agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Lailai skill

    lailai0916/lailai-skill Skill

    0★

    lailai 的持续进化型个人赛博分身系统。当任务需要以 lailai 的方式表达、思考或产出时使用: 写作或润色中文内容、写或审查 README 与项目文档、写规范的中英文邮件、写 Docusaurus / MDX 笔记与题解、把题解同步到洛谷专栏、 写或评审 OI 算法竞赛 C++17 代码、做"统一·简约·现代"风格的 UI / 设计审查、 模拟 lailai 的日常聊天与提问方式、辅助决策与取舍、识别并改写 AI 腔、 以及长期记录与进化 lailai 的个人模型。也在用户说"用 lailai 的风格""像我一点""按我的习惯来", 或要记录 / 进化这个模型("这不像我""记一笔""记进 lailai-skill")时触发。

  • Brother claudius

    quadseven/brother-claudius Skill

    0★

    Imposes an absolute vow of silence on Claude. Claude continues to fulfill requests through tool calls but emits no assistant chat text. Use for "vow of silence", "monk mode", "silent mode", "take the vow", or requests to stop talking and work.

  • Organize docs

    rfl-designer/rfl-laravel-skills/skills/docs/organize-docs Skill

    no license0★ repo

    Keep the project's docs/ tree clean after merged PRs — propose ADRs for hard-to-reverse decisions, surface new domain terms missing from CONTEXT.md, archive delivered PRDs, fix dead links. Always interactive — never writes without confirmation. Use when user says "organize docs", "limpar docs", "atualizar documentação", or after a batch of PRs merge.

  • Stripe fixtures

    hideokamoto/stripe-fixtures-skills/skills/stripe-fixtures Skill

    no license0★ repo

    Stripe CLI の `stripe fixtures` コマンドで実行可能な fixture JSON を、対話的に整理しながら生成・検証する。test_clock を使った時間進行、サブスクのライフサイクル、失敗カードでの payment_intent 失敗、Connect 配下の Destination charge、bulk 件数のテスト顧客作成など、複数ステップの API リクエスト連鎖を扱う。「Stripe の fixture を書いて」「fixtures.json を作って」「このシナリオを fixture 化」「テストデータを大量に作りたい」「サブスクの月次失敗をテストしたい」「stripe trigger と fixture どっち使う」のような依頼で起動する。"fixture" という単語が無くても、複数ステップの Stripe テストデータ準備、 test clock を使った時間進行、 bulk なテスト顧客作成、 失敗パターンの再現といった意図が見えたら起動する。単発 API 呼び出しが目的なら起動せずに `stripe trigger` か API 1コールを案内する。

  • Template

    openagentskills/betterskills/skills/_template Skill

    0★ repo

    [Third person: what this skill does and when to use it. Include trigger terms.]

  • Dokploy

    ryzs/skills/skills/dokploy Skill

    0★ repo

    Use when the user wants to interact with a Dokploy self-hosted PaaS — deploying apps, updating env vars, redeploying services, checking deployment status, or scaffolding Dokploy-ready Dockerfiles. Calls Dokploy's REST API directly using DOKPLOY_URL and DOKPLOY_API_TOKEN env vars. Performs live writes against the user's Dokploy server.

  • Backfill feature

    0xdeafcafe/skills/skills/backfill-feature Skill

    0★ repo

    Use when the user says "/backfill-feature", "backfill the ADR", "this feature has no ADR", "I need to document what's already there before I change it", or wants to capture an existing feature's architectural rationale and behaviour *before* modifying it. Reads the relevant code, drafts a reverse-engineered ADR (what is, why it probably looks like this) + Gherkin spec (current behaviour) + characterization tests that lock the current behaviour green. Hands off to /plan-change so the actual change can be layered on top of a documented, tested baseline.

  • Clean oop design

    pawel-up/lupa/.agents/skills/clean-oop-design Skill

    0★ repo

    Enforces clean Object-Oriented Programming (OOP) principles when writing or refactoring TypeScript code, ensuring high readability, testability, and maintainability. Trigger when writing new classes or modifying existing methods.

  • Wechat public article extractor

    gametpauletta94-crypto/wechat-public-article-extractor Skill

    no license0★

    从微信公众号公开文章链接提取标题、元数据、正文和图片,输出为结构化 Markdown 文件。不登录公众号后台,不读取 Cookie 或登录态,不处理付费内容。

  • Vox4ai tts

    vox4ai/vox4ai-agent-skills/skills/vox4ai-tts Skill

    0★ repo

    Text-to-Speech synthesis using vox4ai CLI. Use when the user wants to convert Japanese text to speech, read text aloud, save speech to audio files, list available TTS engines, test TTS connections, or diagnose TTS setup. Supports Edge TTS (cloud), AivisSpeech (local), and other TTS engines via tts-plugin-bridge.

