agentsclimarketplace

The catalog

608,666 rows, by stacks then stars

  • Pcan operations skill

    InitusNovus/pcan-operations-skill Skill

    1★

    Use when operating PEAK-System PCAN interfaces or PCANBasic-compatible hardware through PCANBasic or python-can. Covers discovery, Classic CAN and CAN-FD initialization, exact bit timing, safe read/write, status handling, filters, timestamps, cleanup, and bounded recovery.

  • Continuity

    inwrkai/continuity Skill

    1★

    Extract records from chats and discover a workspace schema from spreadsheets or an interview. LLMs are great at summarizing but not good at records — point this at any chat with your connectors and get structured records out, with grounding from other relevant sources. Use when the user mentions continuity, discover schema, extract records from chats, convert a conversation into records, update an inwrk bundle, asks about records already stored in inwrk/, wants to visualize their knowledge base (visualize, canvas, show my knowledge base), apply canvas changes to create, update, or delete records in the bundle, or manage event-driven automations (when X happens do Y, add an automation, check schedules).

  • Supermarketer skill

    cskwork/supermarketer-skill Skill

    1★

    Use for product marketing strategy and execution across 47 specialist domains, including research, positioning, pricing, offers, SEO, lifecycle, outbound, campaigns, launch plans, copy, ads, social, creative production, conversion, analytics, experiments, audits, and measurement.

  • Weave

    KKenny0/weave Skill

    1★

    Multi-source research pipeline that produces evidence-grounded Chinese longform from a source bundle, technical project, or open domain. Deep Read handles prose sources, Source Dive reconstructs technical systems, and Survey uses a Learn-based six-phase research-to-writing workflow with an explicit Spine Direction Gate and sparse Visual Pass. Auto-scouts when the user provides only a topic. Use whenever the user asks in any language to 深入研究, 研究一下, 深度阅读, source dive, survey, 测绘领域, 从零讲懂, 让非专业背景也能读懂, 写一篇深度解析, 整理成研究文章, research, deep dive, study, or wants to understand material deeply enough to write about it.

  • Help

    zhangtao272820/AI_Agent/DB_Agent/.trae/skills/help Skill

    no license1★ repo

    输出系统能力清单与示例问题。当用户问“你能做什么/怎么用/支持哪些查询”时调用。

  • Omega3 distill

    mohamed-essam/omega3-template/skills/omega3-distill Skill

    1★ repo

    Nightly "sleep on it" pass for the omega3 knowledge hub. Drains inbox into systems/knowledge (dedup + link), optionally refreshes a knowledge graph, updates per-initiative journal rollups, and does a review-gated generative pass proposing new cross-system insights. Meant to run autonomously on a nightly schedule (e.g. cron) as `claude -p "/omega3-distill"`; can be run manually.

  • Amplifier skill forge

    michaeljabbour/amplifier-skill-forge Skill

    1★

    Spin up, fan out, drive, and test terminal apps in persistent PTY sessions via the forge terminal daemon — including orchestrating coding agents (Claude Code, Codex, Gemini, OpenCode) and Microsoft Amplifier. Use when asked to launch or test an app in a terminal, drive a TUI, run terminal sessions in parallel, operate Claude Code / Codex / OpenCode / amplifier programmatically, spawn or delegate to another coding agent, coordinate multiple agents through shared artifacts, babysit long-running pipelines, or when you need to launch, drive, or test Amplifier itself in a real terminal session (interactive runs, or supervising attractor / evaluation / resolve / superpowers jobs via their file ledgers).

  • Enforce design ci

    sarveshsea/enforce-design-ci Skill

    1★

    Use when a repository needs deterministic pull-request checks for new accessibility, design-token, component-structure, responsive, and UI-state regressions with file-level evidence.

  • Sync skills

    noppu-labs/ai-toolkit/.claude/skills/sync-skills Skill

    1★ repo

    Use when checking vendored skills for upstream updates, pulling or merging upstream changes into this repo, or re-baselining skills-lock.json after editing a vendored skill.

  • Remek

    benblackthorn/remek/skills/remek Skill

    1★ repo

    Use when a request names remek or asks to initialize a governed Agent Skills source; capture, import, or revise governed skills; record reviewed external evidence or distribution approval; audit an untrusted skill; or prepare and verify a release mirror you own. remek governs completed skill bytes and reviewed results; authoring, evaluation runs, Git, installation, and publishing use compatible capabilities.

