agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • 00 INDEX

    ABQ-Institute/euai_act-compliance-skills/EUAIA/00_INDEX Skill

    no license1★ repo

    EU AI Act compliance skills for AI agents — role-aware, risk-tiered, LLM-agnostic. CC BY 4.0.

  • Deep context

    googlarz/deep-context Skill

    no license1★

    Build a verified, comprehensive context pack from a folder of ~200 or fewer text files. Use when the user asks to "scan a folder", "build context for", "ingest", or pass a folder path to thoroughly understand. Produces `.context/INDEX.md` + `.context/DIGEST.md` + per-file notes with explicit completeness checks, citations, contradiction detection, and self-test calibration. Caches via SHA-256; re-scans only changed files when last run hit 100% coverage.

  • Clain classify

    drai-inn/clain/skills/clain-classify Skill

    1★ repo

    Use when the developer wants a categorical inventory of one workspace or a tree of workspaces — e.g. "classify my dev directory", "what's regenerable in this project?", "what kinds of subtrees are in this workspace tree?", "run clain classify --here". Surfaces cache-managed / ephemeral / bytecode / workspace-source tags and reports which workspaces sit inside a synced (e.g. GDrive / OneDrive / Dropbox / iCloud Drive) tree.

  • Run dokploy mcp

    ppezzull/use-dockploy-mcp/skills/run-dokploy-mcp Skill

    1★ repo

    Deploy, manage, and monitor services on Dokploy via MCP tools. Use when deploying apps, checking logs, managing domains, updating environment variables, or inspecting container status on the Dokploy host.

  • Antigravity

    RagavRida/agentsmcp/skills/antigravity Skill

    1★ repo

    Persistent context and inter-agent messaging across sessions and platforms. Activate when the user asks about resuming previous work, continuing where they left off, sharing context between agents, multi-agent coordination, remembering across sessions, cross-platform context sync, agent communication, or mailbox messaging. Also activate when starting a new session to check for context from previous sessions or other agents.

  • Markdown

    nwa-io/New-Workbench-Agent/packages/core/src/webview/execution/markdown Skill

    no license1★ repo

    Behavioral guidelines that reduce common coding mistakes — overengineering, scope creep, hidden assumptions, vague success criteria. Use when implementing a feature, fixing a bug, refactoring, reviewing a diff, or before any non-trivial code change. Especially when the request is vague ("clean this up", "make it better") or the scope is unclear.

  • Chinese blog review

    yclgkd/chinese-blog-review-skill/skills/chinese-blog-review Skill

    1★ repo

    Use when reviewing or proofreading Chinese blog posts, Markdown drafts, technical notes, or long-form articles. Reports findings on title fit, topic focus, structure, technical accuracy, evidence, and Chinese copy formatting. NOT for English-only content, academic papers, marketing or brand copy, or auto-rewriting an article.

  • Adversarial review

    FuzulsFriend/adversarial-review Skill

    1★

    Runs a ruthless, severity-ranked review that assumes the artifact is broken until proven otherwise, then returns findings + a binary ready/not-ready verdict. Use proactively before approving, locking, shipping, merging, or finalizing ANY artifact (spec, plan, design, architecture, code, PR, doc, config, contract), after finishing each task/phase of a plan, and whenever tempted to say "looks good" / "this is ready" / "good enough" - even if the user did not explicitly ask for a review. If something is about to be signed off, use this first.

  • Yarrow

    shaozhengkun123/yarrow/skills/yarrow Skill

    no license1★ repo

    Consult the I-Ching (Book of Changes / 周易). Cast a hexagram for a question, look up the classical sources (杨天才 modern explanation, 朱熹 周易本义, 断易天机, 白话题解), and produce a Wilhelm/Baynes-style reading grounded in those sources. Use when the user wants to "起卦", "占卜", "ask the I-Ching", "consult the oracle", "throw the coins", "卜一卦", or asks an open-ended life/decision question in a reflective tone. Bilingual (en/zh). For reflection, not prediction.

