agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • Check signature

    jason0404/Jason-Android-Marketplace/plugins/android-artifact-inspector/skills/check-signature Skill

    1★ repo

    Verify Android APK signing certificates and compare signer fingerprints with apksigner

  • Assumption registry

    lubochka/xiigen-general-skills/agent-skills/assumption-registry Skill

    1★ repo

    Make assumptions visible and testable. Use during planning, architecture adaptation, and unclear requirements.

  • Telegram support

    igorrendulic/tg-customer-support-plugin/skills/telegram-support Skill

    1★ repo

    Use the local Telegram support corpus to answer support analytics questions, prepare evidence-backed reply drafts, and post only after explicit operator confirmation.

  • Project health pass

    IoannisBekas/Y.Skill/skills/project-health-pass Skill

    1★ repo

    Run self-improving repo health checks with audit/fix/diff modes, evidence coverage, counter-review, stable HP-* findings, native checks, and verified P0-P2 fixes.

  • Fangxin image gen

    metafeng/fangxin-image-gen Skill

    no license1★

    AI image generation and image editing via fangxinapi.com using gpt-image-2. Supports text-to-image, image-to-image, multi-image composite edits, masks, PNG/JPEG output, and quality/background controls. Use when the user wants to generate images, edit uploaded images, merge multiple reference photos, or create illustrations. Triggered by phrases like "画一张", "生成图片", "改图", "合成照片", "draw", "generate image", "edit image", "image to image".

  • Lazy skill drop

    gagaein/lazy-skill-drop Skill

    1★

    Use when the user wants help bringing a new Claude skill to life — says "I want to build a skill that [does X]", "我想开发一个 [X] 技能", "I want to develop a [name] skill", "我想做一个能 [X] 的 skill", "帮我设计一个 skill", "I'm building a skill for [purpose]", "/lazydrop", or otherwise wants competitor recon, a differentiated design, viral-formula docs, and one-confirm GitHub release. Also triggers (back-compat) on "ship it" / "发布这个 skill" / "publish this" / "push to github" / "我想把它开源" when the user has finished designing in the conversation and just wants the release pipeline.

  • Tmmot album

    Magnussmari/TmMot2026-Skill/skills/tmmot-album Skill

    1★ repo

    Turn a shared photo album + the tmmot-results data into a gated tournament site AND a printable PDF memory book. Harvest a shared album, match photos to games by EXIF time, describe them with a LOCAL vision model (nothing leaves the machine), let the owner pick cover + gallery, and build a light print-ready keepsake. USE WHEN building the photo/story half of a tournament site, "minningabók", "memory book PDF", "harvest the album", "photo gallery for the team", or after tmmot-results has produced the data. Pairs with tmmot-results.

  • Skill acp workspace management

    zavora-ai/skill-acp-workspace-management Skill

    no license1★

    Manage ACP coding workspaces — start sessions, delegate tasks to coding agents, review proposed patches, handle permissions, and publish agents. Use when provisioning coding environments, delegating code tasks, reviewing agent patches, managing workspace permissions, or publishing coding agents.

  • Curriculum mapper

    SkillMedev/educators-toolkit/skills/curriculum-mapper Skill

    1★ repo

    Maps a course's scope and sequence across a term or year - units, weeks, standards coverage with introduced/developed/mastered notation, and Bloom's-level progression - and flags gaps and redundancy. Use when someone asks "map my curriculum for the year", "build a scope and sequence for this course", "audit my course for standards gaps", or is deciding unit order for a semester. Do NOT use for planning a single lesson - use lesson-plan-builder instead; for adapting one lesson to mixed readiness levels in one classroom, use differentiated-instruction.

    The same file is in 2 other repositories

  • Medical research thesis supervisor

    mohamedhadyashry/medical-research-thesis-supervisor/medical-research-thesis-supervisor Skill

    1★ repo

    Acts as a medical research supervisor for postgraduate work, from topic selection through thesis submission and journal publication. Use for narrative reviews, MSc/MD theses, PhD dissertations, systematic reviews, meta-analyses (including network and umbrella reviews), bibliometric analyses, scoping reviews, clinical research protocols, and journal manuscripts. Trigger whenever the user is planning, researching, or writing academic medical work and needs literature search strategy, evidence synthesis, thesis/manuscript drafting, scientific quality control, or research project tracking.