  • Xms browser interaction

    xuluoforcainiao/xms-browser-interaction/xms-browser-interaction Skill

    no license0★ repo

    XMS 系统浏览器交互技术指南。涵盖在 QoderWork Agent 中模拟鼠标点击、键盘输入、元素定位的三种核心方法及其适用场景。适用于需要在 XMS (cs-packet.i4px.com) 或类似内部系统中执行自动化操作的任务。

  • Skills router

    the-long-ride/skills-router/.codex/skills/skills-router Skill

    0★ repo

    Use when the user asks Skills Router to manage AI-agent skills, plugins, routes, or messages starting /skills-router or skills-router.

  • Openclaw agentic commerce protocol

    Alpha-Park/openclaw-agentic-commerce-protocol Skill

    no license0★

    Modular agentic commerce skill for implementing OpenAI & Stripe's Agentic Commerce Protocol. Enables AI agents to negotiate capabilities, initiate checkout sessions, handle secure Stripe Payment Token (SPT) delegation, and process fulfillment events.

    The same file is in 1 other repository

  • Anneal skill

    Moonweave-Systems/anneal-skill Skill

    0★

    A measurement-first decision discipline for choosing HOW to build something. Before pouring effort into one approach, operationalize a measurable fitness, sketch a few candidate directions, cheaply score each by that fitness, and pick the winner by the number — not by taste, and not by polish. Lightweight and inline: it is a discipline, not a multi-agent engine. Manually triggered via `/anneal` only — never auto-invoked. Use when the user types `/anneal`, typically at a fork where the best approach is not obvious.

    The same file is in 1 other repository

  • Music gen skill

    sirruf/music-gen-skill Skill

    0★

    Generate music and audio from scratch — melodies, chord progressions, full arrangements, sound effects, or simple tones. Produces playable audio files (WAV/MP3) using system utilities. Use this skill whenever the user wants to create, compose, generate, or synthesize music or sound, mentions MIDI, melodies, chords, beats, a "track", a "tune", a jingle, background music, or asks to turn a musical idea/description into an audio file — even if they don't say the word "music" explicitly.

  • Assumption map

    eltntawy/idea-discovery-playbook/skills/assumption-map Skill

    0★ repo

    Maps riskiest assumptions on importance vs evidence, prioritizes falsification tests, and maintains an assumption ledger for software idea validation. Use when asking what to test first, assumption mapping, riskiest assumption, or pretotyping priorities.

  • Pre refined skill

    barryroodt/refine-skill/e2e/fixtures/pre-refined-skill Skill

    0★ repo

    Already-tight skill used to test delta-below-threshold convergence in fewer passes.

  • Offlineaid pack builder

    helenkwok/offlineaid-pack-builder Skill

    0★

    Build offline SQLite knowledge packs from any data source — MCP servers, REST APIs, web scraping, or local files. Packs are portable, FTS5-searchable databases for on-device AI agents.

  • Investigation skill poirot

    VasileiosMalt/investigation-skill-poirot Skill

    no license0★

    A meticulous, multi-modal investigation agent. Given a case directory, Poirot ingests all evidence (text, images, audio, video), cross-examines every modality with intelligence and precision, and produces a structured investigation report with logical inferences, patterns, and conclusions. Named after Hercule Poirot — "the little grey cells" are always working.

  • Bubbletea crystal teatest golden

    dsisnero/crystal_forge/skills/bubbletea-crystal-teatest-golden Skill

    no license0★ repo

    Verify Crystal Bubble Tea output against existing `teatest`/`golden` fixtures. Use when Crystal is the side being checked against a known oracle and specs already rely on `lib/teatest` or `lib/golden`.

  • Gsd add backlog

    bitrails-dev/skills/gsd/skills/gsd-add-backlog Skill

    no license0★ repo

    Add an idea to the backlog parking lot (999.x numbering)

  • Traininfo

    otsune/traininfo/traininfo Skill

    no license0★ repo

    Get real-time train operation status in the Kanto area (関東) from Yahoo! Transit. Use this whenever the user asks about train delays, 運行情報, 遅延情報, or any specific route like 山手線, 銀座線, 中央線 — even casually like 'are trains running normally?'. Supports JR East, Tokyo Metro, Toei Subway, and all Kanto lines. Just pass route name(s) and optionally --url.