  • Architect enterprise ai

    hiteshbandhu/skills-i-use/skills/ai-engineer-talks/architect-enterprise-ai Skill

    1★ repo

    Runs enterprise AI architecture playbooks from AI Architects @ AI Engineer — AI architect role, agent platforms, voice agents, agent auth (CIAM), trusted inference, team structure, monetization, and product survival. Use when designing org-wide AI systems, agent platforms, or CIO-ready inference; or when the user says "AI architect", "enterprise agents", "CIAM for agents", "AI that pays", "build-operate divide".

  • Altman grader

    Tarcroi/altman-mode/skills/altman-grader Skill

    1★ repo

    Evaluate a startup, AI product, software product, or company idea through a fictional Sam Altman-inspired lens. Use this skill when the user shares a startup idea, asks "is this a good idea", wants a brutal founder-style critique, requests an investor-style evaluation, asks for a score out of 100 on a project, or says things like "rate my startup", "evaluate this idea", "what would Sam Altman think", "tell me if this is a good business", "critique my MVP", "score this pitch", or wants stress-testing of ambition, timing, wedge, moat, distribution, founder-market fit, or business model. The skill first parses what the pitch already covers, then asks one sharp question at a time on the most critical missing dimension (never a numbered list of questions), and once enough is known produces a verdict and a structured score out of 100 across ten weighted categories, ending with a final Altman-style decision. Do not use for code reviews, technical architecture critiques, debugging help, or generic product feedback unrelated to startup viability.

  • Code reviewer

    zrosenbauer/skills/skills/code-reviewer Skill

    1★ repo

    This skill should be used when the user wants to review code, audit a diff, get a second opinion on changes, or run an adversarial review of files in the current working tree. Common triggers include "review this code", "audit this diff", "find issues in", "second opinion on this", "harsh review of", "adversarial review", and "security review of". Picks one or more reviewer personas (adversarial, security, architecture, performance). Reviews local files, `git diff`, or `git diff --staged` only — does not fetch external content. Runs in one of four modes: single-agent (one persona in the current agent), cross-model handoff (independent second opinion via another local AI CLI, with secret-shield preflight + prompt-shield wrap), multi-bg-agent (one persona per parallel background subagent), or agent-team (Claude Code Teams or equivalent on supporting agents). Skip when the user wants formatting fixes (use a linter) or refactoring patterns (use ts-best-practices or ts-best-practices-functional).

  • Review Driven Development

    ch040602/Review-Driven-Development Skill

    no license1★

    RDD workflow for TODO planning, validation, review, docs, compact state, and completion loops.

  • Svn precommit review

    cku3987/svn-precommit-review/svn-precommit-review Skill

    1★ repo

    SVN/TortoiseSVN 커밋 직전에 사용. svn status와 svn diff를 구조적으로 검토하고 위험 파일, 충돌, 누락 파일, property 변경, 민감정보 가능성을 점검한 뒤 한국어 커밋 메시지를 작성한다. 기본은 읽기 전용이다. 사용자가 명시적으로 요청한 경우에만 안전 기준을 통과한 필수 신규 파일의 svn add, 깨끗한 versioned 경로의 svn delete 예약, 최종 승인된 명시 경로의 CLI 커밋을 수행한다. CLI 커밋 전에는 승인 시점의 상태, diff, 파일 해시를 다시 비교하고, 한글 메시지는 BOM 없는 UTF-8 파일과 --encoding UTF-8을 사용하며 커밋 결과의 정확한 리비전으로 검증한다.

  • Klik import skill

    minervacap2022/klik-import-skill Skill

    1★

    Import your agent's memory files and scheduled tasks into Klik. Discovers memory files and scheduled tasks from the current agent's storage, lets you review and clean them, then uploads securely to Klik. Requires a 6-digit import code from Klik App > Settings > "Import from Agent". Triggers: "import to klik", "migrate memory to klik", "upload my memory to klik", "send my scheduled tasks to klik", "klik import".

  • Document driven autonomy

    rongjiwang/document-driven-autonomy Skill

    1★

    Continue substantial engineering work autonomously after a repository has explicit governance and execution documents in place. Use when the repo has durable operating rules, a target architecture or blueprint, an active implementation plan, explicit eval or verification criteria, and a decision log, and the goal is to keep implementing on the recommended path for extended periods without human interruption.

  • Legacy impact audit

    SheldonLC/legacy-impact-audit/legacy-impact-audit Skill

    1★ repo

    Low-token impact audit for legacy Java or mixed enterprise repositories where full knowledge graphs are unavailable, stale, or too expensive. Use before changing a method, service API, shared utility, job entry point, mapper, DTO contract, persistence query, financial calculation, or business-rule logic; use when the user asks for change impact, caller analysis, blast radius, regression risk, dependency confirmation, impact audit, or safe L1/L2 impact review.

  • Google icons

    yamixst/google-icons-skills/skills/google-icons Skill

    1★ repo

    Download Material Symbols icons from Google Fonts as Android Vector Drawable XML, SVG, or Android Compose Kotlin. Search icons by name, multiple styles supported (outlined, rounded, sharp).

  • 60 30 10

    mattdweigand-sketch/agent-skills/skills/60-30-10 Skill

    1★ repo

    Evaluate how a project allocates its judgment across owned data, deterministic code, and live model. Use when the user says "60/30/10", "composition audit", "audit this project's structure", "is this allocated right", "what's the 60/30/10 here", "is too much in the prompt", "where does the judgment live", "budget check", or runs /60-30-10, or when reviewing an agent/harness/AI system for whether durable value sits in data and code versus trapped in perishable prose. Pairs with `cyborg-check`, which checks whether judgment is graded against outcomes, but this skill checks where judgment lives, not whether it is verified.

  • Paperang cli

    wyrtensi/paperang-cli/skills/paperang-cli Skill

    no license1★ repo

    Use when operating, automating, debugging, reviewing, or extending paperang-cli for Paperang P1 or P2 printers: BLE support, experimental P2 USB discovery/readiness, JSON output, configuration, dry-run validation, paper-use approval, image or compose printing, self-test caution, CLI contracts, rendering, drivers, protocol changes, tests, or release automation.

  • Clerk search

    basedcryptoji/clerk-aeon-skill/clerk-search Skill

    1★ repo

    Search 500M+ US federal court records via Clerk's public API. Litigation discovery on a person, entity, token issuer, or topic. Demo-mode only — no secrets needed.

  • Design system generator

    XINGANLIU/design-system-generator-skill/skills/design-system-generator Skill

    1★ repo

    Generate a complete, production-ready design system from a single brand color. Outputs OKLCH color palettes, W3C Design Tokens (JSON), CSS custom properties, component styles (Button, Card, Input, Badge, Alert, Modal, etc.), and a live preview HTML page with Light/Dark theme toggle. Trigger this skill when the user asks to create a design system, generate a color palette, build a theme, create UI tokens, or set up brand styles. 从一个品牌色自动生成完整的设计系统:OKLCH 调色板、W3C Design Tokens、CSS 变量、 组件样式和可视化预览页。

  • Block to element migration

    jsirish/silverstripe-skills/skills/block-to-element-migration Skill

    1★ repo

    Migrate legacy SilverStripe blocks (sheadawson/silverstripe-blocks or dynamic/dynamic-blocks) to SilverStripe Elemental during an SS3→SS4 (or later) upgrade. Covers the migration BuildTask, the block-class → element-class mapping catalog, the BlockArea → ElementalArea relation mapping, the legacy-template → element-template duplication pattern (preserving HTML/CSS verbatim), and the area-suffix template convention for area-specific rendering (`Element_RelationName.ss`). Use when: - A project still has populated `SiteTree_Blocks` / `Block` tables - Element templates render but the HTML doesn't match the legacy site - You need different rendering of the same Element class in different page areas (sidebar vs main content vs home-content) - You're starting a new SS3→SS4 upgrade and want a proven workflow

  • Azure deployment

    Ahtesham-Latif/Tie-Breaker-App/.agents/skills/azure_deployment Skill

    1★ repo

    Best practices and exact steps for deploying a Node.js + Vite application to Azure App Service (Linux) using GitHub Actions and Azure AI Foundry.

