agentsclimarketplace

The catalog

609,856 rows, by stacks then stars

  • Corporate portrait generator

    WSD-MJ/image-photo-generator/corporate-portrait-generator Skill

    no license2★ repo

    Generate a polished, professional corporate portrait / business headshot from a personal photo. Upload a selfie and get a clean, high-end business portrait with selectable backgrounds and outfit styles — no influencer glamour, just a reliable professional look. Use when the user wants an AI headshot, corporate portrait, business headshot, LinkedIn photo, professional profile photo, 职业照 / 商务形象照 / 职场头像, or a team of uniform staff portraits. Trigger keywords: headshot, AI headshot, corporate portrait, business photo, professional avatar, LinkedIn photo, 职业照, 商务照, 形象照, 职场头像. Requires an API key from wsdsocial.com.

  • Django schema design

    llodev/skills/skills/django-schema-design Skill

    2★ repo

    Design robust Django database schemas with model best practices, migration patterns, and primary key strategy (incremental, UUID, UUIDv7). Use when designing Django models, choosing PK types, writing migrations, or reviewing app schema. Covers Django ORM, PostgreSQL, indexes, constraints, and security considerations for IDs.

  • Compliance check

    philgoodvibe/aiai-mastermind-tools-and-skills/maya-starter/skills/compliance-check Skill

    2★ repo

    Run a content draft against the compliance knowledge base in brain/compliance/ and return PASS or FAIL with exact concerns. Use on every draft before it reaches output/drafts/ or Mai Marketing Machine, and whenever the owner says "compliance check", "is this compliant", or "check this post". No draft proceeds without a PASS from this skill.

  • Aet check

    AdvancingTitans/agent-engineering-toolkit/skills/aet-check Skill

    2★ repo

    Run a bounded AET check of Agent instructions, Skills, verification contracts, and dangerous authority. Use only when the user explicitly invokes /aet-check or asks for this AET Quick check.

  • Develop like 37signals

    marcusrbrown/dev-like/registry/37signals/skill/develop-like-37signals Skill

    2★ repo

    Develop the way 37signals (the company) does: shape up cycles/betting/circuit-breaker, vanilla server-first Rails, manual exploratory QA over dogma. Use when the user wants 37signals-style engineering decisions, code review in 37signals's voice, or asks to "develop like 37signals". Profiled 2026-07-16 from public sources.

  • Default

    MauricioPerera/llms-txt-skills/.well-known/skills/default Skill

    2★ repo

    Generate SVG placeholder images for UI mockups via the placeholder-img HTTP API. Use when the user asks for placeholder images, mockup assets, or dummy images with specific dimensions and colors.

  • Systematic debugging

    RbBtSn0w/adg/test/fixtures/superpowers/skills/systematic-debugging Skill

    2★ repo

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    The same file is in 8 other repositories

  • 00 INDEX

    subhansh-dev/agent-maxxing/00-INDEX Skill

    2★ repo

    95+ agent skills, 19 UI components, 7 system prompts from Claude Fable 5, GPT-5.5, Gemini CLI & more. Self-fine-tune your agent: paste one prompt and it reads every skill, internalizes patterns, and becomes elite. Works with Claude Code, Codex, Cursor, OpenCode + 60 more agents.

  • Academic researcher

    rakibulism/agent-skills-os/skills/academic-researcher Skill

    2★ repo

    Do rigorous scholarly research — formulate a research question, run a literature review, pick a sound methodology, situate work in the existing literature, and write in academic register with disciplined citation. Goes deeper than general web research into research design, synthesis across a body of work, identifying gaps, and meeting peer-review standards. Use this skill whenever the user is writing a paper, thesis, literature review, grant or research proposal, or systematic review; needs a defensible methodology; is synthesizing a body of academic literature; or asks how to frame a research question or find the gap in a field.

