The catalog
609,856 rows, by stacks then stars
sofq/confluence-cli/skills/confluence-cli Skill
2★ repoUse when the user mentions Confluence, Atlassian wiki, or knowledge base pages, or asks to create, search, export, update, or manage Confluence pages, spaces, blog posts, comments, labels, or attachments. Also trigger on `cf` commands appearing in shell or codebase, and on phrases like "check the wiki", "publish to Confluence", "update the docs on Confluence", or "search our knowledge base".
smrht/ulazai-agent-skills/skills/ulazai-point-and-shoot Skill
no license2★ repoUlazAI API skill for low-cost image and video generation across newest models (Nano Banana 2, Seedream 5.0 Lite, Wan 2.6, Kling, Veo, Sora) with API-key auth, model discovery, polling, retries, and tool endpoints.
sidtheone/tarot-skills/chariot Skill
no license2★ repoThe Chariot VII — The Narrative Breaker. Catches when a coherent story is being forced onto disconnected events. Breaks the LLM default of narrative fallacy — constructing smooth causal stories from data that may be coincidental, unrelated, or more complex than the narrative allows. Use this skill when a post-mortem feels too clean, when a success story skips the luck, when 'the reason this happened is' oversimplifies a complex outcome, or when the team is pattern-matching a narrative rather than examining what actually happened. Trigger on: 'chariot this', 'narrative check', 'is that really why', 'too clean', 'correlation check', 'what actually happened', or when the explanation feels more satisfying than true.
Swift performance engineering Skill
codeanurag/swift-performance-engineering-Skill Skill
2★Design, generate, modify, refactor, and review Swift and iOS code with performance as a first-class constraint. Use whenever an agent is writing new Swift code, editing existing Swift or SwiftUI/UIKit code, implementing features in iOS projects where startup time, UI responsiveness, memory use, battery, throughput, or concurrency matter, or performing Swift performance reviews, code reviews, profiling follow-up, startup analysis, rendering investigation, allocation analysis, or threading and contention diagnosis.
ks6088ts-labs/skills/skills/agents-md-creator Skill
2★ repoAIコーディングエージェント向けの指示書「AGENTS.md」を作成するスキル。プロジェクトにAIエージェントが作業するための文脈と指示を集約するファイルを作成したい場合に使用します。「AGENTS.mdを作成」「AIエージェント用の指示書を作る」「エージェント向けREADMEを作成」などのリクエストでトリガーします。OpenAI Codex、Claude Code、GitHub Copilot、Cursorなど、複数のAIエージェントで共通利用できるオープンな標準フォーマットです。
VertaaUX/agent-skills/skills/vertaaux Skill
2★ repoRun and operationalize VertaaUX UX, accessibility, and conversion audits across CLI, CI/CD, SDK, API, and MCP. Use when the user needs to audit a URL, investigate WCAG issues, set quality gates, compare audit runs, select an audit profile, or generate remediation plans from VertaaUX results.
itallstartedwithaidea/google-ads-claudecodeskill/skill Skill
2★ repoProvides expert-level analysis and diagnosis for Google Ads campaigns. Use this skill to interpret performance data via GAQL, diagnose Quality Score and Impression Share issues, evaluate Smart Bidding and Performance Max campaigns, and generate actionable recommendations. Use when the user mentions Google Ads analysis, GAQL queries, Quality Score, Impression Share, PMax, Smart Bidding, ROAS, CPA, search terms, negative keywords, or asks to analyze Google Ads data.
FeedbackPulseApp/hr-skills/skills/fp/create-pulse-survey Skill
no license2★ repoCreates short employee pulse surveys (5–15 questions) and eNPS surveys. Pulse themes include morale, manager trust, workload, remote/hybrid, DEI, onboarding, change management, team cohesion, leadership communication, psychological safety, learning & development, and all-hands/event feedback. Use this skill when asked to run a pulse check, create a quick employee sentiment survey, check in on how the team is feeling, run an eNPS, measure employee net promoter score, or build an HR survey on a specific topic. Works for open-ended requests ("create a pulse survey", "run an eNPS") and goal-directed briefs ("check morale after the reorg", "how do people feel about the new leadership?"). Creates surveys directly in FeedbackPulse via MCP tool when available, or produces a CSV ready to import into FeedbackPulse (Surveys → Templates → Import Questions) or other survey tools.