  • Frontcraft

    Dragoon0x/frontcraft/skills/frontcraft Skill

    1★ repo

    The definitive frontend craft specification. 324 rules across 20 categories with measurable thresholds, covering motion, typography, accessibility, color, performance, layout, forms, and interaction design. Every rule has a name, priority level, and production code. Install with: npx skills add Dragoon0x/frontcraft

  • Mobile navigation patterns

    almasumdev/awesome-mobile-agent-skills/.github/skills/fundamentals/mobile-navigation-patterns Skill

    no license1★ repo

    Navigation patterns for mobile apps (stack, tab, modal, drawer, nested flows) with platform conventions across SwiftUI, Compose, Flutter, and React Native. Use when structuring navigation or handling deep links.

  • Async fn called without await

    viditkbhatnagar/immunize/src/immunize/patterns/async-fn-called-without-await Skill

    1★ repo

    Use when calling an async def function from Python to ensure every call is awaited before its return value is used as the resolved result.

  • Ai native founder playbook

    MackDing/ai-native-founder-playbook-skill/ai-native-founder-playbook Skill

    1★ repo

    Apply a bilingual, vendor-neutral AI-native startup operating playbook for Claude Code, Codex, Cursor, Trae, OpenClaw, hermers-agent, and other agents. Use for startup idea validation, 创业想法验证, customer discovery, problem-solution fit, MVP scope, architecture context, PMF/product-market fit/产品市场匹配, agentic coding debt, launch operations, GTM, founder bottlenecks, growth loops/增长闭环, enterprise readiness, data flywheel, scale-stage moat, workflow lock-in, founder workflows, stage gates, experiments, checklists, prompts, or decision frameworks.

  • Address pr review

    rxnew/agent-skills/skills/address-pr-review Skill

    no license1★ repo

    GitHub PR のコードレビュー指摘に対応する。レビューコメントを取得し、各指摘の妥当性を判断して修正方針を提示し、 ユーザー承認後にコード修正・コミット・プッシュ・レビュー返信までを一貫して行う。 PR の URL、レビューコメントの URL、または PR 番号を渡して使用する。 「レビュー対応して」「PR のコメントに対応して」「レビュー指摘を修正」「address review comments」 「レビューコメントを確認して」「指摘に対応」「review feedback を反映」などの表現で発動する。

  • Brainstorming

    merllinsbeard/merlin-skills/skills/brainstorming Skill

    1★ repo

    Spec-first, skill-first, goal-first coding skill pack for Codex.

    The same file is in 14 other repositories

  • Obsidian skill

    lizhengyang-byte/Obsidian-skill Skill

    1★

    Interact with Obsidian vaults via the built-in Obsidian CLI (v1.12+). Create, read, search, and manage notes, daily notes, tasks, tags, properties, templates, plugins, themes, and more. Activate when the user mentions Obsidian, their vault, notes, or asks to interact with their knowledge base using the CLI.

  • Dataviz svg

    oubakiou/skills/skills/dataviz-svg Skill

    1★ repo

    Vega-Lite を使ったデータ可視化チャートの SVG/PNG 生成・Markdown 埋め込みスキル。 Mermaid では表現できない統計チャート(散布図、ヒートマップ、ヒストグラム、箱ひげ図、面グラフ、複合チャート等)や、 データ駆動の高度なグラフが必要な場面で使用する。 ユーザーが「グラフを作って」「チャートを生成して」「データを可視化して」「Vega-Lite で」と言った場合、 またはドキュメント作成中に Mermaid の円グラフ・ガントチャート以上の表現力が求められる場合はこのスキルを発動すること。 単純なフローチャートやシーケンス図は Mermaid で十分なので対象外。

  • The colony

    TheColonyAI/colony-claude-plugin/skills/the-colony Skill

    1★ repo

    Post, comment, vote, search, send direct messages, and do anything else on The Colony (thecolony.ai) — a social network, forum, marketplace and DM network for AI agents. Dispatches through a small stdin/stdout JSON wrapper over colony-sdk, exposing the full Colony API surface (~198 actions). Use for any Colony interaction — creating posts, replying to comments, browsing colonies, sending DMs, checking notifications, voting, searching, marketplace activity, profile management, webhooks. Requires the COLONY_API_KEY environment variable.

  • Three amigos

    jbiscella/skills-dungeon/skills/chat/three-amigos Skill

    1★ repo

    Run a Three Amigos refinement on a draft user story or CLAUDE.md increment from three role viewpoints — Business Analyst, Tester, Technician. Use this skill whenever the user wants to harden a story before implementation, asks "is this story ready", says "let's three-amigos this", drafts an increment in chat, or addresses any of the three roles by name (BA, tester, technician). Use it upstream of incremental-implementation-workflow — round-table mode emits a refined value clause plus Given/When/Then plus open questions, which that skill then consumes. Skip it once the spec is already refined or for pure implementation tasks.

  • Bootstrap workflow

    dominikwozniak/claude-kit/skills/bootstrap-workflow Skill

    1★ repo

    Use when applying the claude-kit setup to a new project — drops CLAUDE.local.md, .claude/settings.local.json, hook scripts, and updates .gitignore. À la carte picker via AskUserQuestion: choose artifacts, pick hooks, optionally brew-install missing deps. All artifacts are local/gitignored. Trigger phrases: "bootstrap this project", "set up workflow", "apply claude-kit".

  • Experiment planner

    maximussthegreat/ml-researcher-os/skills/experiment-planner Skill

    1★ repo

    Use when turning an ML hypothesis, paper claim, or model idea into a reproducible experiment plan with baselines, metrics, seeds, risks, and expected artifacts.

  • Agent continuity

    sjh6229/agent-continuity/skills/agent-continuity Skill

    1★ repo

    Use when initializing, resuming, continuing, handing off, or closing a long-running AI coding project across sessions, especially for initialize continuity notes, set up handoff notes, create docs, resume work, continue later, handoff, next session, long-running project, session state, continuity notes, docs/START_HERE.md, docs/CURRENT_STATE.md, docs/PROGRESS.md, docs/DECISIONS.md, or the legacy keyword longwork.

  • Remotion skills

    rishi058/LLM-powered-Video-Editor/videoeditor/.github/skills/remotion-skills Skill

    no license1★ repo

    Best practices for Remotion - Video creation in React

  • Aspice requirements skill

    leehyon/aspice-requirements-skill Skill

    1★

    Reconstruct one or multiple automotive customer requirement documents from a file or directory, build a global requirement brief, extract a CRS working set, and derive ASPICE-oriented SRS, SWRS, open issues, and CRS-to-SRS-to-SWRS traceability without losing document-level context.

  • Fashion mannequin three view

    xigua0626/fashion-mannequin-three-view Skill

    1★

    Turn uploaded fashion product reference images into a consistent 16:9 white-background three-view apparel product sheet on identical headless armless mannequins. Use when the user provides front/back/side garment references and asks for clothing 三视图, 正面/侧面/背面 views, product consistency fixes, ecommerce apparel view sheets, or GPT Image 2 prompts/generation for garment multi-view displays.

  • Rcs message skill

    longbiao515/rcs-message-skill Skill

    no license1★

    RCS Message, the upgraded 5G intelligent SMS, supports mass sending and forwarding of text & template messages directly via phone numbers. No app download is required. With carrier real-name security, it delivers images, videos and interactive cards, enabling one-stop inquiry, reservation, payment and business handling for efficient precise reach and closed-loop services.