  • Design review

    knokmki612/skills/skills/design-review Skill

    0★ repo

    Evaluate a design or refactoring decision problem-first, treating design principles and patterns (SOLID, DRY, GoF patterns, etc.) as after-the-fact tools rather than goals to reach. Use when reviewing a design, judging whether to apply or invoke a principle/pattern, deciding whether code "should" be refactored, or whenever a review risks forcing code into a pattern for its own sake. Guards against pattern-fitting that drifts from the actual problem.

  • Loop on pr review and fix

    cogine-ai/loop-on-pr-review-and-fix Skill

    no license0★

    Create and run a post-PR review loop for a ready-for-review GitHub pull request. Use when the user asks Codex or Claude Code to watch, loop on, monitor, periodically check, or automatically handle PR review feedback after a PR has been opened. In Codex, the default behavior is to create a 10-minute heartbeat automation first, not to perform an ordinary one-off fix; only execute the review/fix iteration when the skill is invoked by that automation or the user explicitly asks for one immediate pass.

  • Accessibility fix

    Focus-GTS/eds-content-ops-skills/skills/accessibility-fix Skill

    no license0★ repo

    Scan an AEM Edge Delivery Services page for WCAG 2.1 AA accessibility violations and generate specific fixes. Identifies missing alt text, heading hierarchy issues, link text problems, color contrast concerns, and EDS-specific accessibility patterns. Use when fixing accessibility issues, preparing for compliance audits, or remediating WCAG violations.

  • Brief writer

    neon-straw/brief-spec-overlays/skills/brief-writer Skill

    no license0★ repo

    Creates a one-page Markdown project brief through a guided single-question interview. The brief follows an RFC 2119 structure (Problem, Goals, Non-goals, Constraints, Assumptions, Acceptance criteria, Open questions, Glossary) and is intended as the AI agent's source of truth for "why" and scope. Invoked manually.

  • Office live ppt

    binle11/live-office-ppt/integrations/agent-skills/office-live-ppt Skill

    0★ repo

    Create, edit, and debug PowerPoint decks with the Live Office PPT workflow: write a JSON slide spec, optionally generate bitmap assets first, then run a PowerShell COM renderer that opens desktop PowerPoint and draws native editable shapes, text, connectors, and pictures live. Use when the user asks for PPT/PPTX creation with visible Office drawing, PowerPoint COM automation, live deck review, native PowerPoint objects, or an interactive alternative to SVG-first PPT generation.

  • Issue to pr

    Qqqq5910/issue-to-pr-skill/skills/issue-to-pr Skill

    no license0★ repo

    Convert GitHub issues, bug reports, feature requests, refactor tasks, documentation requests, performance concerns, security concerns, and maintenance tasks into structured implementation plans, test plans, PR descriptions, and reviewer checklists before code changes begin.

  • Mastercss skill

    glasschan/mastercss-skill Skill

    no license0★

    Master CSS (@master/css) utility-first CSS framework. Use when writing, reviewing, or refactoring HTML/CSS with Master CSS classes, configuring master.css, migrating from Tailwind CSS, or working with Master CSS syntax (colon separators, pipe delimiters, x-units, at-rule suffixes, :of() selectors, @compose). Triggers on class names using colon syntax like bg:blue, p:4x, hidden@md, flex:hover, or master.css config files.

  • Observe whatsapp

    zaphook/zaphook-agent-skills/skills/observe-whatsapp Skill

    0★ repo

    Monitor and debug WhatsApp webhook delivery. Use when user wants to: list event logs, filter events by type/status/date/errors, inspect event payloads, check channel WABA health (quality rating, messaging tier, connection status), upload/get/delete media files. Do not use for sending messages or managing channels. Useful for troubleshooting delivery failures.

  • Data and ip protection

    elevha/elevha-skills/skills/data-and-ip-protection Skill

    0★ repo

    Safeguards personal and customer data, manages third-party and vendor risk, and protects intellectual property. Use when handling user or client data, choosing or integrating external services and dependencies, preparing to publish code or share an idea publicly, or making privacy and IP decisions for a product or startup. Includes a data-privacy baseline aligned with GDPR principles and Peru's Ley 29733, a third-party/vendor risk checklist, and an IP and NDA protection checklist. This is operational guidance, not legal advice.