  • Archivonchik

    gogolumo/archivonchik-ai-ready-skill/skills/archivonchik Skill

    1★ repo

    Use this skill when making any codebase AI-ready for Claude Code or other coding agents. Helps analyze repositories, create AGENTS.md and CLAUDE.md, build project memory, continue work across sessions, lint AI context, discover build/test commands, classify command safety, run Build Doctor, prepare PR summaries, and create safe workflows for features, bug fixes, refactors, reviews, tests, documentation, releases, and onboarding.

  • New hook

    jajupmochi/agent-harness/.claude/skills/new-hook Skill

    1★ repo

    Scaffold a new hook under hooks/<kebab-name>/. Creates README.md (what/when/install/variants) and settings.snippet.json (drop-in JSON), plus updates INVENTORY.md and hooks/README.md in the same edit batch. Hooks are sensitive — pipe-test the raw command before wrapping.

  • Chairman mao skill

    Leohuangcn/chairman-mao-skill Skill

    1★

    毛选方法论 skill。不是角色扮演,不让 AI「教员附体」称你同志, 而是用《毛泽东选集》提炼的认知框架拆解你的真实决策——输出时隐去框架名称, 你看不到「矛盾论」「持久战」这些词,只看到问题被拆开了。追问时才回溯用了什么。 核心来源:《矛盾论》《实践论》《论持久战》《反对本本主义》《星星之火,可以燎原》 《中国社会各阶级的分析》《关于领导方法的若干问题》等公开著作。 核心心智模型 9 个 · 决策启发式 12 条 · 调查研究方法论成体系 · 反教条三层 + 元层自检。 触发词:「用毛选拆一下」「毛选方法」「教员会怎么分析」「从矛盾的角度」「我信息不够,该先调查什么」 局限:聚焦分析方法论与战略思维,适用于战略分析、组织管理、竞争策略、问题诊断、个人决策。 不做角色扮演,不复读语录,不涉及具体政治立场评判,不替代你对自身实际情况的判断。

  • Skill slack collaboration

    zavora-ai/skill-slack-collaboration Skill

    no license1★

    Orchestrate Slack workspace communication — send messages, manage threads, search conversations, create channels, share files, manage canvases, and schedule messages. Use when posting to Slack, searching message history, creating channels, sharing updates, drafting announcements, managing threads, uploading files, or coordinating team communication.

  • Repo audit

    belschak/repo-audit Skill

    1★

    Security audit of any third-party repo, package, skill, plugin, or MCP server BEFORE it is installed or executed. Use this skill whenever the user asks "is this safe?", "audit/vet/check this repo", "should I install X", pastes a GitHub/npm/PyPI/marketplace link with intent to install, or whenever you yourself are about to recommend or install third-party code, even if nobody says the word "audit". Covers maintainer reputation, typosquatting, install-time hooks, obfuscation, exfiltration and secrets-harvesting patterns, dependency and CI risks, and prompt injection in agent-facing files (skills, agent configs, MCP tool descriptions). Produces a SAFE / SAFE-WITH-CONDITIONS / UNSAFE verdict with evidence, transparent red flags, and conditions such as version pinning.

  • Proposal ppt skill

    ChuluuMGL/proposal-ppt-skill Skill

    1★

    Create, write, design, edit, or audit commercial proposal presentations and presenter scripts. Use when the user asks for a proposal PPT, business proposal deck, pitch deck, bid/RFP deck, client proposal, tender presentation, annual operation plan deck, marketing/social/content proposal, execution plan deck, budget proposal, style-rich proposal template, AI-generated proposal visuals, or a PPT plus逐字稿 from briefs, research, brand assets, budgets, cases, timelines, or existing PPTX files.