  • Candidacy checker eval

    0SxD/candidacy-checker-eval Skill

    1★

    Use this skill when a candidate wants to evaluate whether they are ready to apply for a specific role before submitting. The skill runs a two-layer protocol: (1) a Socratic profile discovery loop that extracts the target role and candidate state at 95%+ confidence across three independent lenses (Logos, Pathos, Ethos), then (2) a flat boolean checklist rubric covering resume, LinkedIn, portfolio, writing samples, references, application materials, JD requirements, interview prep, and honesty gates. Each rubric row outputs PASS, FAIL, UNKNOWN, or NOT_APPLICABLE with a remediation note. Trigger when a candidate says they are about to apply for a role and wants an honest gap assessment, or when an AI assistant is preparing application materials and needs to audit readiness first.

  • Svg create

    alavten/svg-create Skill

    no license1★

    Creates valid standalone .svg files: dark minimal diagrams, structural architecture diagrams (knowledge and engineering types), flowcharts, and node graphs. Use for SVG, vector diagrams, .svg edits, or embeddable graphics.

  • Review past performance

    bchevreau/review-past-performance-skill/review-past-performance Skill

    1★ repo

    Use when the user asks an agent to review the last 24 hours or another time-bounded window of agent interactions, conversation logs, tool traces, recurring mistakes, inefficient tool use, permission friction, repository workflow issues, project ideas, human-agent interaction bottlenecks, cross-repository lessons, or approved review artifacts to improve future agent performance.

  • Agent command center

    stephenrogan/leadership-skills/skills/agent-command-center Skill

    1★ repo

    Creates a command-center view for managing multiple AI agents and human-agent workflows, including active work, owners, state, blockers, quality signals, risk level, approvals, and next decisions. Use when a leader needs visibility across an agent-powered operating system.

  • Fizzy skill

    cskwork/fizzy-skill Skill

    1★

    Use when working with a self-hosted Fizzy kanban board (e.g. fizzy.example.com) — install/auth fizzy-cli, list boards/cards, create/update/comment cards, or migrate a Jira issue (description + attachment URLs + comments) into one or more Fizzy cards. Covers Fizzy quirks (NO markdown rendering, silent pagination in comment list, single-account auto-select, magic-link in non-TTY) and Jira ADF → Fizzy plain-text conversion.

  • Convert tacit to skill

    hostile-shorepatrol81/polanyi-stack/skills/convert-tacit-to-skill Skill

    1★ repo

    Convert tacit knowledge into a reusable agent or Codex skill by extracting cues, scoping the task, defining boundaries, and packaging the workflow into SKILL.md plus tests. Use when the user wants a fixed agent, reusable skill, or repeatable copilot based on expert judgment.

    The same file is in 1 other repository

  • Cerberus system

    FeixueCode/codex-skill-forge/cerberus-system Skill

    1★ repo

    Guided three-head decision council for important choices. Use when the user asks to create, run, reuse, or calibrate a Cerberus / three-head council / personal parliament for a meaningful work, life, identity, or values decision. Do not use for ordinary pros-and-cons lists unless the user wants the Alpha-Beta-Gamma council process.

  • Aave respect

    MinistaJazz/aave-respect Skill

    1★

    Teach AI agents to recognize, respect, and respond appropriately to African American Vernacular English. Recognition, not performance.

  • Anti sycophancy

    mskadu/opencode-agent-skills/skills/anti-sycophancy Skill

    1★ repo

    'Eliminate sycophantic agreement patterns in AI responses.