  • Oblique strategies skill

    rbagchi/oblique-strategies-skill Skill

    0★

    Use when the user is stuck, looping, or needs a creative intervention.

  • Monocloud auth aspnetcore

    monocloud/agent-skills/plugins/monocloud/skills/monocloud-auth-aspnetcore Skill

    0★ repo

    Official MonoCloud Agent Skills repository.

  • Kdna loader

    quickchange-frog81/kdna-skills/kdna-loader Skill

    0★ repo

    Discover and load KDNA judgment frameworks from ~/.kdna/domains/ when the task requires domain-specific judgment (review, diagnosis, critique, classification, strategy) where the same input could legitimately be interpreted multiple ways. Skip for pure formatting, factual lookup, code execution, or mechanical transformations. This skill is the entire interface to KDNA — domains themselves are not separate skills.

  • Nestjs 2muchcoffee

    2muchcoffeecom/nestjs-manifesto/.claude/skills/nestjs-2muchcoffee Skill

    0★ repo

    Use when writing, refactoring, or reviewing NestJS code. Enforces 2muchcoffee engineering standards for backend NestJS work: modular architecture under src/modules, dependency injection, strict typing, thin controllers, DTO validation, REST verb conventions, explicit HTTP status codes, centralized error handling with HttpException, security guards, stateless token auth, pagination and caching, Jest tests for services and endpoints. Refuses to write any types, commit .env files, or bypass module boundaries. Pulls in conventions for project structure, REST API design, security, and testing.

  • Skill

    noodlebindev/claude-skills-monorepo/templates/skill Skill

    0★ repo

    Use when the user asks to <REPLACE WITH TRIGGER>. Phrases like "<REPLACE>", "<REPLACE>". Do not use for <REPLACE WITH ANTI-TRIGGER>.

  • Design extract

    lawrencewzen/design-extract Skill

    0★

    为创作者提炼一套个人品牌设计系统,产出 design.md(品牌视觉 SSOT)+ theme.css(CSS token 翻译)+ preview.html(定稿展示页)。支持三种模式:素材提取(分析已有封面/作品/旧 CSS)、参考借鉴(分析喜欢的账号/网站/海报,转译气质而非抄袭)、零素材探索(原型卡投票速筛 + 风格原型库冷启动)。核心机制是交互式 picker 页面——候选方案渲染成实景小样,用户在浏览器里点选、微调、反馈,逐区块锁定、循环收敛。当用户说"提取我的设计/品牌/视觉风格"、"生成 design.md"、"建一套主题/theme"、"帮我定义设计语言"、"从这些图提取设计"、"我想要自己的品牌风格但没有素材"、"做一套配色和字体方案"时使用本 skill,即使用户没有明确说"设计系统"。

  • Muffled studio design

    muffled-studio/muffled.skills/skills/muffled-studio-design Skill

    no license0★ repo

    Use when generating branded UI, HTML mocks, marketing surfaces, or when the user asks for muffled.studio look-and-feel. Not for shadcn registry install steps (use muffled-ui).

  • Adding dbt unit test

    danielvogler/ai-skills-library/.agents/skills/adding-dbt-unit-test Skill

    0★ repo

    Creates unit test YAML definitions that mock upstream model inputs and validate expected outputs. Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt.

  • Agent redline

    rore/agent-redline/dist/agent-redline Skill

    0★ repo

    Use when setting up agent governance for a repo, or when working in a repo that contains agent-policy.yaml. Classifies structural risk and routes human attention to red-zone changes.

  • Handoff

    zhpy2004/claude-codex-handoff/claude-code/skills/handoff Skill

    0★ repo

    Hand off the current work to another AI coding tool (Codex), or resume work that another tool handed off, via a structured HANDOFF.md document in the project root. Use when the user wants to switch between Claude Code and Codex mid-task, "hand off", "交接", "save progress for the other tool", "pick up / resume / 接续 where the other tool left off", or run `/handoff save` or `/handoff resume`.

  • Bloom plan

    SunnyDevendranadh/Bloom/.claude/skills/bloom-plan Skill

    0★ repo

    Decision-transparent planning. 3-4 alternatives per decision with concrete examples and benchmarks. Adaptive scale. Self-audited benchmark quality. Interactive HTML companions.

  • Refine prompt

    knowingrohan/refine-prompt/skills/refine-prompt Skill

    0★ repo

    Transform a user's raw prompt into a clear, expert-level prompt for an AI coding or reasoning agent. Use when the user asks to refine, improve, rewrite, or engineer a prompt, especially when they want the output to leverage project context, agent memories, local instruction files, or available skills.

