AI Ml AI agent skills

8,771 skills in the archive. Read a skill’s instructions or open its original repository.

• Minutes Prep

  by @silverstein

  Interactive meeting preparation — builds a relationship brief and talking points before a call. Use when the user says "prep me for my call with", "I'm meeting with X", "prepare me for", "what should I bring up with", "meeting…

• Minutes X1 Closeout

  by @silverstein

  Prepare a sourced Minutes meeting outcome for human-governed closeout of existing X1 work. Use when the user wants a meeting decision or commitment to close, defer, escalate, or retire a specific X1 coordination thread. Never…

• Minutes Setup

  by @silverstein

  Guided first-time setup for Minutes — download whisper model, create directories, configure audio input. Use when the user says "set up minutes", "install minutes", "first time setup", "configure minutes", "get started with…

• Minutes Debrief

  by @silverstein

  Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that…

• Minutes Lint

  by @silverstein

  Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check",…

• Minutes List

  by @silverstein

  List recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they…

• Minutes Note

  by @silverstein

  Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during…

• Minutes Weekly

  by @silverstein

  Weekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week. Use when the user says "weekly review", "what happened this week", "weekly summary", "recap my week", "any…

• Minutes Cleanup

  by @silverstein

  Manage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage…

• Minutes Release Notes

  by @silverstein

  Draft user-facing Minutes release notes for a version from the commit range, recent GitHub releases, and the repository release checks. Use when the user asks to write, generate, prepare, revise, or review release notes or a…

• Minutes Video Review

  by @silverstein

  Analyze a product walkthrough, bug report video, Loom, or ScreenPal using Minutes transcription plus visual review. Use when the user wants a recorded demo or bug clip turned into a durable brief with transcript, key frames,…

• Minutes Ideas

  by @silverstein

  Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.

• Domain Ml

  by @actionbook

  Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理

• Minutes Graph

  by @silverstein

  Policy-safe relationship rankings, commitments, aliases, person profiles, and topic research. Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache.

• Minutes Mcp Recall

  by @silverstein

  Route meeting-recall questions to the right Minutes MCP tool.

• