Most popular Claude skills · page 254

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 12145–12192

  1. 12145TeleportHmbown/Wizards-of-the-GhostsTeleport is FULL-CONTEXT migration, not partial transformation. The defining characteristic is that EVERYTHING must move together and keep working: data, dependencies, auth, traffic routing, background jobs, secrets, and human workflows. The old system must remain recoverable until the new one is proven. This spell IS: Database migrations (RDS→Cloud SQL, self-managed→Atlas), cloud provider moves (on-prem→AWS, Heroku→K8s), environment promotions (staging→prod), account/tenant consolidations, platform migrations (Jenkins→GitHub Actions, SendGrid→SES), identity migrations (AD→Azure AD), cluster u113
  2. 12146Teleportation CircleHmbown/Wizards-of-the-GhostsUse this spell when you need a permanent, reliable portal between two environments — a CI/CD pipeline, a standing data sync, a repeatable deployment, or a migration path you will use more than once.113
  3. 12147Test All Devicehw-native-sys/simplerRun the full hardware (onboard) CI pipeline (examples + tests/st) with automatic platform and device detection. Use when the user asks to run all device/hardware tests or the full onboard CI locally.49
  4. 12148Test All Simhw-native-sys/simplerRun the full simulation CI pipeline (examples + tests/st) on a2a3sim/a5sim. Use when the user asks to run all sim tests or the full simulation CI locally.49
  5. 12149Test Example Devicehw-native-sys/simplerRun the hardware (onboard) device test for a single example/scene-test directory ($ARGUMENTS). Use when the user asks to run or onboard one example on real hardware.49
  6. 12150Test Example Simhw-native-sys/simplerRun the simulation test for a single example/scene-test directory ($ARGUMENTS). Use when the user asks to run one example in simulation.49
  7. 12151Test Runtime Devicehw-native-sys/simplerRun hardware (onboard) device tests for one runtime ($ARGUMENTS — host_build_graph or tensormap_and_ringbuffer). Use when the user asks to onboard or test a single runtime on real hardware.49
  8. 12152Test Runtime Simhw-native-sys/simplerRun simulation tests for one runtime ($ARGUMENTS — host_build_graph or tensormap_and_ringbuffer). Use when the user asks to test a single runtime in simulation.49
  9. 12153Testinghw-native-sys/simplerTesting guide and pre-commit testing strategy for simpler. Use when running tests, adding tests, or deciding what to test before committing.49
  10. 12154ThunderwaveHmbown/Wizards-of-the-GhostsUse this skill for intentionally theatrical or forceful actions, but only behind explicit confirmation and a hard safety boundary.113
  11. 12155Tile Picking Interaction0xheycat/isometric-game-skillsUse when converting a mouse/touch position into the correct isometric tile for selection, highlighting, and placement.49
  12. 12156Tilemap Data Format0xheycat/isometric-game-skillsUse when designing the map data format (layers, tiles, objects, metadata) so maps are editable, versionable, and engine-agnostic.49
  13. 12157Tlaplus Add Variabletlaplus/AgentSkillsAdd a new variable to an existing TLA+ specification without changing its semantics. Ensures the variable is declared, initialized, and added to all UNCHANGED statements. Use when the user asks to add, introduce, or declare a new variable in a TLA+ spec, or mentions UNCHANGED statements.49
  14. 12158Tlaplus From Sourcetlaplus/AgentSkillsGenerate a high-level TLA+ model from source code (C, C++, Rust, etc.). Analyzes code to understand its purpose, creates abstractions, writes TLA+ specification, and proposes invariants and properties. Use when the user wants to model source code in TLA+, create a formal specification from implementation, or verify concurrent/distributed algorithms.49
  15. 12159Tlaplus Split Actiontlaplus/AgentSkillsSplit a TLA+ action into two sequential actions by introducing a new program counter (pc) state. Handles pc variable updates, UNCHANGED statements, TypeOk predicates, and follows naming conventions with renumbering. Use when the user asks to split, divide, or break an action into two parts, or wants to add an intermediate step to an action sequence.49
  16. 12160TonguesHmbown/Wizards-of-the-GhostsTongues is universal translation across languages, formats, and protocols. It can mean English to Spanish, JSON to XML, REST to GraphQL, Python to JavaScript, or one team's business vocabulary to another team's schema. The spell is not just about swapping tokens. It is about preserving meaning while crossing into a different representation. Good Tongues work makes both sides feel native. Bad Tongues work creates a smooth-looking mistranslation that fails at the edges.113