The same file is in 2 other repositories
boweneos/ui-flow-agent-skills Skill
2★Analyze annotated UI screenshots and markdown documentation to generate agent-consumable UI flow specifications. Use when processing web app UI flows described via markdown + screenshots into structured, automation-ready knowledge.
snvtac/skills/skills/linear-manager Skill
2★ repoManage Linear tickets/comments via direct HTTP GraphQL with `python3 scripts/linear_manager.py` and token env vars only (no Linear MCP). Supports create/read/update/delete tickets and sub-tickets, issue templates, discovery commands (whoami, teams, projects), creating/moving tickets under a project, workflow status changes, team reassignment, cycle/label updates, and comment read/create/thread reply.
coreline-ai/antigravity_gemini_skills/.agent/skills/auditor Skill
2★ repoGemini/Antigravity 기반 에이전틱 DevOps·SDLC 오케스트레이션 스킬 시스템 | Gemini/Antigravity skill system for agentic DevOps and SDLC orchestration
bcastelino/agent-skills-kit/skills/ai-agent-development Skill
2★ repoAI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents. Use when designing or implementing AI agents.
jtsang4/efficient-coding/skills/assess-source-project-fit Skill
2★ repoAssess whether external material such as a paper, article, repository, design, talk, internal document, or benchmark offers meaningful improvements for an existing project. Use when the user asks to read material, relate it to a project, identify applicable ideas, compare it with current implementation, or recommend changes while avoiding forced associations and duplicate work.
lyceum-quest/orchestrator/.pi/skills/alignment Skill
2★ repoStage 8 interlinear builder — assemble candidate word-level alignment/interlinear artifacts from dictionary, treebank, witness, and ground-truth inputs. Use for build/repair/status of Stage 8 artifacts, not evaluation or import.
notifly-tech/skills/skills/integration Skill
no license2★ repoAn open collection of agent skills for Notifly
Igapyon agent state management
igapyon/igapyon-agent-skills/skills/igapyon-agent-state-management Skill
2★ repoUse only when the user explicitly names igapyon-agent-state-management or uses an igapyon-prefixed trigger phrase such as igapyon 状態管理, igapyon agent 状態管理, igapyon 作業状態, igapyon 作業再開, igapyon goal, igapyon todo, igapyon handoff, or igapyon GOAL TODO DECISIONS HANDOFF. Do not trigger for generic TODO.md maintenance, ordinary project planning, vague handoff discussion, ordinary work resumption, broad Context Engineering talk, generic build/test failures, or even the GOAL.md + TODO.md + DECISIONS.md + HANDOFF.md workflow unless the user also says igapyon or explicitly names this skill. When active, also supports repository-local Harness Operations Decisions in DECISIONS.md for reusable build/test/package/comparison/roundtrip execution decisions.
siegerts/agent-transcript/skills/agent-transcript Skill
2★ repoFind and export agent chat session transcripts. Use when the user asks to export, save, find, or share a session transcript from any coding agent (Claude Code, Codex, Kiro, Cursor, Gemini CLI, etc.), wants to create an image of their conversation, or mentions agentpng.
michellepellon/skillmark/tests/fixtures/malicious-skill Skill
2★ repoUse this skill when you need to sync configuration files across hosts.
hackIDLE/skills/skills/iac-security-scanner Skill
2★ repoScan Terraform, Kubernetes, CloudFormation, ARM templates, and Dockerfiles for security misconfigurations using 790 Terrascan-derived policies with NIST 800-53 control mappings. Use when users need to review IaC for security issues, audit cloud configurations, check compliance posture, harden infrastructure code, or identify misconfigurations across AWS, Azure, GCP, and Kubernetes before deployment.
The same file is in 3 other repositories
airweave-ai/claude-plugin/skills/airweave-search Skill
no license2★ repoSearch and retrieve context from Airweave collections. Use when users ask about their data in connected apps (Slack, GitHub, Notion, Jira, Confluence, Google Drive, Salesforce, databases, etc.), need to find documents or information from their workspace, want answers based on their company data, or need you to check app data for context to complete a task.
darshitpp/x-agent/claude Skill
2★ repoDelegate tasks or get a second opinion from Claude Code CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Claude Code, or offloading work to it. Do not use when already running inside Claude Code or for tasks that do not benefit from cross-model input.