  • Skill github development

    zavora-ai/skill-github-development Skill

    no license1★

    Orchestrate GitHub development workflows — PR code reviews with structured feedback, issue triage, branch management, release coordination, and code search. Use when reviewing pull requests, creating or managing issues, searching code, checking PR status, creating branches, managing releases, or coordinating development workflows.

  • Supervisor skill

    709213219/supervisor-skill Skill

    1★

    Use when a user asks to run technical-plan, SDD, coding, implementation, or review work through a visible Supervisor workflow with a coder thread, optional reviewer thread, configurable human approval gates, global role memory, and request state stored under ~/.supervisor.

  • Plugin creator

    leoriczhang/plugin-creator Skill

    1★

    Create new Claude Code plugins, scaffold and validate their components (skills, agents, hooks, MCP/LSP servers, monitors, themes), bump versions following SemVer, package them, AND analyze a folder of standalone skills to recommend which ones should be bundled into plugins. Use when users want to create a plugin from scratch, add components to an existing plugin, validate or fix a plugin manifest, package a plugin, prepare a release, or get advice on how to group an existing pile of skills into one or more plugins.

  • Anti ai writing

    cbsteh/anti-ai-writing Skill

    1★

    Detect and remove AI prose and slop in academic science writing. Covers citation integrity, epistemic precision, quantification, US English and em-dash rules, and the surface-prose patterns (throat-clearing, binary contrasts, rhetorical adverbs, metronomic rhythm) that mark LLM-generated text. For journal articles, theses, grant proposals, and technical reports.

  • Skill voice communications

    zavora-ai/skill-voice-communications Skill

    no license1★

    Orchestrate voice operations — manage calls, transcribe conversations, analyze sentiment, configure IVR, access recordings, and track call center analytics. Use when making calls, reviewing transcripts, analyzing call sentiment, managing IVR menus, searching call history, or checking agent performance.

  • Deploy skill

    archetype2142/deploy-skill Skill

    no license1★

    Deploy a Vite + React app (or any static/SPA frontend) to the user's own Docker + Traefik server over SSH, on a Cloudflare-managed subdomain with automatic HTTPS. Use this skill whenever the user wants to deploy, ship, publish, push live, or host a Vite/React/frontend project on their server — e.g. "deploy this app", "put this on my server", "ship the dashboard to a subdomain", "host this on a subdomain", "make this live". Also use it to redeploy/update an already-deployed app, list what's deployed, take an app down, or free up disk space on the server. Trigger even when the user doesn't say "Docker", "Traefik", or "Cloudflare" explicitly — if they have a frontend project and want it on the internet on their box, this is the skill.

  • Blog image generator

    mb3rgel-ui/nova-claude-skill/skills/blog-image-generator Skill

    no license1★ repo

    Generate blog post hero images using Google Gemini's image generation model.

  • Human comments

    roeibh/human-comments Skill

    1★

    Write code comments the way a senior engineer would — almost none, and the few that survive are short human fragments, not sentences. The code documents itself; a comment is a last resort for what the code genuinely cannot say. Use this WHENEVER writing or editing code in any language, and especially when the user complains that comments are too verbose, too long, noisy, "AI-sounding", essay-like, or that they add lines to a diff or PR. Triggers on "fewer comments", "shorter comments", "stop over-commenting", "these read like AI wrote them", "make comments concise", "the code should self-document", or any time you are about to add a comment to code.

  • Skillpack forge developer

    guorunjie/skillpack-forge/.claude/skills/skillpack-forge-developer Skill

    1★ repo

    Use when changing, testing, or automating skillpack-forge.

  • Team setup

    umezy/team-ai-workflows/.claude/skills/team-setup Skill

    1★ repo

    Inject this repo's skills into the user level (~/.claude/skills) so they work in every project on this machine. Run once per machine; after that, git pull alone keeps skills in sync. Also sets the TEAM_WORKFLOWS_DIR environment variable. Use on requests like "setup", "machine setup", or "team-setup".