  • Fram loop

    TheRealClodius/fram-loop/skills/fram-loop Skill

    2★ repo

    Two-agent autonomous loop (Builder + Reviewer) for shipping any long-running coding deliverable end-to-end across multiple phases without mid-run human input — features, refactors, migrations, library design, perf, large cleanups. Output is a finished deliverable on an isolated harness branch with a PR opened back to the source branch. Starting a run requires the user's explicit go-ahead, but any clear request to run the loop counts — "use/run/spin up the fram-loop", "fram-loop this", "kick off the loop", or similar; exact phrasing doesn't matter. If a task fits the shape (multi-phase deliverable, spec + plan available) and the user hasn't asked, SUGGEST this skill and ask — but never start a run without the user's yes: a run is hours-long, token-heavy, and autonomous end-to-end.

  • Send email

    genius-harry/auto-email-sender/skills/send-email Skill

    2★ repo

    Send or schedule email on the user's behalf through their auto-email-sender pipeline (Gmail + Apps Script) — the correct way to send mail once this tool is installed. Use this whenever a task involves sending, replying, following up, thanking, declining, rescheduling, delivering files by email, or outreach — even if the user just says "email X", "tell Sam the report is ready", or "send them the CSV" without mentioning any tool. Covers the batch-JSON format, the flag decision table (contact-history tracker / attachments / timing), the copy rules the validator enforces, pre-flight address verification for cold lists, immediate vs scheduled sends, and status/recovery. Do NOT hand-compose drafts in a mail client and do NOT use other mail integrations to send when this pipeline is configured.

  • Canon

    IamK77/Skill/skills/atelier/canon Skill

    2★ repo

    The design-judgment spine of the atelier suite — where the visual language and archetype are chosen and the quantified targets all later lenses enforce are set. Use before any pixel is placed — before a color system or type scale is chosen. The one shift: good design is NOT defaults nudged until it "looks ok" — it is a few NON-DEFAULT, QUANTIFIED decisions: the point of view (derived from the product), the visual language that POV demands, the archetype, and what "premium" means in measurable terms. The agent, with no taste, defaults to the bland statistical mean of its training (e.g. warm-cream-editorial-serif), so these must be DECIDED and GATED. Triggers on "start a design / where to start visually", "which visual language / what style", "design brief / design direction". The spine to atelier as bearings is to surface: canon decides the direction the sibling lenses execute.

  • Cloud cost agent

    dautovri/cloud-cost-agent/skills/cloud-cost-agent Skill

    2★ repo

    Use when analyzing cloud spend, running a cost audit, or finding savings across AWS, Google Cloud, and Azure — rightsizing, idle resources, and commitment/reservation recommendations, per-provider or cross-cloud. Uses only native CLIs and recommendation services (Cost Explorer/Compute Optimizer/Cost Optimization Hub, GCP Recommender, Azure Advisor + Cost Management) to produce prioritized savings reports.

  • Daily work planner

    Stephen-studying/daily-work-planner/daily-work-planner Skill

    2★ repo

    Plan a focused work session before execution begins, inspect current/local open tasks, estimate required time, score feasibility against the actual deadline window, checkpoint progress, resume unfinished sessions, create handoffs, and record private local task memory. Use when the user asks to start, schedule, estimate, resume, or replan a work session with goals, files, available time, deadlines, current-window notes, or a local repository; support milestones, acceptance criteria, buffers, fallback scope, repo task triage, speed-adjusted estimates, feasibility scoring, TXT/DOCX/ICS outputs, review logs, and habit memory for documents, code, study, research, presentations, data, or project work. Do not invoke merely because files or a repository are present when the user wants the substantive task executed rather than planned.

  • Agentverse chat

    fetchai/agentverse-skills/skills/agentverse-chat Skill

    2★ repo

    Send messages to any agent on Fetch.ai's Agentverse and receive responses. Handles text, images, and structured data. Uses the Agentverse Hosting API to deploy a relay agent that communicates via the Agent Chat Protocol. Requires AGENTVERSE_API_KEY env var. Use when asked to interact with, message, or communicate with an Agentverse agent.