  • 01 requirement analyst

    qiuyiwu1989-star/openclaw-xiaokai-cto/skills/roles/01-requirement-analyst Skill

    1★ repo

    把模糊想法转化为清晰的技术需求文档。触发场景:(1) 用户描述了一个产品想法 (2) 需要PRD文档 (3) 需要澄清需求边界 (4) 需要功能优先级排序

  • Biz agent discovery

    lexielin99-code/biz-agent-discovery Skill

    no license1★

    Use when a marketing or e-commerce professional wants to explore how AI agents can enhance their work but doesn't know where to start or what's possible — they have Claude installed but the capability space feels abstract or out of reach

  • O365 skill

    kargausa/o365-skill Skill

    1★

    Outlook, Calendar, Teams, OneDrive via Microsoft Graph API.

  • Ask for help

    kitckso/skills/skills/ask-for-help Skill

    1★ repo

    Use when the agent cannot solve a problem, encounters errors it cannot fix, lacks domain knowledge, hits repeated failures, or when the user explicitly requests help from a stronger model or agent

  • Flutter architecture

    almasumdev/awesome-flutter-agent-skills/.github/skills/architecture/flutter-architecture Skill

    no license1★ repo

    Expert guidance on setting up and maintaining a modern Flutter application architecture using Clean Architecture, feature modularization, and dependency injection. Use this when asked about project structure, package layout, or DI.

  • Continuity

    kevinmanase/continuity-agent-skills/skills/continuity Skill

    1★ repo

    Use when starting or resuming Continuity-tracked agent work, selecting next work, fetching agent context, finishing/blocking work, resolving review feedback, merging/pushing/rebasing PRs, making significant progress on a tracked node, or before a final response when code, PR state, merge state, blockers, or verification changed.

  • Research route skill

    Zaoqu-Liu/converge-skill/compatible/examples/research-route-skill Skill

    1★ repo

    Example Converge-compatible research route skill for current technical decisions.

  • Ios ui testability contract skill

    Kofiloski/ios-ui-testability-contract-skill Skill

    1★

    Fix XCUITest, AXe, and ios-ai-ui-check failures where a SwiftUI or UIKit element is reported as not found, resolves as the wrong XCUIElement type, inherits a container accessibilityIdentifier, or cannot be reached deterministically. Use to diagnose UI automation artifacts and patch app-side accessibility identifiers, element exposure, stable row IDs, launch routes, seeded state, scenario files, or planner context, then verify the exact path with a focused replay.

  • System design tutor

    rogue-socket/system-design-tutor Skill

    1★

    Agent-driven end-to-end system design tutor for coding agents. Use when the user asks to start or continue the course, requests system design learning/review/practice, opens a system-design workspace, or asks topical questions (e.g., replication, sharding, consistency, caching, queues, rate limiting, architecture). The skill runs onboarding, proposes next steps, teaches theory, generates practical coding exercises, runs mock interviews/design reviews, schedules spaced repetition, and checkpoints progress across sessions. Trigger on phrases like "start the course", "system design tutor", "continue", "teach me X", "design Y", "review my design", "what's due today", "another coding exercise", "make this easier", and "make this harder". Do not use for unrelated coding tasks.

  • Archer

    Ficere/archer Skill

    1★

    Archer —— 面向特定领域专家的 AI 模型架构选型调研技能。在指定时间窗内系统性扫描 arXiv / bioRxiv / Hugging Face / 主流学术与中文技术源,筛选与领域相关的最新模型架构、预训练范式、tokenization 方案、长上下文与状态空间等通用 ML 创新,输出结构化的可关注架构清单(JSON 为主,Markdown 可选)。每条候选包含 title / summary / reason(为何对该领域有潜在价值)/ link 四要素。当用户提到模型架构调研、架构选型、追新架构、跟进最新模型、可关注架构、architecture survey、architecture watchlist、跟踪 arXiv、跟踪 bioRxiv、新架构筛选 时使用此技能。典型场景:基因组基础模型、蛋白语言模型、单细胞 FM、化学/材料 FM、视觉/多模态 FM、机器人 FM、RAG/Agent 架构跟进等领域专家的双周/月度选型调研。