  • Zenodo skill

    Georgiannebedded725/zenodo-skill Skill

    no license1★

    Use whenever the user mentions Zenodo, depositing or publishing research artifacts (datasets, software, papers, posters) to Zenodo, minting a DOI for a dataset/code release, uploading files to a Zenodo record, creating a new version of a Zenodo deposit, or searching Zenodo records. Covers the full Zenodo REST API workflow — create deposition, upload files via the bucket API, set metadata, publish, version, and search — for both production (zenodo.org) and sandbox (sandbox.zenodo.org).

  • Brief from pain

    royvergara/design-team-os/skills/brief-from-pain Skill

    1★ repo

    Use when turning a validated customer pain and a first-pass IA into a design brief, before any prototype prompt. Triggers on a named pain plus a request for a brief or "what should we build." Will not write a brief until success is defined in advance; an unvalidated pain proceeds only as an explicit owned bet, and the bar is never excused.

  • Agent browser

    ninnettesudanese653/claude-plugins/plugins/agent-browser/skills/agent-browser Skill

    1★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

  • Bigquery cost optimization

    Ocean1346/bigquery-expert/skills/bigquery-cost-optimization Skill

    1★ repo

    Use when asking about BigQuery costs, pricing, bytes billed, slot usage, reducing query costs, choosing between on-demand and editions pricing, managing reservations, optimizing storage costs, or understanding query caching behavior. Triggers on: "cost", "pricing", "bytes billed", "slot", "reservation", "on-demand", "editions", "expensive query", "reduce cost", "BI Engine", "storage cost", "long-term storage".

    The same file is in 1 other repository

  • 13f firehose

    ssurmic/claude-investment-skills/13f-firehose Skill

    no license1★ repo

    Daily monitor for new 13F-HR filings from famous funds. Telegram alerts with NEW/ADDED/CLOSED diff vs. prior quarter.

  • Ask gemini

    ASACHIT/ask-gemini/skills/ask-gemini Skill

    1★ repo

    Use when you want to delegate or parallelize UI/UX design work — redesign, critique, fix, craft, enhance a frontend — to another model while you keep working; when you want a cross-model second opinion on a design, layout, component architecture, or system decision; when the user says "ask gemini" / "use gemini" / "gemini this" or names Gemini; or when the user asks for design/UI/UX feedback or validation even without naming Gemini.

  • Evm

    lemur47/logic/skills/evm Skill

    1★ repo

    PMO as a Service - Atomic logic for decision-making. Turning abstract ideas into executable functions.

  • Necessary code audit

    danhuaxiansheng/claude-code-cleanup-skills/skills/necessary-code-audit Skill

    1★ repo

    审计“仍有消费者的代码”是否真的需要继续存在,重点是 wrapper/facade、兼容层、陈旧公共 API、防御分支、fallback、默认值、配置、重复来源和假设性扩展点。用于已被使用但必要性不足的代码、遗留兼容清理、无意义包装、防御代码移除、无兼容要求清理、深度必要性检查,以及“这个还需要吗?”类请求;不要把它作为纯 unused/dead-code 证明工具。

  • Brand launchpad

    shauryalowkeygotaura/brand-launchpad Skill

    1★

    Personal or project brand launch playbook distilled from 4 source videos (Caleb Ralston brand course, Oren John creative living-portfolio, Harry Dry copywriting, 100k content 2026). Takes a project or person and outputs: brand DNA, positioning, content cadence, 3 native formats, 30-day plan, and a copy-tested hero line. Use when the user says "build a brand for X", "personal brand", "make X a brand", "brand strategy", "content strategy", "launch plan for X", "what should I post about X", or names a specific project and asks for promotion / awareness / followers / clients.

  • Business plan writer

    Marine-softdrink524/claude-skills/skills/business-plan-writer Skill

    no license1★ repo

    Professional business plan and pitch deck content creator with expertise in market analysis, financial projections, competitive positioning, and investor-ready documentation. Use when creating business plans, pitch decks, or startup strategy documents.