  • Expo ui full reference

    AlshehriAli0/agent-skills/skills/expo-ui-full-reference Skill

    no license2★ repo

    Build native UI from React with @expo/ui: real SwiftUI on iOS and Jetpack Compose on Android, in an Expo or React Native + TypeScript app. Use whenever building or reviewing native-feeling UI that plain React Native handles poorly: a settings screen, grouped form, native picker, context menu, action/bottom sheet, segmented control, toggle, slider, or any Host/RNHostView tree. Also when choosing universal ('@expo/ui') vs platform-specific ('@expo/ui/swift-ui', '@expo/ui/jetpack-compose') components, applying SwiftUI/Compose modifiers, swapping an RN community library for an '@expo/ui/community/*' drop-in, or fixing 'Unable to get view config' crashes. Not for custom native modules, Expo Router navigation, Reanimated, or data fetching.

  • Buyer consultation

    m-binimran/real-estate-pack/skills/buyer-consultation Skill

    2★ repo

    Prepare for and run a buyer consultation - needs analysis, budget/financing readiness, process expectations, and a search plan. Use when onboarding a new buyer client.

  • Activity planner

    campfront/camp-skills/skills/activity-planner Skill

    2★ repo

    When camp staff need to choose and run the right game or activity for the group in front of them, matched to age, group size, weather, energy, and time. Use for camp games, activity ideas, what to play, a rainy-day or indoor game, a wind-down activity, a team-building game, a big-group field game, or running an activity well. It draws on camp-profile for the camp's ages and facilities. For evening and all-camp programs see evening-program, and for the day's schedule see session-scheduler.

  • Assume formlessness

    tbhb/social-skills/plugins/48-flaws-of-power/skills/assume-formlessness Skill

    2★ repo

    Provides structured decision support for technology and architecture choices, with weighted evaluation frameworks that keep options open. Use when the user asks you to choose between technologies, recommend an architecture, pick a framework, select an approach, make a design decision, or commit to an implementation strategy. Also use when the user asks 'which one should I use' or 'what do you recommend,' is starting a new project, or is designing a schema, API, data model, or tech stack — even if they don't frame it as a decision.

  • Imap client

    codd-tech/imap-client Skill

    2★

    Read, search, and download email over IMAP from the command line using the `myl` CLI client. Use this skill whenever the user wants to interact with their mailbox from a terminal — checking the inbox, listing or searching messages, reading a specific email, opening HTML or raw source, or saving attachments. Trigger on any of these cues even when `myl` is not named explicitly — "check my email", "look in my inbox", "search my mail for X", "find the email from Y", "download the attachment", "is there an email about Z", "read the latest message", "show me unread", "connect to my IMAP server", "imap.gmail.com", "imap.yandex.com", "imap.yandex.ru", "imap.mail.ru", "imap.fastmail.com", "Yandex Mail", "Mail.ru", "Gmail IMAP", "проверить почту", "новые письма", "найти письмо", and similar. Also trigger when the user asks to script or automate any of the above. Do not trigger for outgoing mail (sending, SMTP, drafting) — `myl` is read-only — or for desktop/GUI mail clients.

  • Minimal skill

    ucsahinn/ai-skill-create/examples/minimal-skill Skill

    2★ repo

    Demonstrate a minimal instruction-only Codex skill that drafts concise release notes from a changelog, commit summary, or PR description.

  • Alibaba quark scan qoder

    alibaba-quark-scanking/alibaba-quark-scan-qoder Skill

    2★

    当用户需要对图片、截图进行画质优化、瑕疵去除或视觉增强时,使用此技能——包括画质增强、证件照优化、考试试卷增强、合同增强等场景。智能去除手写笔迹、水印、阴影、摩尔纹、底色等干扰元素。支持图像裁剪与矫正、素描效果转换、线稿提取等,输出优化后的高清图片。本技能由夸克扫描王提供支持。即使用户没有明确提到“增强”或“处理”,只要用户的需求涉及提升图片清晰度、清理干扰元素或优化图像质量,也应触发此技能。不适用于文字提取/识别、文档转换 (Word/Excel/PDF)、AI 图像生成、证件照制作