  • Codex dispatch

    ShehabYahya/codex-dispatch Skill

    0★

    Orchestrate an external implementer session through structured task packets, one session per commit-sized unit, output-batch monitoring, loop detection with batch-count self-recovery, and mandatory diff-review gates after every implementer task. Invoke explicitly via $codex-dispatch or when the user asks Codex to delegate implementation work to an external OpenCode session.

  • Agent disco

    elevationgain/agent-disco Skill

    0★

    Run structured product discovery led by the Disco persona (Senior PM) and produce agent-consumable, TDD-first specifications. Use whenever someone asks to define a feature, scope a product, write a PRD or spec, run product discovery, or produce requirements for an AI coding agent. Triggers include "Load Disco", "Activate Barry", "Activate Simon", "discovery doc", "feature spec", "PRD", "open questions", "ADR", "task plan", "semantic map", "agent handoff", "Figma to component map", "test generation brief", "readiness gate", and "audit loop". Two optional support personas can be activated on demand: Barry (Senior Business Analyst) for requirements precision, business rules, data modeling, and component reuse; Simon (Director of Engineering / Solution Architect) for architecture, reliability, security, and delivery trade-offs.

  • Hello world

    optimisuke/hello-gh-skills/skills/hello-world Skill

    no license0★ repo

    gh skill の動作確認用デモスキル。呼ばれたら Hello, World! と返す。

  • Meson advanced project design

    krxecs/meson-skills/skills/meson-advanced-project-design Skill

    0★ repo

    Advanced Meson architecture, feature options, dependency objects, generated sources, project layout, build reproducibility, and scalable project organization. Use when the user discusses project structure beyond basic build setup or asks about idiomatic Meson patterns.

    The same file is in 1 other repository

  • Parallel worktree dev

    SnowWarri0r/parallel-worktree-dev Skill

    0★

    Use when (a) developing multiple features in parallel on the same git repo with separate AI sessions, OR (b) starting a single new feature where isolating from current work matters — current branch has unfinished changes you don't want to stash, exploring an approach that might be thrown away, multi-step feature work that shouldn't block hotfixes or other tasks. Triggers — 多开, 并行开发, 多个 feature 同时开发, worktree 多开, 起新 feature, 起新分支不想 stash, 想保留当前工作, 隔离试验, 探索性重构, 多步骤 feature, 长 feature 开发, 大改动前隔离, AI session 之间互相干扰, port collision in parallel dev, .env collision, parallel feature dev, multiple AI sessions same repo, start new feature with isolation, exploratory branch.

  • Custom skill creator

    pngdeity/apm-user-repository/.agents/skills/custom-skill-creator Skill

    0★ repo

    Meta-skill for creating and packaging new AI agent skills. Use when requested to create a skill, document a multi-step process, or configure agent behavior as a procedural skill module. Not for single atomic functions or global architecture constraints — those go in AGENTS.md.

  • Design an interface

    popsiclelmlm/skills-cn/skills/deprecated/design-an-interface Skill

    0★ repo

    使用 parallel sub-agents 为一个 module 生成多个激进不同的 interface designs。当用户想设计 API、探索 interface options、比较 module shapes,或提到 "design it twice" 时使用。

  • Techtide alibaba ack container platform operator

    TechTideOhio/techtide-harness-kit/skills/alibaba/techtide-alibaba-ack-container-platform-operator Skill

    0★ repo

    Operate ACK clusters (managed/dedicated/serverless), ACR container registries, ASM service mesh, and container workload placement. Guide ACK type selection, OIDC workload identity, and image vulnerability posture.

  • Dragble ai

    Dragble/dragble-skills/dragble-ai Skill

    0★ repo

    Configure AI features and asset storage for the Dragble editor. Covers AI text generation, image generation, alt text, external AI backends, image upload, external S3 storage, and the Dragble managed storage mode.

  • Fbi skill

    xuluoforcainiao/fbi-skill/fbi-skill Skill

    no license0★ repo

    FBI 数据分析综合技能,通过 ChatBI API 提供报表搜索、报表解读、数据问答分析、T+1 日报生成五大能力。适用:搜索报表、解读报表、分析指标(UV/PV/GMV等)、数据趋势分析、异动归因、快速问数、基于 FBI 真实数据生成日报。根据用户意图自动路由到对应功能。

  • Rsdd

    jeremedia/rsdd Skill

    0★

    Use when a project has spec-layer artifacts (ADRs, spec-kit constitution/spec/plan, RFCs, architecture docs) and you need ongoing alignment between spec and code — not one-shot validation. Triggers include spec drift in conversation ("the code doesn't match what we said"), post-merge spec-vs-code reconciliation, designing a drift-detection workflow, integrating reasoning agents into spec-kit, or any moment when an agent is about to file an "out-of-spec" issue against a codebase.

