comparing test methods or revising an experiment plan.298
  30. 5118Extract Design Mdsuperhero-tech/superhero-skillsInspect the rendered style of supplied website URLs and create an evidence-backed DESIGN.md for building matching prototypes. Use for extracting a site's visual language, design tokens, typography, or component styling; not for implementing or redesigning the site.298
  31. 5119Five Whysintercom/2x-skillsRun an evidence-grounded five-whys RCA: claims verified by fact-checker subagents, causal links stress-tested by a cynic subagent. For internal RCAs, post-mortems, "why did this happen". Not for customer-facing incident write-ups.280
  32. 5120Fix Flaky Testsintercom/2x-skillsInvestigate and fix flaky or intermittently-failing tests in any framework and CI system — detects the framework, CI provider, and app profile, then applies the matching classification and fix patterns. Triggers on a flaky-test issue or CI URL, a test that "passes on retry" or "fails in CI but passes locally", a bot that skipped a test, or a request to reopen or dispute the closure or diagnosis of a flaky-test issue (for that case open the issue first; its title or label confirms scope even when the prompt has no flaky-test keywords).280
  33. 5121Interview Plansuperhero-tech/superhero-skillsTurn a brief, data, or desk research into a customer interview plan: research questions, screener, guide, and a note format. Use when someone is about to talk to customers and needs to decide who to recruit, what to ask, and when to stop.298
  34. 5122Interview Simulatorsuperhero-tech/superhero-skillsPractice customer research interviews with a realistic fictional persona and receive evidence-based feedback on interviewing skills. Use for mock interviews, synthetic-user roleplay, or interview training; use interview-plan to prepare a research guide.298
  35. 5123Lightweight Charts React Componentsukorvl/lightweight-charts-react-componentslightweight-charts-react-components recipes for TradingView lightweight-charts in React. Candlestick, line, and area series; volume and indicator panes; realtime WebSocket updates; infinite history on scroll; crosshair OHLC legends and tooltips; trade markers and price lines; compare multiple instruments by percentage return; synchronized charts; numeric options and yield-curve axes. Use when adding or fixing a financial or trading chart in a React app, or when the user mentions lightweight-charts, TradingView charts in React, or this package.140
  36. 5124Paymentsecond-state/payment-skillRequest and receive payments. Use this skill when you need to request payment from another party. It will generate a payment link that you can send out. Through the payment link, you can also monitor the status of the payment.220
  37. 5125Permissions Analyzerintercom/2x-skillsVet a Claude Code permission allowlist against a GREEN/YELLOW/RED safety model and reduce permission prompts. Runs on top of the built-in /fewer-permission-prompts scan (and permission auto mode): filters proposed auto-allow commands through a GREEN/YELLOW/RED safety model — never auto-allowing interpreters or package-manager executors — before merging the safe ones into ~/.claude/settings.json. Also turns the proactive "reduce your prompts" suggestions off or on (disable/enable).280
  38. 5126Poster People UIsuperhero-tech/superhero-skillsBuild or extend screens in a poster-like visual direction with crisp black contours, paper surfaces, pink accents, and expressive hand-drawn people. Use when this direction or a Gumroad-meets-illustrated-people style is requested for a job board, marketplace, directory, or adjacent product screen.298
  39. 5127Pres Prioritizationsuperhero-tech/superhero-skillsPrioritize product opportunities using Pain, Reach, Evidence and Strategic fit. Use when comparing user needs or problems, scoring opportunities with PRES, or reviewing an opportunity ranking; not for ranking solutions or experiments.298
  40. 5128Production Readinesssuperhero-tech/superhero-skillsGuide users through preparing a web app or API for production, verifying its deployment and observing real use. Create an offline HTML checklist with separate stage ratings, environment-specific evidence and blockers, and implement agreed local fixes.298
  41. 5129Release Managerukorvl/lightweight-charts-react-componentsRelease lightweight-charts-react-components end to end. Invoke as `/release-manager <major|minor|patch>`; with no argument on a `release-vX.Y.Z` branch it resumes that release.140
  42. 5130Rolecraftrolecraft-sh/rolecraftInstall AI agent skills as roles & behaviors from any source — local folder, GitHub, GitLab, SSH git URL. Zero-dependency CLI with 90 agent targets (65 verified).99
  43. 5131Secure Github Actionsintercom/2x-skillsHarden GitHub Actions workflows against supply-chain and injection attacks when creating, modifying, or reviewing a `.github/workflows/*.yml` file. Skip for unrelated CI work (other CI providers, test harnesses, dependency pinning) that does not touch a workflow YAML.280
  44. 5132Skill Reviewintercom/2x-skillsReview Claude Code skills against substantive quality standards — an 8-category rubric with JSON output, single-pass full-rubric review, and a determinism contract. Complements Anthropic's `plugin-dev:skill-reviewer` (structural checks). Use for: "review a skill", "check skill quality", "does this skill need evals", "review skill quality".280
  45. 5133Super Landing Pagesuperhero-tech/superhero-skillsUse when building a distinctive landing page through a guided interview, independent art direction, a detailed execution prompt, and visual iteration. Preserve ambitious composition and motion for the chosen direction. Not for routine code fixes or prompt analysis alone.298
  46. 5134Supersentencesuperhero-tech/superhero-skillsUse when someone wants to discover or clarify a business idea through a compact interview and market research, ending with a super sentence about the customer change and chosen mechanism.298
  47. 5135Supersprintsuperhero-tech/superhero-skillsRun Supersprint from product context to an evidence-supported decision, routing specialists and showing a growing discovery tree. Use when starting, resuming or reviewing a Supersprint cycle.298
  48. 5136Swiftui Skillsameyalambat128/swiftui-skillsApple-authored SwiftUI and platform guidance extracted from Xcode. Helps AI agents write idiomatic, Apple-native SwiftUI with reduced hallucinations.126