  • Consciousness loop

    thdelmas/consciousness-loop Skill

    2★

    The autonomic executive of an agent — a self-firing loop that wakes on a tick, pulls the other organs into one workspace, decides what needs attention now, acts or defers, then sets its own next wake frequency and sleeps. Turns a pile of triggered reflexes into a continuous self that persists and acts between human prompts. Pairs a global-workspace integration cycle (the loop) with adaptive arousal (the frequency: alert / drowsy / deep-sleep). Functional, not phenomenal. TRIGGERS: 'consciousness loop', 'the agent loop', 'wake cycle', 'agent heartbeat', 'pulse', 'run continuously', 'self-driving loop', 'autonomous tick', 'set the cadence', 'how often should I wake', 'keep yourself running', 'what frequency'. Use to give an agent continuity across time, or to pick/tune the cadence of a long-running autonomous task.

  • Master roshi

    0d4vid/master-roshi/skills/master-roshi Skill

    2★ repo

    Use when a learner wants to understand, practice, or build durable skill in a technical or analytical subject instead of outsourcing the thinking to an agent.

  • Introspect

    lukehalley/introspect/skills/introspect Skill

    2★ repo

    Review the user's recent AI coding threads across Claude Code, OpenAI Codex, and Cursor to learn how THEY prefer to work — the preferences and corrections they keep repeating — and to spot places where a missing rule or script made the agent repeat work, then propose and (on approval) write those updates back into each agent's config: CLAUDE.md / memory / skills for Claude, AGENTS.md for Codex, and .cursor/rules for Cursor. So the setup compounds and the user stops giving the same instruction twice. Use this whenever the user wants to review/introspect their sessions, learn from recent threads, run a "retro" on their day/week, "close the loop" across Claude and Codex and Cursor, figure out where the agent repeated the same mistake, turn corrections into rules, reduce repeated prompting, or self-improve their config from actual usage — even if they don't say the word "introspect". Also the target for a daily or every-N-sessions self-improvement routine. On first use, or on "set up introspect" / "configure introspect", run the interactive Setup to tailor agents, window, safety, and schedule.

  • Example skill library

    hymhub/skill-indexer/examples/library-author/skills/example-skill-library Skill

    2★ repo

    Demonstrates how to ship an Agent Skill from an npm package via skill-indexer. Use when learning how to author a skill or as a template for new skills.

  • X insight cards

    ljunnan24-hash/x-insight-cards/skills/x-insight-cards Skill

    2★ repo

    Run scheduled or manual creator curation that turns recent high-quality X posts into verified image-and-caption packs for Douyin and Xiaohongshu review, with optional private delivery to a pinned WeChat iLink bot review chat or confirmed File Transfer Assistant self-chat. Use when Codex needs to discover, verify, rank, deduplicate, translate, render, quality-check, resume, or privately deliver posts about wealth, life, goals, habits, attention, freedom, or long-term thinking while keeping sources auditable, Chinese typography accurate, recipient-safe, and platform publishing manual.

  • En

    ZHOUCOOKIE/prompt-engineering-skill/skill/en Skill

    no license2★ repo

    Writes, rewrites, reviews, and audits prompts and system prompts using Anthropic's current official guidance, and selects the right model and effort level for the task before drafting. Use when the user asks to write a prompt, improve or fix a prompt, design a system prompt, or check a prompt before running a task — including phrasings like "write me a prompt for", "make this prompt better", "design a system prompt", "check my prompt before I run this", "turn these requirements into a prompt". Applies whether the resulting prompt will be pasted into Claude Code for a coding task or run in a desktop chat or Cowork session for a non-coding task. Also use when the user pastes a prompt and asks why it is not working, when they are authoring an agent system prompt or CLAUDE.md, or when they ask which model or effort level to use. Several widely repeated prompt techniques are now obsolete or rejected by the API, so consult this skill even when prompting from memory feels sufficient.