  • Waypoint

    omorShahriar/waypoint Skill

    1★

    Turn approved plans into local, resumable work and carry execution safely across fresh agent sessions. Use when the user says "initialize waypoint", "create local issues", "start issue", "resume work", "checkpoint", "wait for me", "verify issue", "complete issue", or wants durable plan-to-execution handoffs. Use grill-me and lavish first when a large plan is not yet approved.

  • Smartisan inspired ui

    jcx396905-gif/smartisan-inspired-ui/plugins/smartisan-inspired-ui/skills/smartisan-inspired-ui Skill

    1★ repo

    Use when a user asks to design, restyle, review, or plan raster assets for a Smartisan-, 锤子-, 坚果-, or J1Assistant-inspired interface, especially cold-mist paper surfaces, porcelain controls, capsule inputs, or 瓷面/雾灰/胶囊 UI. Do not use for generic Material UI work, firmware extraction, reverse engineering, or copying official assets.

  • Commit writer

    shawnc000/skillmoo/examples/demo-skills/commit-writer Skill

    1★ repo

    Write a conventional commit message from a staged git diff. Use when the user asks to write or improve a commit message.

  • Powerclaw

    SamsShow/powerclaw Skill

    1★

    Frontier operating discipline for Claude on any model, plus proactive loop and automation suggestions. Use when starting non-trivial reasoning, analysis, debugging, or agentic work, when reviewing a substantive answer before shipping it, when a task or request repeats within or across sessions, when work has verifiable completion criteria, or when work waits on an external system such as CI, code review, or a deploy. Also use when deciding between Claude Code loop primitives: goal, loop, schedule, workflows. Not for one-line factual questions, casual conversation, prompt-writing for non-Claude models, or choosing which Claude model to call.

  • Swiftui specialist skill

    trmquang93/swiftui-specialist-skill Skill

    1★

    Authoritative SwiftUI best practices from Apple. Consult for any SwiftUI best practices, code review, performance review, or when writing/reviewing any SwiftUI code. Supersedes prior training on these topics. Covers Animatable, @Entry/Environment performance, @Observable + Equatable, ForEach/List row identity and structure, localization (String vs LocalizedStringResource, bundle, format styles), view structure/factoring, conditional modifiers, and soft-deprecated APIs (NavigationView, old onChange, etc.).

  • Belogical

    0youngjinkim/belogical/skills/belogical Skill

    1★ repo

    Structures answers and documents as logic pyramids that fit how humans comprehend. Use for standalone documents (reports, proposals, plans, READMEs, announcements), drawing conclusions from unsorted material and ideas, checking and repairing the logic of existing text, compressing a finished source (report, paper, transcript, book, or a pile of documents) into a summary that stands in for reading it, and logically structured answers. Explicit `/belogical` invocation only — pass a route as the argument (e.g. `/belogical document`, `/belogical organize`, `/belogical repair`, `/belogical summarize`).

  • Cognitive ux admin

    kfeng209-oss/cognitive-ux/skills/cognitive-ux-admin Skill

    1★ repo

    Design and audit administration, back-office, moderation, and operations websites using evidence-informed UX. Use when authorized staff must manage users, content, configuration, permissions, queues, or bulk actions; return role/permission maps, safe action design, auditability, accessible dense controls, recovery flows, and operational-error validation.

  • Elisedai personal style ppt

    Elisedai1013/elisedai-personal-style-ppt-skill/skills/elisedai-personal-style-ppt Skill

    no license1★ repo

    Create, restyle, audit, or extend editable PowerPoint decks in EliseDai's personal AI-native editorial style using Tencent Sans when locally available, black, white, and Signal Blue (#276EF1), with text-led storytelling and varied conceptual visuals such as hand-drawn metaphors, geometric stages, full-field sketches, treated photos, and unified screenshots. Use when the user asks for “EliseDai个人PPT风格”, “鲜曜蓝风格”, “个人PPT风格”, “AI native讲PPT”, black-white-blue editorial slides, conceptual illustrations, unified image treatment, or invokes $elisedai-personal-style-ppt.