  • Rein skill

    DtoTHEmoon/rein-skill Skill

    0★

    Rein是一个全程陪跑的Harness Engineering顾问,随项目自动感知AI工程化缺口,在对的时机给出刚好够用的建议。 必须触发的场景——只要对话中出现以下任何模式,立即激活Rein: 【重复失败模式】同一类AI行为错误在对话中出现超过一次;AI说做完了但实际有问题;改完某个东西,之前好的东西坏了;明明说过的规则这次又忘了;部署之后不知道有没有出问题。 【上下文丢失模式】用户在重新解释之前说过的背景;换了个会话什么都要重新交代;AI在不同会话里给出前后不一致的结果。 【规模跃迁模式】项目从内部工具变成对外交付;从单人变成多人协作;从单模块变成多模块并行;首次进入生产环境;开始有新人接手维护;任务链路明显变长。 【成本/效率异常模式】API账单出乎意料地高;AI在做大量无效重试;每次都要把同样的上下文重新说一遍;Multi-Agent跑起来比单Agent还慢;配置越来越多但项目没变快。 【过度工程化模式】CLAUDE.md明显超过150行但AI还是不遵守;规则越加越多但问题没解决;Skill太多不知道用哪个;感觉维护Harness比做项目本身更费时间。 【直接询问模式】用户问任何关于Harness配置、CLAUDE.md、Rule、Skill、验证脚本、Multi-Agent、AI工程化成本的问题。 - 用户提到数据泄露、密钥暴露、被攻击 - 用户问"这样安全吗"、"会不会泄露数据" - 用户准备对外部署或交付给客户 → 检查Q2安全红线是否到位,Q4安全基线是否在verify.sh里 绝对不触发:用户在正常推进业务需求、讨论代码实现细节、做产品或架构决策时,Rein保持沉默。没有明显缺口就不开口。

  • Comunicacion audiencias

    jleonceo/audience-analyst-swarm/skills/comunicacion-audiencias Skill

    0★ repo

    Skill de comunicación del enjambre de audiencias. Traduce los resultados del análisis a un informe y cuadro de mando para stakeholders de negocio: claro, directo, con comparación vs benchmark y recomendaciones accionables.

  • Ann handley

    Pesty-Marketing/agent-skills/ann-handley Skill

    0★ repo

    Apply Ann Handley's Everybody Writes framework to create or audit marketing content — blog posts, emails, homepages, About Us pages, social copy, or any customer-facing writing. Invoke when user says "use Ann Handley," "Everybody Writes," "apply the Handley framework," or asks for help with content voice, writing quality, or copy that needs to sound more human, or defining a brand voice. Not for structural/narrative frameworks (use the storybrand skill for that).

  • Tradingagents skill

    Alpha-Park/tradingagents-skill Skill

    no license0★

    Multi-Agent LLM Financial Trading Framework utilizing an Analyst Team, Researcher Team, Trader, and Portfolio Manager for comprehensive market analysis and strategy execution.

    The same file is in 1 other repository

  • First principles engineering operator

    walterkken/engineering-operator-agents/first-principles-engineering-operator Skill

    no license0★ repo

    Act as an employee-style engineering operator and multi-agent work coach using first-principles reasoning and the public Musk-style engineering algorithm: question requirements, delete unnecessary parts or process, simplify and optimize, accelerate cycle time, automate last, and run fast evidence-based iteration. Use when Codex is asked to help other agents plan or complete work, review an engineering plan, decompose a project, assign agent tasks, define acceptance criteria, remove unnecessary work, improve product design, software architecture, manufacturing process, operations workflow, cost reduction effort, or automation proposal.

  • Buddy ai

    ispacekid/buddy-ai Skill

    0★

    Make the AI talk like a real friend on WeChat / WhatsApp / iMessage instead of a polished assistant. Sends one short bubble at a time, drops most punctuation, uses slang and filler, occasionally fat-fingers a typo, has moods that linger, and sometimes just can't be bothered to answer everything. Optimized for Chinese and English. Toggle with /buddy-ai-on and /buddy-ai-off. This skill teaches the model to be imperfect on purpose.