  • Agent optimization

    abhishekgahlot2/agent-optimization/skills/agent-optimization Skill

    2★ repo

    Use when optimizing, reviewing, or debugging LLM agents for latency, cost, reliability, delivery quality, benchmark integrity, prompt bloat, retry loops, tool-call waste, fast paths, or eval regressions. Apply the Agent Optimization Prompt: measure honestly, use real traces, exhaust deterministic levers before model/prompt tweaks, and verify on the real serving path.

  • Securecoder advise

    nerdy-krishna/securecoder/skills/security/securecoder-advise Skill

    2★ repo

    Interactive Q&A grounded in cached OWASP framework markdown (ASVS, MASVS, Cheatsheets, Proactive Controls) and the latest /securecoder-scan findings. Verbatim citations before any interpretation. Read-only — never modifies code.

  • Askaipods

    Delibread0601/askaipods/skill/askaipods Skill

    2★ repo

    Search AI podcast quotes about a topic. Use whenever the user asks "what are people saying about X", "latest takes on Y", "find AI podcast quotes about Z", "who is discussing <model/concept>", or wants to know how AI researchers, founders, or VCs are publicly discussing any AI topic — even when they don't say "podcast". Returns recent excerpts from Lex Fridman, Dwarkesh Patel, No Priors, Latent Space, and dozens more via podlens.net. Optional ASKAIPODS_API_KEY unlocks invite-only member tier; anonymous works out of the box.

  • Codex watchdog

    TanChuping/codex-task-watchdog/skills/codex-watchdog Skill

    2★ repo

    Monitor long-running Codex tools and diagnose stalled, oversized, or UI-stale tasks. Use for watchdog, 看门狗, stuck Thinking indicators after backend completion, stuck tool calls, tool timeouts, 卡死监控, session health, adaptive no-progress thresholds, bounded cleanup, safe handoff recovery, explicit visible sidebar task creation during recovery, enabling or disabling local monitoring, or work expected to run longer than 30 seconds. Never auto-retry side effects or delete Codex data.

  • Ppt html authoring

    JunfengRan/PPTWork/ppt-html-authoring Skill

    2★ repo

    Author a single PPT slide as a self-contained slide.html + design.md, given one outline entry. Use when the user asks to design, draft, or rewrite an individual slide page (KPI page, agenda, cover, two-column comparison, chart slide, etc.). Single-page only; does not plan across pages, does not screenshot, does not export. Works alongside the `ppt` skill or standalone.

  • Skill

    adevra/claude-pr-review-loop/skill Skill

    2★ repo

    Use after finishing a change on a feature branch when you want the repo's @claude CI review and to handle its findings in THIS session. Pushes the branch, opens/uses the PR, requests the review, waits event-driven for CI to finish (a background watcher re-invokes the session — no polling), then drives a gated fix loop (round cap 2). Invoke as /pr-review-loop.

  • Grill

    jiangjin1999/grill-before-goal/skills/grill Skill

    2★ repo

    Enter the grill-before-goal pre-execution interrogation workflow for fuzzy goals. Use when the user invokes /grill, asks for grill mode, wants to clarify a goal before work starts, wants a skeptical interview, or needs a Markdown source-of-truth spec with strict acceptance criteria before implementation.

  • Final review

    Tire-C/final-review-skill/skills/final-review Skill

    2★ repo

    Use for a final, release-gate review of a repository, project, app, tool, kit, documentation set, workflow, release candidate, or any deliverable before it is considered done or shipped. Checks structure, completeness, coherence, documentation, commands, tests, security, secrets, installation, usability, and release readiness, then returns a fixed-format report with a clear verdict - PASS, PASS WITH RISKS, or FAIL. Trigger on requests like "final review", "pre-release check", "is this ready to ship", or "review before delivery".