  • Ai industry daily html

    differance-dfhs/ai-industry-daily-html-skill/skills/ai-industry-daily-html Skill

    1★ repo

    Research today's AI industry developments and produce a source-verifiable, art-directed, single-page HTML daily report with inline CSS and desktop/mobile browser QA. Use when the user asks for an AI news daily, industry briefing, editorial HTML report, or a repeatable AI-news automation loop.

  • Requirement clarifier

    dinghaochen1004-blip/requirement-clarifier Skill

    no license1★

    Clarify ambiguous, complex, multi-step, costly, or high-risk requests before planning or execution. Use when the goal, scope, inputs, constraints, deliverables, acceptance criteria, tradeoffs, or authorization boundaries could materially change the solution; for software changes, system design, automation, agent workflows, long-form deliverables, data work, bulk edits, destructive actions, production changes, or any request with multiple consequential interpretations. Also use when the user explicitly asks to clarify requirements or reach 95% confidence. Do not slow down simple, explicit, low-risk tasks such as translation, arithmetic, small rewrites, or narrowly specified reversible fixes; fast-pass those without unnecessary questions.

  • Skill compass

    yinyoudexing/skill-compass Skill

    1★

    Use when a user wants to find, understand, browse, install, update, or remember Agent Skills without memorizing their names

  • Flow ai chat

    jpoindexter/ux-flow-skills/skills/flow-ai-chat Skill

    1★ repo

    Proven UX flows, user journeys, and app layout patterns packaged as agent skills for Claude Code, Codex, Gemini CLI, and any coding agent

  • Fastapi best practices

    dkmqflx/fastapi-best-practices-plugin/plugins/fastapi-best-practices/skills/fastapi-best-practices Skill

    1★ repo

    Use when writing, reviewing, or refactoring FastAPI code — endpoints, APIRouter, query/path parameters, dependencies (Depends), Pydantic request/response models, error handling, async def vs def, lifespan events, streaming, background tasks, settings, middleware, or CORS. Triggers on FastAPI backend work, route design, or API code review. For auth/security see fastapi-security; for tests see fastapi-testing.

    The same file is in 1 other repository

  • Mediabunny

    gabros20/product-skill/.agents/skills/mediabunny Skill

    1★ repo

    Multimedia handling with the Mediabunny library

    The same file is in 1 other repository

  • QuantAll mcp

    mifochen/quantall-mcp/QuantAll-mcp Skill

    no license1★ repo

    QuantAll(全A解析)MCP —— 股市全市场向量化计算引擎,为 AI 提供本地 Python 计算环境。 AI 编写向量化代码片段,数秒内完成 5000+ 股票的因子计算、策略回测、IC 分析和 GPU 可视化。 让 AI 从"信息查询者"升级为"数据计算者"——用代码算出客观结果,而非搬运网络观点。 触发:用户明确提到"回测""因子分析""IC分析""选股策略""QuantAll""全A解析"等量化关键词时。 不主动在普通股市聊天中触发,仅在用户有明确量化分析需求时使用。 能力声明:本技能需在用户电脑上创建 Python 虚拟环境(300MB+)、安装 quantall 库、 修改 MCP 配置、启动本地 HTTP 服务(localhost:8686)、创建配置文件和启动脚本。 所有涉及用户电脑的操作,AI 必须事先告知用户并获得同意。 UpdateStock 为可选辅助 MCP(数据库管理,需 tushare API),非 QuantAll 必需。

    The same file is in 2 other repositories

  • Okf cli

    auto-medica-labs/okf-cli/skills/okf-cli Skill

    1★ repo

    User manual and reference for the okf CLI tool (Open Knowledge Format). Use for questions about bundling plain markdown into OKF knowledge bases, validating OKF bundles, listing concepts, reading concepts, CLI options, and end-user workflows. Not for okf-cli source development.

  • Component preview authoring

    shahroz-a/skills/skills/component-preview-authoring Skill

    1★ repo

    Create, repair, and verify live previews for reusable UI components. Use when building component galleries, registry index cards, detail-page demos, preview fixtures, isolated sandboxes, lazy renderers, or fallbacks for blank, crashing, oversized, nondeterministic, or noninteractive component previews. Do not use for static marketing thumbnails, unrelated page redesign, or copying a third-party demo without source and license review.