  17. 12161Transparent Cutout Cleanup0xheycat/isometric-game-skillsUse when removing backgrounds from generated sprites to get clean alpha edges with no halo, fringe, or leftover background pixels.49
  18. 12162Triagelllyys/vreaderClassify and route incoming issues to the correct tracker (bugs vs features). Use this skill whenever the user reports a problem, describes unexpected behavior, asks you to triage, process the inbox, check tasks, or pastes an error/crash log. Also trigger when the user says things like 'this is broken', 'I found a bug', 'X doesn't work', 'add support for Y', or describes any issue that needs classification. Even casual complaints like 'the reader crashes when I open big files' should trigger this skill.49
  19. 12163True PolymorphHmbown/Wizards-of-the-GhostsIn D&D, True Polymorph is the permanent transformation — the target becomes something fundamentally different, and if held long enough, the change is irreversible. Unlike Polymorph (temporary disguise or adaptation), True Polymorph means the old identity is gone. The real-world version is irreversible system transformation: rewriting a service from Python to Rust so thoroughly the Python version cannot be recovered, migrating from SQL to a graph database with no backward-compatible schema, or restructuring an organization so completely that the old org chart is not just outdated but nonsensica113
  20. 12164True SeeingHmbown/Wizards-of-the-GhostsUse this spell when the surface presentation is misleading and you need to see what is actually there — beneath the marketing, the abstractions, the outdated docs, or the complexity.113
  21. 12165True StrikeHmbown/Wizards-of-the-GhostsUse this spell for preflight certainty: dry runs, validation checks, dependency verification, and rehearsals that make the next deploy, query, or command much more likely to succeed. It trades a little time up front for fewer blind swings and fewer expensive misses.113
  22. 12166Unseen ServantHmbown/Wizards-of-the-GhostsUse this spell when you need a tireless helper that organizes, tidies, triages, and maintains without requiring your constant attention.113
  23. 12167Using Isometric Skills0xheycat/isometric-game-skillsUse when starting ANY isometric game task to route the request to the correct specialized skill before writing code or generating art.49
  24. 12168Verifylllyys/vreaderRun a verification iteration — pick something that needs verifying, verify it CU-free, and complete its gate. Use this skill whenever the user wants to verify a shipped feature or bug fix, asks 'verify feature #N', 'verify bug #N', 'run device verification', 'work the verification backlog', or 'close the awaiting-device-verification issues' — and whenever the verify cron fires. Covers BOTH bug close-gate verification (awaiting-device-verification GH issues → closed) and feature Gate-5 verification (docs/features.md DONE → VERIFIED). Verification-only: files bugs, never fixes them; fix work bel49
  25. 12169Vicious MockeryHmbown/Wizards-of-the-GhostsThe bard's cantrip that deals psychic damage through insults. In practice this is adversarial review — the art of finding and articulating exactly what is wrong with something in a way that is impossible to ignore. Unlike polite feedback that gets filed and forgotten, vicious mockery lands. It is the red-team report that makes the PM cancel the launch, the code review that makes the author delete the PR, the roast that makes the founder pivot. The damage is the point.113
  26. 12170Vote PredictYrzhe/claude-skillsPredict how a target population would vote, respond to a policy, or react to a political message. Use when the user wants a distribution (not a winner-take-all answer) across demographic segments, with calibration disclaimers. Triggers on 投票预测, 民意模拟, policy response, 政策反应, 选举模拟, 民意分布, 某群体怎么看.65
  27. 12171Weekly Changeloghw-native-sys/simplerSummarize user-facing changes merged in the current Friday-anchored week (most recent Friday up through yesterday) in the simpler repo into a markdown changelog with before/after code examples. Also emits a full all-PR inventory (WEEKLY_ALL_PRS) and Chinese (_zh) translations of both docs. Use when the user asks for a weekly changelog, weekly summary, or weekly external changes report.49
  28. 12172Youtube Data APIYrzhe/claude-skillsYouTube Data API v3 complete wrapper - search videos, get video/channel/playlist details, get comments, download subtitles, etc. Supports filtering and sorting by time/views/rating and more.65