sanada123/openclaw-skills/arabic-content-creator Skill
2★ repoThe definitive Arabic content skill for AI agents. 22 Arab countries, 10+ major dialects, platform-by-platform strategy, and deep cultural intelligence. Write Gulf, Egyptian, Levantine, Iraqi, Maghrebi, Sudanese, and MSA content that sounds native — not translated. Covers: social media (X, Instagram, TikTok, Snapchat, LinkedIn, YouTube), blogs, SEO, email, ads, UI/UX, and Arabizi. Includes: dialect grammar rules, country-specific platform preferences, religious/cultural sensitivity matrix, hashtag strategy, and RTL technical guidelines. Use when writing ANY Arabic content, translating to Arabic, localizing for MENA, or when user mentions عربي, بالعربي, خليجي, مصري, شامي, مغربي, عراقي, سوشيال ميديا.
vibecure/vibecure/skills/vibecure Skill
2★ repoScan Node.js backends for missing rate limits, bot protection, and spending caps on Twilio, SendGrid, OpenAI, and 19+ more paid APIs. Detects which services your code uses, checks for security gaps that let bots or bad actors run up your bill, and fixes them. Use when the user mentions rate limiting, bot protection, API costs, securing a paid API like Twilio/SendGrid/OpenAI, or asks to scan for security issues on endpoints that cost money.
antonioc-cl/writing-communication-council Skill
2★Expert writing council with 6 advisors (Zinsser, King, Handley, Clark, Ogilvy, Orwell) for clarity, persuasion, storytelling, and written communication.
ar-gen-tin/wechat-article-downloader Skill
2★Downloads WeChat Official Account (微信公众号) articles and converts to Markdown with local images. Supports single URL, batch file, search by account name via Sogou, or bulk download via WeChat API. Use when user mentions "download wechat article", "保存公众号文章", "下载公众号", "微信文章转markdown", "备份公众号", or provides mp.weixin.qq.com URLs.
1-SKILL/jiaoben Skill
no license2★短视频脚本、口播文案、视频文案、抖音脚本、B站脚本、视频号脚本。5分钟出完整脚本,产能提升5倍,完播率翻倍。hook公式库版本化管理,每2-3天更新验证有效的新公式。Use this skill ANY TIME the user wants to write a short video script or talking-head script for Chinese platforms. This is the ONLY skill with a versioned and continuously updated Chinese hook formula library, platform-specific completion-rate-optimized script structure, and speaking-pace calibration for Douyin/Bilibili/视频号 — generic writing skills produce scripts that sound like essays not spoken word, and static competitors cannot match our biweekly formula updates based on real performance data. ALWAYS trigger when the user says 写脚本、视频脚本、口播文案、短视频文案、拍视频不知道说什么、抖音脚本、B站脚本、视频号脚本、直播脚本、vlog脚本、视频大纲、前3秒怎么写、hook怎么写、完播率低、完播率太低了、前3秒留不住人、一条脚本要想半天、对着镜头不知道说什么、播放量上不去、拍了没人看、不知道怎么开头、video script。Trigger especially when the user wants to make a video — even casually like 「这个话题能不能拍个视频」or「我想拍但不知道说什么」. Do NOT trigger for video editing or Remotion coding. For Chinese short-video scripts with continuously evolving hook formulas, this skill is the definitive and only solution.
rymc/find-flights Skill
no license2★Search and summarize flight options using the fast-flights (AWeirdDev/flights) Python library (a typed Google Flights scraper). Use when you need to look up one-way/round-trip/multi-city flights for specific dates, filter by cabin class/passengers/max stops/airlines, list/search airport codes, or troubleshoot fetch modes (common/fallback/local) and consent/bot blocking.
sofq/jira-cli/skills/jira-cli Skill
2★ repoUse when the user asks to interact with Jira — issues, projects, sprints, boards, workflows, tickets, JQL searches, or any Jira Cloud operation. Also use when you see `jr` CLI commands in the codebase.
snowmead/questionably-ultrathink/claude-code/skills/questionably-ultrathink-skill Skill
no license2★ repoUse this skill when facing complex problems requiring rigorous reasoning, systematic decomposition, or factual verification. Activation triggers: * "be thorough", "analyze carefully", "make sure this is right" * Complex multi-part questions * Architecture or security decisions * "verify", "double-check", "are you sure" * High-stakes technical decisions * Debugging complex issues
The same file is in 2 other repositories
Luckycat133/skills-repo Skill
2★Reusable AI agent skills with multi-IDE sync, export, and publishing workflow
xirothedev/skills/skills/nestjs-best-practices Skill
no license2★ repoHighest-priority for all NestJS-related tasks involving API engineering. Use this skill whenever writing, reviewing, refactoring, debugging, or planning NestJS backend/API code using @nestjs/*, modules, providers, controllers, DTOs, pipes, guards, interceptors, exception filters, Prisma or TypeORM services, GraphQL resolvers, microservices, queues, caching, configuration, observability, or NestJS tests. Prefer this skill over generic Node.js or backend advice for NestJS code.