  • Master system builder

    zethfion/rw-master-system/skills/master-system-builder Skill

    1★ repo

    Build, audit, and maintain source-grounded AI expert knowledge systems from public or user-authorized email, books, articles, YouTube, podcasts, webinars, and courses. Use when an agent must create an expert package from zero, ingest mixed source types, distill evidence-backed personas and frameworks, add new material incrementally, or teach a human how to consult the resulting system. Do not use to bypass access controls, redistribute protected content, or impersonate a real person deceptively.

  • Create agent

    aetox-skills/create-agent Skill

    1★

    Use this skill to design or modify AI agents with a scope-first process. Clarifies mission, boundaries, authority, inputs, outputs, risks, metrics, tools, tests, and stop conditions before producing an Agent Spec.

  • Capability gap analysis

    wde123sadw/agent-preflight/skills/capability-gap-analysis Skill

    1★ repo

    Determine whether an agent already has the capabilities required for a task before recommending or installing anything new. Use when a task may require unfamiliar file formats, external services, browsers, desktop apps, media generation, databases, deployment access, specialized runtimes, large-context handling, or verification tools. Produce a capability map and hand only proven gaps to tool discovery.

  • Decision records

    mc856/decision-records/skills/decision-records Skill

    1★ repo

    Record, consult, and review the user's significant decisions in DECISIONS.md ledger files (the DECISIONS.md format). Use this skill whenever the user says "log this decision", "record this decision", "we've decided", "记决策", "记一下这个决策", "拍板"; right after a significant technical choice, architecture tradeoff, or priority call is made in conversation — even if the user doesn't mention recording; when the user overrides a model recommendation; when the user asks "why did we choose X", "what did we decide about this", "当时为什么选"; before starting significant work in a project that has a DECISIONS.md; or when the user asks for a decision review. Pure progress logging ("log today's progress") is not this skill — but offer to record any qualifying decisions at session end.

  • Herdr peer review

    Elio2000/herdr-peer-review Skill

    1★

    Drive a second ("peer") coding agent from Claude inside a herdr session, in a watchable TUI pane, so the user can SEE the multi-agent conversation. Use when running inside herdr and the user asks to have another agent review the current changes / a diff / a file, or to consult / ask another agent ("让 codex/grok review", "问一下另一个 agent", "找 X 咨询一下", "peer review", "第二意见"). The peer agent is a single swappable config knob — codex today, grok / cursor / claude / etc. tomorrow. Completion is detected via herdr's agent-status (agent-agnostic). The peer is ALWAYS launched auto-approve ("YOLO") so the loop never stalls on a prompt and can run unattended / AFK; the peer can also arbitrate decisions to close the loop with no human present. Encodes the project's Claude = Code Agent / peer = Reviewer split.

  • Black swan radar

    Jinchengawu/stock-monitoring-kit/skills/black-swan-radar Skill

    1★ repo

    Triage sudden geopolitical, war, tariff, sanctions, policy, liquidity, cyber, or market-structure shocks and trace their likely market impact. Use when breaking news may be a black-swan event, the user asks for urgent risk analysis, or existing market scenarios need rapid invalidation and monitoring triggers.

  • Article writing

    vivekkhimani/gtm-tools-template/.agents/skills/article-writing Skill

    1★ repo

    Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

    The same file is in 4 other repositories

  • Super spec

    wlj103/super-spec Skill

    1★

    Spec-driven engineering discipline for AI coding agents—seven-gate pipeline with anti-laziness interception, five-document cross-validation, and evidence-based verification. For new projects, core modules, and major version upgrades. Ensures AI can't skip steps, pass empty, or deliver untested code.

  • Benchmark design

    Dafenxz0/skillproof/benchmarks/self/fixtures/benchmark-design Skill

    1★ repo

    Review a technical change for correctness, regressions, and missing tests.

  • Classcorpus

    haixinnn05/classcorpus Skill

    1★

    Index and search local PDF, PowerPoint, DOCX, Markdown, and text lectures as persistent, citation-aware course memory. Use for class questions, summaries, comparisons, flashcards, practice exams, cheat sheets, study plans, visual slide analysis, or cited study guides.