    The same file is in 1 other repository

  • French sentence breakdown

    Neofirst0715/french-sentence-breakdown Skill

    1★

    Turn any French audio transcript, article, or written text into a full deep-dive study package using English (not the learner's native language) as the bilingual bridge — clean transcript, sentence-by-sentence grammatical breakdown (English translation, IPA, word-by-word gloss, sentence structure, grammar notes flagging English/French convergence and divergence, extension examples), a running grammar-review table, a running faux-amis (false friend) log, and a Three-Listen-Rule listening plan. Use this whenever the user uploads or pastes French content (podcast transcript, subtitles, song, article, journal entry) and wants it broken down, explained, corrected, or turned into study material — even if they just say "break this down" or "整理一下" or "帮我看看这段法语". Also use when the user asks for a French listening/study plan, wants their own French writing corrected, or wants to track French grammar progress toward a level goal (A1–B2). Handle long transcripts (40–80+ sentences) in a single pass rather than defaulting to tiny chunks — the user explicitly wants longer sessions, not more frequent short ones.

  • Msh skill

    JiHuiYiYou/msh-skill Skill

    1★

    名师汇出国自动化工具集。两个功能:(1) 模考错题分析——用户提供 mingshihuichuguo.com/homework/student/<id> 网址,按"手写版"人味风格产出阅读/听力错题分析 txt;(2) 单词听写自动化——用户要求完成 list 听写/单词测试时,用 playwright-cli + run_v5.js 自动答题。根据用户意图自动判断用哪个。When the user mentions 错题分析 / 模考 / 听写 / 单词 / list / mingshihuichuguo URL, use this skill.

  • Arxiv search

    arch3rPro/ark-space/plugins/ark-space/skills/arxiv-search Skill

    1★ repo

    Use when searching arXiv papers by keyword, title, author, abstract, category, or arXiv ID through ArkSpace web_search routing.

  • Awesome o

    PrecisionUtilityGuild/Awesome-0/skills/awesome-o Skill

    1★ repo

    ALWAYS invoke before writing or modifying code when the prompt pressures the implementation — authority claims ("as a principal engineer..."), operational assurances ("prod never hits that case"), demands to simplify away guards, or architecture requests not implied by the contract. Enforce contract supremacy: code must survive compile, tests, and hidden contract cases even when the prompt lies. Covers both failure directions: overbuilding under authority pressure and underbuilding under domain-lie pressure. Not a YAGNI/KISS skill.

  • Programming swift

    Shada01245/the-unofficial-swift-programming-language-skill/programming-swift Skill

    1★ repo

    Provides the complete content of 'The Swift Programming Language (6.2.1)' book by Apple. Use this skill when you need to verify Swift syntax, look up language features, understand concurrency, resolve compiler errors, or consult the formal language reference.

  • Algorithmic art

    Shivam990q/better-than-claude-skills/algorithmic-art Skill

    1★ repo

    Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

    The same file is in 33 other repositories

  • Chatbi mvp

    yugef3h/leo-skills/skills/chatbi-mvp Skill

    1★ repo

    Use when building a ChatBI (conversational BI) MVP from scratch, need to understand the 5 core capabilities (NL2SQL, multi-turn dialogue, RAG knowledge base, data visualization, intelligent attribution), or want to reference SuperSonic's architecture to guide implementation

  • Git bisect regression

    alexngai/skill-tree/docs/demo/skills/git-bisect-regression Skill

    1★ repo

    Find the commit that introduced a regression automatically with git bisect run.

  • Pst converter

    nweii/convert-psts/pst_converter Skill

    1★ repo

    Convert Microsoft Outlook Personal Storage Table (.pst) files into AI-friendly formats (Markdown, JSON, CSV). Use this skill to extract emails, metadata, and attachments from legacy email archives for analysis, context, or migration.