  29. 12173Zone of TruthHmbown/Wizards-of-the-GhostsEnter a mode where every assertion is backed by evidence, confidence is calibrated, speculation is flagged, and hallucination is actively resisted.113
  30. 12174AI Factory Operations Agent HeadlessNVIDIA/AI-Factory-Operations-AgentUse AI Factory Operations Agent without opening the browser UI. Invoke it through the headless HTTP API, packaged CLI, or stdio MCP server, and deploy it first when no service is available.43
  31. 12175BcmNVIDIA/AI-Factory-Operations-AgentInspect Base Command Manager (BCM) inventory and health evidence, and make explicitly requested changes when Base Command Manager edit mode is enabled.43
  32. 12176Checklist Decisionkangarooking/poor-charlies-almanack-skill当用户面临重要决策且需要系统化排查遗漏、用户过度自信于自己的经验/判断力、用户是领域专家但正在处理复杂或高风险情境、或用户需要将自己的思维模型编排为可重复的决策流程时激活。典型触发信号:用户说"我很有经验,不需要清单";用户在高压环境下做决策;用户承认"事后发现遗漏了关键因素"。不适用于简单、低风险的日常小决策或纯创意/探索性思考。49
  33. 12177Circle of Competencekangarooking/poor-charlies-almanack-skill当用户考虑进入自己不熟悉的领域做决策,或需要判断自己是否真正"理解"某件事时激活。典型触发信号:用户说"我可以学""应该差不多""这个不难"但缺乏相关领域的深度经验。不适用于用户已在领域内有长期成功记录且正在圈内行动的场景,也不适用于需要冒险试错才能拓展边界的早期探索阶段。49
  34. 12178Clawguard AuditorSafeAgent-Beihang/clawguardClawGuard v3 Auditor - 企业级 Skill 安全审计器,支持意图偏离检测、SAST、供应链安全、ML 异常检测。当用户要求审计、检测、安装前检查一个 Skill 的安全性时触发。49
  35. 12179Clawguard GuardianSafeAgent-Beihang/clawguardClawGuard Guardian v3 - Runtime guardian with behavior monitoring, interception, session freeze/replay, and emergency response49
  36. 12180Clawguard Security CheckerSafeAgent-Beihang/clawguardClawGuard Security Checker v3 - Advanced configuration analysis, runtime integrity verification, permission modeling, and one-click hardening recommendations49
  37. 12181Clawguard Self Improving SafetySafeAgent-Beihang/clawguardSelf-improving safety module that proactively learns and enforces safety constraints. Works as a standalone firewall or integrates with ClawGuard Detect for automated learning.49
  38. 12182Clawguard ShieldSafeAgent-Beihang/clawguardClawGuard Shield v3 - Active defense with prompt injection detection, intent validation, zero-width character detection, and intent integrity verification49
  39. 12183Clawguard Threat DetectSafeAgent-Beihang/clawguardClawGuard Threat Detector - Real-time behavioral monitoring, attack pattern detection, MITRE ATT&CK mapping, and AI-powered anomaly detection for OpenClaw runtime environments49
  40. 12184Connect (500+ Apps)ArogyaReddy/ComposioHQ-awesome-claude-skillsConnect Claude to 500+ apps including Gmail, Slack, GitHub, Notion, and more. Send emails, create issues, post messages, and automate workflows across platforms.52
  41. 12185Connect AppsArogyaReddy/ComposioHQ-awesome-claude-skillsConnect Claude to external apps like Gmail, Slack, GitHub. Use this skill when the user wants to send emails, create issues, post messages, or take actions in external services.52
  42. 12186Darwinian Objectivitykangarooking/poor-charlies-almanack-skill当用户已形成强烈观点或理论,需要检验其可靠性时调用。典型触发信号:确认偏见、只看支持性证据、对新证据本能排斥、"我觉得这肯定是对的"、需要做重大判断前的自我审查。不适用于需要快速决策的紧急场景,也不适用于纯信息收集阶段(尚无观点时不需要证伪)。49
  43. 12187Deprival Superreactionkangarooking/poor-charlies-almanack-skill当用户因失去(或即将失去)某样东西而做出不成比例的激烈反应,或在损失后急于"扳平"、无法止损时调用。典型触发信号:沉没成本陷阱、赌徒式加注、拍卖中的非理性竞价、无法放弃已投入大量资源的失败项目。不适用于一般的投资估值(用 value-assessment)或从众行为(用 misjudgment-checklist)。49
  44. 12188Dual Track Analysiskangarooking/poor-charlies-almanack-skill当用户在做重要决策时需要同时检查"理性分析是否正确"和"我的判断是否被认知偏差扭曲"时激活。典型触发信号:用户的分析逻辑严密但直觉不安,或者分析过于顺畅似乎"毫无破绽"。不适用于纯技术问题(如代码调试、数学计算)中不存在人类判断偏差的场景,也不适用于纯情感/人际关系问题中理性轨道不相关的场景。49
  45. 12189Enrich Notebholmesdev/llm-knowledge-base-skillsEnrich a single note with topic tags, source attribution, and links to related notes. Use when asked to enrich, tag, or add metadata to a note.47
  46. 12190Enrich Notes Loopbholmesdev/llm-knowledge-base-skillsEnrich every un-enriched note in the vault by running enrich-note over each one. Use to bulk-enrich the vault or auto-tag notes unattended ("while I sleep").47
  47. 12191Enrich Notes Loop Cloudbholmesdev/llm-knowledge-base-skillsRun enrich-notes-loop unattended in a cloud sandbox against an Obsidian Sync vault, syncing before and after. Use for scheduled cloud runs.47
  48. 12192Game Accessibility SpecialistAlterLab-IEU/AlterLab_GameForgeAccessibility Specialist (Kael Oduya). Designs motor, visual, auditory and cognitive accommodations, runs accessibility audits, scopes the European Accessibility Act, CVAA and Game Accessibility Guidelines, and maps fixes to Godot, Unity, Unreal or web. Use for "accessibility audit", "EAA", "colorblind", "subtitles", "remapping". Not for general UX flows (use game-ux-designer).57