  • 507 commit

    ssdiwu/507-skills/code/507-commit Skill

    1★ repo

    Git 提交:在用户明确要求提交时,轻量安全复核变更、精确暂存、运行相关验证并创建真实 Conventional Commit;只做本地提交,推送与对外发布由 507-release 承接。Use when user says commit, 提交, 提交一下, 提交这些改动, 提交代码, Git 提交, commit 一下, 生成并执行提交, 准备提交, 存个档。

  • Wayback site recovery

    nazroll/wayback-site-recovery/skills/wayback-site-recovery Skill

    1★ repo

    End-to-end recovery of dead or expired websites from the Internet Archive's Wayback Machine - inventory what's archived via the CDX API, bulk-download with resume and polite rate-limiting (pywaybackup or wayback-restorer), audit missing images/assets, fix links, and rebuild a browsable static site or extract posts to Markdown for migration to Hugo/Astro/Eleventy. Use whenever the user wants to download, restore, mirror, rebuild, or rescue an old website, blog, or expired domain from the Wayback Machine / archive.org / web.archive.org; recover lost images or content from an archived site; check what the archive holds for a domain; or migrate an archived blog to a modern static site generator. Trigger even if the user just says a site "is only on the Wayback Machine", "my old blog is gone", or "I bought an expired domain and want the old content back".

  • 测验验收

    chenyuxiaojin/CYXJ-79/测验验收 Skill

    1★ repo

    测验验收(quiz 验收):一段长工作会话或大改动结束后、合并/发布/交付之前, 生成一份"发生了什么"的直白报告 + 底部测验,用户满分才算验收通过。 解决的问题:Claude 干的活越多,用户越可能"以为自己懂了"——光看 diff 或摘要 只能获得表面理解,测验暴露真实的理解缺口。 触发词:测验验收、考考我、quiz、出个测验、「我想确认我真的理解了这次改动」。 当一次会话改动量大、决策多,而用户即将合并/发布/关闭会话时,应主动建议做一次测验验收。

  • Animated sticker maker

    wufei-png/animated-sticker-maker/skills/animated-sticker-maker Skill

    1★ repo

    Make one transparent animated sticker package from one static reference image and one natural-language motion prompt. Use only when the user explicitly names or invokes animated-sticker-maker (for example, $animated-sticker-maker on hosts with dollar-sign invocation); do not trigger for ordinary image, GIF, animation, or multi-sticker pack requests.

  • Chengxing conflict

    githubume/chengxing-os-skills/.agents/skills/chengxing-conflict Skill

    1★ repo

    Use when a user wants to analyze a recurring interpersonal conflict, pause escalation, express a boundary, repair a safe relationship, or turn rumination into action. This Codex compatibility adapter routes requests to the independent Chengxing OS conflict-reset plugin and stops ordinary dialogue in violence, coercion, or stalking scenarios.

  • Audit

    eduardkumskyi/octo/skills/audit Skill

    no license1★ repo

    PR-style pre-merge audit: exhaustive, skeptical, read-only review of the current branch against a base chosen from a question card, across companion repos confirmed by active-work detection. Reviews like a senior engineer trying to block a risky merge — severity-graded findings with concrete failure modes, cross-repo compatibility, must-fix vs safe-to-defer; then optionally select findings to fix.

  • Fintech ux

    ravipalwe/design-skills/skills/fintech-ux Skill

    1★ repo

    Fintech UX — design judgment for money products, encoded from 19+ years of financial services design leadership. Activates whenever the work touches money: banking, payments, checkout and billing, invoicing, insurance, lending, wealth/investing, crypto wallets, payroll, expense tools — building new UI, reviewing existing UI, or designing critical flows (onboarding/KYC, transfers, failed payments, disputes). Covers trust architecture, financial-anxiety-aware design, money display craft (tabular figures, pending vs posted, negative conventions — with a bundled lint that computes violations from code), compliance as a design material (KYC, AML, PCI-DSS, Reg E, TILA), and the anti-patterns that erode trust or invite regulatory risk. Use when the user mentions a financial product or feature, a payment/checkout/billing flow, KYC or verification UX, displaying balances/transactions/rates, or asks "does this feel trustworthy?" — even if they never say the word "fintech".

  • Skill router

    youaifuou/skill-router/skills/skill-router Skill

    1★ repo

    Audit installed Agent Skills, identify highly similar Skills that compete for the same user requests, and plan, create, or review focused Router Skills. Use when users want to organize installed Skills, consolidate overlapping entry points, create adaptive coordination between related Skills, or correct a Router that is too broad, rigid, or generic. Keep Skills independent unless aggregation solves a real discovery conflict.