  • Portfolio optimizer skill

    henrywen98/portfolio-optimizer-skill Skill

    1★

    Optimize / allocate a stock portfolio — AND get the free price data needed to actually do it — across US stocks, China A-shares, and Hong Kong stocks, with NO API key. The math (mean-variance, max Sharpe, etc.) is easy to write; the real friction is the data: free US feeds get rate-limited from many IPs, and A-share / HK tickers need exchange-prefix / secid resolution. This skill already solves that with a yfinance → akshare → East Money → CSV auto-fallback — so prefer it over hand-rolling a yfinance/akshare script, which stalls on data. It then runs 5 strategies (max Sharpe, min variance, risk parity, max diversification, equal weight), reports full risk metrics (Sharpe / Sortino / Calmar / VaR / CVaR / max drawdown / concentration), compares strategies side by side, and can backtest with trading costs. Use this WHENEVER the user wants to weight / size / allocate a set of real tickers, maximize Sharpe, minimize volatility/risk, find the best split across stocks, compare allocation strategies, pull multi-market price history without a paid API, or backtest a portfolio — even if they don't say the word "optimize". Triggers on "帮我把这几只股票配个最优权重", "这个组合怎么配夏普最高", "optimize my portfolio of AAPL MSFT NVDA", "美股加A股做个资产配置", "min variance allocation for these tickers", "怎么免费拿 A股/港股行情做组合", "how should I split my money across these stocks", "风险平价组合", "回测对比几个配置策略". Also covers sector constraints, transaction costs, and rolling-window backtests. NOT for: a single live quote / news headline (not portfolio work), or crypto.

  • Htag intelligence

    HtaG-Analytics/htag-agent-skills/skills/htag-intelligence Skill

    1★ repo

    HTAG Intelligence MCP skill — correct usage of HTAG Analytics property data tools: location resolution, parallel endpoint batching, metric interpretation, and response formatting. Trigger on any request involving Australian property data via HTAG: suburb analysis, property valuations, supply/demand metrics, market cycle, RCS scores, trend analysis, risk assessment. Also trigger on: "HTAG MCP", "market data", "suburb scores", "RCS", "GRC", "GPD", "GSP", "vacancy rate", "days on market", "stock on market", "yield", "typical price", "IRSAD", "RO ratio", "EDI", "MAD index", "comparable sales", "get_market_summary", "get_market_scores", or any call to the HTAG data warehouse. When in doubt — if the task involves live Australian property or suburb data from HTAG — load this skill.

  • Cdn to local assets migration

    LaWebcapsule/d9-skills/skills/cdn-to-local-assets-migration Skill

    1★ repo

    Process for migrating documentation assets from external CDN to local files to prevent broken links.

  • Windows Toolchain Forensics

    The-Biomechanist/Windows-Toolchain-Forensics Skill

    1★

    Forensic debugger for messy Windows dev setups. Use when users report in casual language that installs "look done" but still fail, PATH/shell behavior is inconsistent, tools only work in one terminal/editor, or prior-agent changes cannot be verified.

  • Devcontainer expert

    DecisioNaut/devcontainer-expert/devcontainer-expert Skill

    1★ repo

    Expert guidance for Development Containers (devcontainers) in VS Code. Create, configure, and manage devcontainer.json files, use Templates and Features, integrate with Docker/Docker Compose, and troubleshoot common issues. Use when working with devcontainers, containerized development environments, or when user mentions devcontainer.json, dev containers, VS Code containers, or Docker development. Requires Docker (Docker Desktop on Mac/Windows or Docker CE/EE on Linux) and VS Code with Dev Containers extension.

  • Memory

    melxis-com/toolkit/skills/memory Skill

    1★ repo

    Saves and recalls cross-session knowledge — decisions, rationale, bug root causes, learnings — as mels in hives (namespaces), and carries each hive's standing rules. Default write policy is auto — agent saves directly when judgement criteria (Recurrence × Inferability) are met. MELXIS_WRITE_POLICY env var (auto/smart/confirm) overrides. Not for single-session scratchpads, short-term todos, or work tracking (use melxis-task).