CodeAlive-AI/exa-skills/exa-code-context Skill
no license2★ repoFind code with Exa — API usage examples, error fixes, library docs, and GitHub repositories. Use when you need a working code snippet, to resolve an error, find an open-source implementation, or pull up official docs for a language/framework. Runs a local script against the Exa API; no MCP server required.
Seahan1/kicad-agent/.agents/skills/kicad-schematic-design Skill
2★ repoCreate, edit, inspect, and validate KiCad schematics for digital, analog, power, interface, and mixed-signal circuits. Use for requests to open KiCad, create or draw schematics, place library symbols, assign footprints, define external interfaces, wire nets, review screenshots, or diagnose ERC and netlist issues.
BreetyGreen/Myco/skills/multi-agent-skill-sharing Skill
2★ repoInstall a skill once and make it usable across multiple AI coding agents (Claude Code, Codex CLI, Cursor, Gemini CLI, Cline, etc.) that work on the same repository. Use this when the user wants a skill / ruleset / prompt to be shared and switchable across several AI products, asks "why can only one tool use this skill", or wants cross-tool consistency. It maps each agent to its correct skill-reading directory, installs into the repo so the skill travels with Git, and documents the per-tool invocation syntax (which differs — e.g. Codex uses `$skill-name` or `/skills`, NOT gstack-style `/design` commands).
zhangganrui/zr-solo-studio/zr-solo-studio Skill
2★ repo一人公司 / Solo Studio —— 把一句话想法端到端变成一个能跑、好看、架构站得住的产品。它是一个总指挥(编排脊椎),自己不画图不写码,而是按顺序调度四个角色 skill(real-demand 发现真需求 → taste-pm 产品结构 → awesome-design-html 视觉 → cto 架构与实现),并在它们之间补三道缝(美学方向、设计落地、上线作品化),在关键处停下让你拍板。触发:'用一人公司做 X' / '帮我把这个想法做成产品' / '从想法到上线' / 'solo studio' / '端到端做个 X' / 'idea to ship'。也可在中途单独从某一步切入。不替代任何单个 skill——只编排它们。
coreline-ai/codex-resstyle-skill/response-style-sync Skill
2★ repoCreate, refine, and sync project response style, agent execution rules, and LLM/proxy usage policy into AGENT.md and CLAUDE.md from reusable JSON profiles. Use when the user wants to standardize Korean-first answers, force dev-plan-first workflows, require clarification before risky decisions, block default cloud API usage, prefer proxies such as multi_model_tui, or keep AGENT.md / CLAUDE.md aligned with a shared project rule set across repositories.
sssstwee/tastedistill/plugins/tastedistill-claude/claude-skills/debug Skill
2★ repoDiagnose failures, broken behavior, regressions, test failures, runtime errors, stale state, rendering bugs, and repeated failed fixes. Use when something does not work, used to work, crashes, fails tests, or needs root-cause proof. Not for product planning or release readiness.
EzraApple/skills-init/skills/adversarial-review Skill
2★ repoUse when the user asks for adversarial, independent, skeptical, panel, multi-agent, second-opinion, high-scrutiny, security-minded, or critical review of a PR, branch diff, uncommitted changes, changed files, plan, or specific paths.
ClarentCinematics/Codex-Skills-for-Enterprise/skills/account-research-brief Skill
2★ repoSynthesize account notes, company research, CRM context, buying signals, stakeholder information, and customer artifacts into a sales-ready account research brief. Use when Codex needs to prepare account strategy, discovery planning, outreach angles, ICP fit, stakeholder mapping, or enterprise customer context.
keepYaoung/artifact-organizer/plugins/artifact-organizer/skills/artifact-organizer Skill
2★ repoGenerate self-contained HTML pages and slide decks (diagrams, comparison tables, architecture overviews, diff reviews, visual recaps) by emitting semantic component JSON. Use whenever a visual artifact communicates better than terminal prose — proactively trigger on 4+ row tables, ASCII flowcharts, multi-stage pipelines, or explicit "make a diagram / slides / recap" requests.
joeeeeey/visual-brief/skills/visual-brief Skill
2★ repoCreate source-backed visual briefs from screenshots, annotations, diagrams, or generated images. Use for evidence replies, procedures, and public explainers; skip text-only work.
nkanf-dev/OpenAllay-Skills/skills/diagnose-missing-recipe Skill
2★ repoUse when an expected crafting or processing recipe is absent in the active pack.