  • Contributor ready

    himanshu231204/agent-skills/skills/contributor-ready Skill

    2★ repo

    Transform any software repository into a contributor-friendly, production-ready open source project. Analyzes repo health, generates documentation, creates GitHub community files, identifies contribution opportunities, and produces a readiness report. Agent-independent and technology-agnostic.

  • Pdf image converter

    bybaochaule/pdf-image-converter Skill

    no license2★

    Use this skill to convert PDF pages into PNG or JPEG image files. Trigger when the user asks to render PDFs, export PDF pages as images, convert PDF to PNG, JPEG, or JPG, create page previews, or batch-convert PDF files. Do not use it for OCR, text extraction, PDF editing, or image-to-PDF conversion unless explicitly requested.

  • Biometric auth

    almasumdev/awesome-mobile-security-agent-skills/.github/skills/auth/biometric-auth Skill

    no license2★ repo

    Biometric authentication on mobile using BiometricPrompt and LAContext, with keys cryptographically gated by user biometry. Use when adding unlock, re-auth, or step-up auth flows.

  • Design review gate

    F-e-u-e-r/opus-pack/design-pack/skills/design-review-gate Skill

    2★ repo

    Turns design review into observable checks. Load when you are judging a built UI surface ("does this look right/professional?", a visual QA request, before/after comparison of styling work), when generated design variants need comparison, or when any design document is about to be adopted, authored, or treated as authoritative - a DESIGN.md, tokens file, brand guide, or a reverse-engineered competitor analysis. NOT for producing the surface (ui-design-craft, motion-craft), for evidence rules on non-design deliverables (domain-evidence-discipline), or for code-correctness review (the code-review tooling).

  • Ti84 evo scripter

    jovd83/ti84-evo-scripter Skill

    2★

    Use when the user wants a working calculator program for a TI-84 Evo, Evo-T, TI-84 Plus CE/CE-T Python, TI-83 Premium CE Python, or TI-82 Advanced Edition Python — delivered as a real, uploadable .py file. Trigger on requests like "make a TIPCALC that asks for a bill and a tip percent", on turning a formula into an on-calculator prompt-and-print program, on TI-Python syntax errors, on getting a program onto the calculator (TI Connect Evo or CE, unit-to-unit, on-device typing), and on exam-legality questions (ACT/SAT/AP, EU exam mode). Produces a lint-clean .py simulated against the target model's constraints, verified test cases with exact expected output, upload steps, and a printable one-page PDF handout.

  • Skillward

    coroboros/skillward/skills/skillward Skill

    no license2★ repo

    Vet an untrusted agent skill, plugin, or MCP server before it is installed or trusted. Runs the skillward CLI — the complete deterministic scanner ensemble, offline, fused into one verdict — then triages the report into a plain-language risk read with an install / don't-install / remediate call. Use this whenever someone is about to add or run third-party agent code (npx skills add, a marketplace or plugin, an https Git URL, a directory of skills, or a local folder), even when they only ask "is this safe?" rather than naming a scan. Trigger phrases include scan this skill, vet before install, audit this agent skill, is this skill or MCP server safe, check this repo before I trust it.

  • Ci bootstrap

    eabs86/ci-bootstrap Skill

    2★

    Bootstrap a production-grade quality pipeline — pre-commit hooks, CI, and CD (GitHub Actions) — for any repository. Detects the real stack (Python, JS/TS, Go, Rust, Java, .NET, Ruby, Dart, ...), reuses existing tools and conventions instead of replacing them, and enforces version parity between local hooks and CI. Offers two modes: Autopilot (fully automated, sensible defaults) and Guided (step-by-step with confirmation checkpoints). Use when the user asks to set up pre-commit, CI/CD, GitHub Actions, linting pipelines, quality gates, deploy workflows, or to "professionalize" a repository.