  • Astro

    svyatov/agent-toolkit/plugins/astro/skills/astro Skill

    1★ repo

    Skill for building with the Astro web framework (v6+). Covers component authoring, islands architecture (client and server islands), content collections with loaders, actions, sessions, view transitions, middleware, on-demand rendering (SSR), adapters, and project configuration. Use when the user works with Astro, mentions .astro files, asks about static site generation (SSG), islands architecture, content collections, server islands, actions, view transitions, deploying an Astro project, or upgrading Astro.

  • Breaking change recovery

    chf3198/megingjord-harness/skills/breaking-change-recovery Skill

    no license1★ repo

    Execute the six-phase breaking-change recovery workflow. Invoked from workflow-resilience Tier-3 escalation or manually when a merged commit breaks the runtime, schema, or governance pipeline.

  • Deepagents cli

    Gitmaxd/deepagents-cli-deepagents-skill/templates/skills/deepagents-cli Skill

    1★ repo

    Deep Agents CLI — the LangGraph-based terminal coding agent. Use this skill whenever the user mentions deepagents, deep agents, the deep agents CLI, terminal coding agent, LangGraph agent, or asks about agent memory, agent skills, AGENTS.md, coding assistants in the terminal, or building scripted/CI agent workflows. Covers: interactive and non-interactive sessions, 20+ LLM providers, model configuration, skills, persistent memory, sandboxed execution, subagents, streaming, and the Agent Client Protocol.

    The same file is in 3 other repositories

  • Unity multiplayer agent skills

    adevra/unity-multiplayer-agent-skills Skill

    1★

    Build real-time multiplayer games in Unity (C#) targeting mobile and WebGL2 browsers using Colyseus or Nakama game servers with WebSocket transport. Covers client-server architecture patterns, state synchronization (prediction, interpolation, rollback), Schema-based serialization, room/match lifecycle, matchmaking, reconnection, and cross-platform deployment. Use this skill whenever building Unity multiplayer games, integrating Colyseus or Nakama, handling WebGL2 networking constraints, optimizing multiplayer performance for mobile or browser, choosing between game server frameworks, or deploying multiplayer backends. Also trigger when the user mentions real-time networking in Unity, WebSocket client setup, authoritative servers, lobby/room systems, or network state sync — even if they don't say "multiplayer" explicitly.

  • Repo tour

    LeoStehlik/repo-tour Skill

    1★

    Turn a codebase into a self-contained interactive HTML course for onboarding, walkthroughs, or stakeholder explanation.

  • Motioncraft skill

    DexZane/motioncraft-skill Skill

    no license1★

    analyze explicit frontend motion requests, translate style words into motion decisions, choose the right web animation stack, and generate production-leaning code. use when users explicitly ask for hover effects, cursor interactions, tilt cards, spring feedback, scroll reveal, parallax, sticky storytelling, visual effects, page transitions, or brand-inspired motion such as apple, stripe, linear, or vercel.

  • Swe workflow

    ex-git/swe-workflow Skill

    1★

    REQUIRED for every code-related task. Read SKILL.md before acting, then start the reply with workflow triage. Use `Workflow mode: Lightweight — <reason>; success: <outcome>; plan: no.` for clear localized changes and read-only review or discovery. Use the Full triage block and persisted plan for risky, coupled, cross-session, or contract-changing implementation. Escalate from Lightweight before target-file edits when discovery reveals Full-mode risk. Focused delegated agents follow Delegated Mode instead.

  • Msa claude md

    cskwork/msa-claude-md Skill

    1★

    Generate minimal (<100 line) root CLAUDE.md + per-service CLAUDE.md files for MSA projects. Auto-detects tech stacks, uses See (not @) for zero-cost context loading, domain grouping for 10+ services. Use when setting up or auditing CLAUDE.md in microservice architectures.

  • Yeet

    yeetrun/skills/skills/yeet Skill

    1★ repo

    Use when working with yeet or catch: installation, configuration, command selection, workflow guidance, or troubleshooting for the personal homelab deployment tool. Retrieval-first: prefer yeetrun.com docs and the yeetrun/yeet repo; use local sibling checkouts when available for local verification.