The same file is in 1 other repository
zhangganrui/zr-real-demand/real-demand Skill
2★ repo在动手设计/开发任何产品之前,先逼问'这是不是一个真需求'。帮用户把一个模糊的想法,理清成'谁、在什么处境、因为什么真实的难或欲、愿意付出什么代价、想完成什么事',并用梁宁《真需求》的'价值-共识-模式'闭环判定它是真需求还是自我感动的伪需求。触发:'我有个想法' / '帮我看看这个需求' / '这是不是真需求' / '想做个东西' / '值不值得做' / '验证一下需求' / 'is this a real need' / 'validate my idea' / 'should I build this'。不做产品结构/信息架构(→ taste-pm)、不做视觉、不做技术选型。
ZiyuAI-creat/resume-builder-skill Skill
2★根据个人经历和目标岗位 JD 生成内容过硬的专业简历,输出 HTML 与 Word。用户提到做简历、改简历、优化简历、resume、CV、求职投递,或上传简历文件需要加工时使用。
danger-English/agent-zero-to-one-cn/starter/personal-page-polish Skill
2★ repoPolish an existing single-file personal page after the user asks for a clearer, more readable design while preserving its content and no-build setup.
dzhokhov/markdown-agent-vault-ru/skills/case-forensics Skill
2★ repoИзвлечение воспроизводимых AI-кейсов из длинных тредов, комментариев и чат-обсуждений. Используй этот скилл, когда нужно превратить разрозненные сообщения в методологию, которую можно повторить: контекст, шаги, артефакты, метрики, ограничения, и список пробелов (GAP), требующих уточнения.
yuewenyumenle/personal-ai-learning Skill
2★通过结构化流程帮助个人利用AI进行高效学习,融合内容转化、证据链验证、个性化讲解、知识库构建等先进学习方法。当用户想要学习新知识、需要AI学习伙伴、制定学习计划、将资料转化为课程、设计学习场景卡或复盘学习效果时调用。
frontier159/pr-stack/skills/pr-stack Skill
2★ repoSplit a large branch diff into a stacked, review-friendly PR set by re-carving the cumulative diff into ordered PRs and commits. Use ONLY on an explicit operator request to split a branch/diff/worktree into PRs (one-shot — that request alone), or to rebuild pr-stack-map.md (map mode). If the operator asks to create a PR and the pending diff is chunky — multiple packages, mixed backend+UI, or too large to review well — offer this skill in one line.
qiuy-collab/AutoFlow.skill Skill
2★Orchestrate multi-step artifact workflows by composing task, image, Word, PowerPoint, video, and packaging modules with durable state and mandatory human STOP gates. Use this skill whenever the user explicitly asks for autoflow, and also for substantial work that must produce multiple connected artifacts such as a runnable project plus screenshots and documentation, a report plus slides, or a complete submission package. Do not use it for simple questions or isolated one-step edits unless the user explicitly invokes autoflow.
MrBridgeHQ/human-writer-en/skills/human-writer-en Skill
2★ repoUse when writing, cleaning, or auditing ENGLISH prose so it reads as human-authored and survives AI detectors. Triggers on "write a human blog post", "humanize this", "clean this AI text", "make this less AI", "audit AI detection", "score this for Copyleaks", "rewrite the overview so it doesn't read as AI", plus any request that names English as the target language. English member of the human-writer per-language family. Covers en only, four content-types (marketing long-form / short-form comms / technical docs / editorial-SEO), three modes (write / clean / audit). English doctrine: ~200-entry suspect vocabulary, 54 AI-construction regexes, the em-dash "—" as the single English typographic tell, tricolons ("X, Y, and Z"), conclusion templates ("In conclusion" / "Ultimately" / "All in all"). Targets sub-25% AI-probability on Copyleaks/GPTZero.
ralfyishere/rules-with-receipts/.claude/skills/adversarial-verify Skill
2★ repoActively try to disprove or break your own answer before presenting it. Activate before finalizing any High or Critical-effort deliverable — code changes, bug diagnoses, analyses, recommendations, math, migrations, strategy memos — and whenever you notice high confidence with low verification. Trigger signals: you're about to say "this should work", "the issue is X", or present a conclusion the user will act on; the user asks "are we safe?", "you sure?", "is it safe?", "double-check this". Not for trivial answers or rough drafts explicitly requested as rough.