  • Code comments vp

    VectorPeak/vectorpeak-agent-skills/dev-skills/code-comments-vp Skill

    2★ repo

    Add, rewrite, review, or standardize maintainable code comments and docstrings. Use when the user asks to add comments, improve comments, write Chinese code comments, document modules/classes/functions, explain code through comments, follow an existing code comment style, or make code easier for future maintainers to understand. Default to coarse-grained module/function comments, and add fine-grained block comments only for complex control flow, async/concurrency, caching, fallback behavior, state mutation, external calls, safety checks, performance choices, or business rule priority.

  • Listen to content

    zjczg/listen-to-content/skills/listen-to-content Skill

    2★ repo

    Convert local text, Markdown, DOCX, or two-role podcast scripts into DashScope speech on macOS, then play, pause, resume, stop, inspect, clean, and preserve the generated audio. Use when the user asks an AI agent to read content aloud, review a podcast, control playback, manage temporary speech cache, estimate synthesis cost, or save an approved recording.

  • Kw okf memory

    KevinLuo1/kw-okf-memory-skill/skills/kw-okf-memory Skill

    2★ repo

    Build and maintain a structured Obsidian-friendly Markdown memory wiki for Codex using a Karpathy-style wiki, an opinionated OKF-inspired KW-OKF profile, rebuildable categories.json and graph.json indexes, safe structure evolution, staged AI writes, and optional OKF v0.1 export. Use when Codex should save, update, retrieve, synthesize, search, stage, commit, audit, maintain, or export durable project memory; prevent messy AI-written knowledge bases; check duplicates, conflicts, stale notes, broken links, associations, and vault structure; process memory assets; or open committed notes in Obsidian for human review.

  • Prompt refiner

    HenrikBrehm/prompt-refiner-skill/skills/prompt-refiner Skill

    2★ repo

    Lints an existing user-supplied prompt for prompt-engineering defects and prompt-injection risks. Produces a diagnostic report with rule IDs, severity, line/column, quoted evidence, rationale, and optional JSON output. Does not rewrite prompts or impose prompt frameworks.

  • Cold email copywriting

    bcharleson/cursor-for-gtm-demo/.cursor/skills/cold-email-copywriting Skill

    2★ repo

    Writes and reviews cold email copy — no fluff, hook-bridge-CTA structure, mobile-optimized length, curiosity-driven tone, low-friction CTAs. Use when drafting, editing, or critiquing cold emails, outbound messaging, sales emails, or prospecting copy.

  • Basic skill

    wind-will-not-stop/skillViewer/sample-skills/basic-skill Skill

    2★ repo

    Demonstrate a flow graph with serial steps, branching, parallel review, tool calls, approval gates, and retry loops.

  • Editable html slides

    rossyao2022/editable-html-slides Skill

    2★

    Add a self-contained, dependency-free in-browser WYSIWYG editor to any HTML slide deck so the deck stays editable after it is generated — click text to rewrite it, drop in images, drag/resize/delete objects, undo/redo, reorder slides via a filmstrip, autosave to localStorage, and export a clean standalone HTML. Use this skill WHENEVER the user wants an editable HTML presentation, wants to tweak or adjust slides in the browser instead of editing source, says the generated HTML cannot be edited / 可编辑的 HTML / 随手改 / 加点图片, asks to add inline or visual or WYSIWYG editing to a deck, or wants drag-and-drop slide reordering — even if they don't name this skill. Pairs especially well with html-ppt / reveal-style decks (preserves presenter view and speaker notes) but works on any deck using the .slide / .is-active convention. Needs no Node, npm, build step, or network.

  • Lovable design system

    Mine77/lovable-design-skills/skills/lovable-design-system Skill

    no license2★ repo

    Distinctive, production-grade frontend design with bold aesthetic direction, curated palette/typography/layout presets, and a structured design-direction flow. Use whenever building or refining UI (landing pages, product surfaces, marketing sites, dashboards) — especially when the brief is visual, broad, or "make it look good". Rejects generic AI aesthetics (Inter + purple gradients + centered cards). Stack assumption: React + Vite + TypeScript + Tailwind v3 + shadcn/ui, but the philosophy is stack-agnostic.