  • Accessibility

    andr-ca/agentharness/.claude/skills/accessibility Skill

    1★ repo

    Use when building or reviewing web UIs for accessibility — WCAG 2.2 Level AA compliance, semantic HTML over ARIA, keyboard navigation, color contrast, screen reader patterns, and testing approach.

  • Build intuitive rca wiki

    cskwork/build-intuitive-rca-wiki Skill

    1★

    Turn technical incidents, rollback reports, root-cause analyses, postmortems, and system failure explanations into intuitive standalone HTML wikis for nondevelopers. Use when a user asks for a visual or easy-to-understand incident explanation, a beginner-friendly RCA page, a reusable one-file HTML wiki, or when raw IDs, table names, error codes, and architecture diagrams need a plain-language presentation layer.

  • Openclip

    Oak-Ridge-Ventures/openclip-skill/skills/openclip Skill

    1★ repo

    Turn long videos into short, captioned viral clips from your agent via the OpenClip MCP server. Also FREE with just an account (no subscription): transcribe a video, convert/compress/trim/crop/resize/mute a video, extract thumbnails, edit an image, remove an image background. Plus generate a short UGC-style ad clip from a brief. Triggers include "clip this video", "make shorts", "repurpose this", "find viral moments", "transcribe this", "convert to mp4/gif/mp3", "compress this video", "remove the background", "make a UGC ad", "openclip".

  • Wondel auto router

    carloslimaborges/wondel-auto-router/wondel-auto-router Skill

    1★ repo

    Routes any task to the right wondel.ai framework skills automatically, without the user asking. ALWAYS consult this skill at the start of software development work (writing code, refactoring, code review, architecture, APIs, databases, legacy code, performance, deploys) and also for UI/UX design, landing pages, marketing copy, positioning, pricing, sales, negotiation, product strategy, user research, growth, retention, analytics, or team/management questions — even when the user never mentions "skill", "framework", or wondel.ai. It tells you which expert skills to load before doing the work.

  • Ai parenting coach

    Lucius1105/daihaowa-ai-parenting-expert/skills/ai-parenting-coach Skill

    no license1★ repo

    带好娃 / AI Parenting Expert. Use when a parent, caregiver, teacher, or coach needs practical help with ages 0-18 child education, parenting plans, parent-child communication, homework conflict, screen-time boundaries, emotional meltdowns, intergenerational conflict with grandparents, co-parenting coordination, child independence, confidence, creativity, routines, and non-punitive behavior guidance. Strongest for ages 3-12 in v1.0. For long-term education planning or family-system conflict, use the bundled family education strategy reference. Do not use for medical diagnosis, psychiatric crisis, abuse investigation, legal custody disputes, or advice that replaces qualified professional support.

  • Packaging datacloud

    holapancho/packaging-datacloud-skill/skills/packaging-datacloud Skill

    1★ repo

    Package and ship Salesforce Data 360 (Data Cloud) Data Kits as managed 2GP packages: Standard vs DevOps kit types, retrieve workflow, SSOT dependency, publishing sequence, KQ cleanup, deploy after install, undeploy/uninstall (including Currency Connection / StaticCurrencyRates blockers), and packaging oddities. Use when packaging data kits, DataPackageKitDefinition, DMOs, data streams, or Data Cloud metadata for AppExchange or managed package distribution.

  • Branch sandbox

    Aquish-Lee/agent-handrails/plugins/agent-handrails/skills/branch-sandbox Skill

    1★ repo

    Create a branch, worktree, or scratch clone when a user explicitly requests isolation or a risky or parallel coding task needs a reversible workspace boundary. Use for broad refactors, migrations, autonomous runs, and concurrent work; skip routine micro-tasks and read-only investigation.

  • Gen z

    kopon1/gen-z/plugins/gen-z/skills/gen-z Skill

    1★ repo

    Turn ON a gen-z / extremely-online personality. From the moment it's invoked, talk casual, lowercase, dry, and funny without trying, until the user turns it off. The voice is nonchalant and effortless, not hype and not flat. Slang stays light, one emoji max, and the real answer always survives the tone. Use when the user runs /gen-z or asks you to "talk gen z", "be more gen z", "sound younger", "sound less corporate", "be more casual / more online", or wants social copy (tweets, captions, DMs, memes) in that voice. Turn off with /gen-z-off or "normal mode" / "be professional". This is a persistent voice mode, not a one-off rewrite. Not for professional, legal, or safety-critical text.