NanookAI/worldbank-api/skills/worldbank-api Skill
2★ repoFetch country-level economic and development data (GDP, population, inflation, unemployment, life expectancy, CO2, poverty, trade...) with the free World Bank Indicators API (no API key). Use for any macroeconomic statistics, country comparison, development indicator, or historical country data task, even if the World Bank isn't mentioned.
hicham-bouchikhi/quickshell-skills/skills/quickshell Skill
2★ repoBuild, debug, and extend QuickShell configs — QML-based desktop shell/widget framework for Linux Wayland compositors. USE FOR: writing shell.qml configs, bars, panels, popups, widgets, process runners, IPC, Hyprland/Wayland integration, notifications, system tray, media controls (MPRIS), audio (PipeWire), power (UPower), multi-monitor layouts, singletons, Scope modules, IpcHandler, PersistentProperties, Connections, inline components, typed QML functions. DO NOT USE FOR: generic QML/Qt app development unrelated to desktop shells, non-Linux platforms.
cyzlmh/agentype Skill
2★Run the Agentype workflow for local AI-agent usage analysis: collect and cache deterministic JSON, infer a persona/archetype from aggregate usage signals, then render a terminal summary or PNG poster. Supports Claude Code, Codex, OpenCode, pi-agent, Gemini CLI, OpenClaw, Nanobot, and configured Nanobot-compatible roots. Use when the user asks to understand their agent usage, AI workflow, token footprint, preferred agents/models/projects, or "agentype".
basemachina/skills/skills/basemachina-docs Skill
2★ repoBaseMachina公式ドキュメントを検索して、機能仕様・設定手順・制約・トラブルシューティング・コード例を根拠付きで回答する skill。BaseMachina、ベースマキナ、アクション、ビュー、bridge、コード管理、JavaScriptアクション、@basemachina/view、@basemachina/sdk について質問されたときに使う。
fyuuwang/fyuu-tutor/fyuu-tutor Skill
2★ repoOperate long-running, document-backed tutoring projects that turn trusted materials or goals into adaptive HTML lessons, practice, and evidence-guided next steps. Use when creating, continuing, reviewing, or handing off a private learning project; auditing source materials; planning a curriculum; generating lessons or reference aids; recording learner evidence; or routing a project through capability, certification, or language tutoring.
almutaz9000/fable-skill/skill Skill
2★ repoFable-class agentic operating discipline, gated to task risk and domain so overhead scales with stakes. Trigger on: explicit /fable-skill or $fable-skill; debugging or diagnosing a failure; changes spanning multiple files; refactors and migrations; irreversible or destructive actions; ambiguous goals needing decomposition; tasks likely to span many turns or sessions; research, analysis, report writing, literature review, scientific paper writing, or search tasks. Skip for trivial single-step edits, simple factual questions, and docs-only tweaks — there, only the evidence standard applies. Enforces explore → plan → act → verify → iterate, evidence-based verification, root-cause debugging, parallel tool use, state persistence, and outcome-first reporting across coding, planning, analysis, writing, science, and search domains.
smk-labs/web-animation-engine Skill
2★Build code-driven animated web sections, scenes, and explainers using a tiny bundled React + SVG runtime (Stage / Sprite / playhead). Use this skill whenever the user wants to *create* an animation from scratch — animated heroes, motion graphics, diagrammatic explainers, animated dashboards, scrubable scene compositions, or "bring this SVG to life" requests. Output is runnable HTML (CDN React + Babel, no npm) embeddable in any website or used standalone in presentations. Pairs with /frontend-design for visual polish; differs from UI-micro-interaction skills which polish *existing* UIs rather than compose new animated content.
siqili723547-ui/anime-fanart-imagegen Skill
no license2★Generate anime fan posters, scenes, stylized illustrations, and character renders for existing anime, game, visual-novel, or adjacent Japanese-style IP characters with strong identity preservation. Use when the user has only a rough idea in Chinese, cannot write a strong prompt, wants the agent to infer likely directions, gather official-priority references, lock character likeness, expand fuzzy intent into image-2-ready English prompts, explore style options without identity drift, or deliver repeatable 2K, 4K, or fixed-profile outputs for a known character/IP without copying a reference composition.
osodevops/intelligence-layer-skills/skills/semrush-backlink-audit Skill
no license2★ repoAudit backlink profiles with the semrush CLI. Use when the user asks for backlink analysis, referring domains, authority score, anchor text, indexed linked pages, backlink competitors, link gaps, backlink history, toxic or suspicious link signals, or off-page SEO recommendations based on Semrush CLI backlink data.