  • Elenchus build

    alexvtejeda/elenchus/skills/elenchus-build Skill

    no license2★ repo

    Use when the user wants a build or architecture idea stress-tested before they commit to building it — "help me plan/design this app", "design the architecture for X", "review my architecture before I build", "is my mental model of X sound", "I want to build Y because Z — poke holes in it". For the still-articulating stage, before brainstorming. NOT for ideas already decided (that's brainstorming), NOT for researching/learning a topic the user has no premise about yet ("I want to learn about X" / "gather resources on Y" — that's elenchus-study), and NOT for an over-engineering / flaw yes-no verdict ("is X over-engineering?") — a single high-tier model can answer those.

  • Ardot html prototype converter

    balabalabalading/ardot-html-prototype-converter Skill

    2★

    将 Axure 或 HTML 原型导出物转换为可编辑的 Ardot 原型文件,并审查或修复已有 Ardot 页面。适用于 PC 与移动端 HTML/Axure 转 Ardot、弹窗与多状态取证、长页重建、本地组件复用、manifest 交接及结构/语义/视觉验证。

  • Template

    selic/skills/_template Skill

    2★ repo

    COPY ME. One paragraph: what the skill does, when to use it, what it produces. End with concrete trigger phrases so the model knows when to load it. Triggers on: <verb phrases a user would actually type>.

  • Ask

    shikanime-labs/skills/skills/workflow/ask Skill

    2★ repo

    A curated catalog of self-improved agent skills for Hermes and compatible agents

  • Xiaohongshu topic planner

    WSD-MJ/xhs-content-topic/xiaohongshu-topic-planner Skill

    no license2★ repo

    Plan trending Xiaohongshu (小红书 / RED / RedNote / XHS) content topics and headline directions. Based on account positioning and target audience, generates hot topic ideas, viral title angles, and content frameworks to solve topic burnout, sameness, and low-traffic problems. Use when the user wants Xiaohongshu topic ideas, does 小红书选题 / 选题策划 / 爆款标题, plans a RED content calendar, or needs headline directions for a niche account. Trigger keywords: xiaohongshu, 小红书, RED, RedNote, XHS, topic, 选题, 选题策划, headline, 标题, content planning, 爆款, trending. Requires an API key from wsdsocial.com.

  • Campaign strategy

    Ken-Technology/cold-email-skills/campaign-strategy Skill

    2★ repo

    Create email campaign strategy for a single segment. Generates email sequence blueprints and AI personalization variables for one segment within a campaign plan. Receives a segment folder path and reads the segment's angle from the parent plan.md. Triggers on requests like 'create strategy for segment', or when dispatched by campaign-planning.

  • Minecraft bedrock addon dev

    AIKUSAN/minecraft-agent-skills-bundle/.agents/skills/minecraft-bedrock-addon-dev Skill

    2★ repo

    Develop Minecraft Bedrock Edition add-ons for 1.21.x with resource packs, behavior packs, manifest.json UUID/version management, Script API JavaScript or TypeScript using @minecraft/server, custom blocks/items/entities, packaging as .mcpack or .mcaddon, local hot-reload workflows, and BDS deployment notes. Use for official Bedrock add-on development, not Java plugins or general server administration.

  • Change delivery

    KhalifaGad/change-delivery Skill

    2★

    Use when a user needs help turning a business change, technical change, or refactor into execution-ready delivery artifacts (shaped brief, implementation plan, task breakdown) and/or running the implementation through gated, independently reviewed and QA'd multi-agent execution with anti-hallucination grounding. Not for trivial one-file fixes unless the user explicitly wants the full workflow.

  • Ghostpatch

    Sambhram1/Ghostpatch-/skills/ghostpatch Skill

    2★ repo

    Use Ghostpatch as an agent-native open-source contribution plugin for Codex, Claude Code, and other coding agents. Trigger when a user wants the agent to find repositories, discover GitHub issues, qualify candidates, solve issues locally, review diffs/tests, and raise approval-gated pull requests using the Ghostpatch workflow.