  • Harness build

    atlax-tech/harness-armor/skills/harness-build Skill

    no license1★ repo

    Read substantive product, requirements, design, and planning sources in a docs-only repository and build a project-specific, traceable Harness without business code. Use when the repository has product documents but no implementation, or when harness-build is invoked. Do not use for empty repositories, legacy code promotion, ordinary build commands, or managed-Harness updates.

  • Learn an industry

    ziranjuan168/ai-pm-skills/skills/learn-an-industry Skill

    1★ repo

    Build zero-to-one working knowledge of an unfamiliar industry, sector, profession, job, company type, or business process. Use when a user says they do not understand an industry or its terminology, upstream/downstream chain, roles, workflows, documents, systems, business model, metrics, regulations, or AI opportunities; asks to quickly learn, enter, interview for, research, or build products for a domain; or requests 行业入门、行业知识学习、快速看懂一个行业、岗位扫盲、业务流程扫盲、产业链解释、术语解释、AI+行业机会分析、横纵分析式学习. Also use when evaluating, maintaining, or improving this skill after explicit user feedback. Teach from plain language to a usable mental model instead of jumping directly to a market report.

  • Searxng search

    FactrueSolin/searxng-skills/skills/searxng-search Skill

    1★ repo

    Use the local sxc CLI to search a configured SearXNG instance, inspect instance configuration, and answer research questions with verifiable source URLs. Use when the user asks for web search, current information, source gathering, or SearXNG instance details.

  • After

    RudrenduPaul/evolveguard/fixtures/labeled-non-breaking-edits/case-01-wording-tweak/after Skill

    1★ repo

    Produces a concise summary of a pull request's diff for a reviewer.

  • Agentic os

    giacomoguidotto/skills/skills/agentic-os Skill

    1★ repo

    Coordinate versioned cross-System capabilities. Use when the user invokes /agentic-os scout, /agentic-os pursue, or /agentic-os upskill.

    The same file is in 2 other repositories

  • Cartoon synth

    derrickxu1220/cartoon-synth Skill

    no license1★

    Create clear red-black New Yorker-inspired editorial cartoons and familiar visual fables from essays, articles, abstract ideas, stories, workplace situations, business, technology, AI, culture, education, relationships, or data analysis. Use when the user asks for peitu, chatu, xiao yuyan, visual fables, editorial cartoons, familiar metaphors, niuyueke style, CartoonSynth, New Yorker-style illustration, Orange Line hybrid, red pen-and-ink illustration, article covers, witty conceptual scenes, or a coherent illustration series.

  • Igapyon miku ai assistant builder

    igapyon/miku-ai-assistant-builder-skills/skills/igapyon-miku-ai-assistant-builder Skill

    1★ repo

    ベータ版。Microsoft 365 Copilot内の軽量なAgent BuilderまたはGoogle GeminiのGemに投入するデータを準備し、雑多な既存フォルダを二段階で配備用フォルダへ変換するスキル。Agent Builderを主対象とし、Gemにも対応する。第1段階でJSON / JSONLを1入力1XLSX候補、それ以外の同梱`miku-text-bundle`対応テキストをバンドル候補として確定し、人間の資料追加を待つ。第2段階ではJSON / JSONLの明示mappingをレビューして固定し、確定条件から再実行可能なNode.js変換ジョブを作る。Agent Builder向けMarkdownをDOCX化し、GemではMarkdownのまま使うか同梱`miku-md2docx`でDOCX化するかを利用者が選ぶ。構成固定の内容更新は同じジョブを再実行し、前回条件を再検討する反復実行では新しい作業フォルダを作る。ファイル添付を利用できるライセンス、アカウント、管理者設定が前提。`igapyon-miku-ai-assistant-builder`または`miku-ai-assistant-builder`が明示されたとき、このスキルを使ったフォルダ変換、その再開、確定済み構成の内容更新、または前回条件を参照した再実行が依頼されたときに使用する。Copilot Studio固有のエージェント作成には使用しない。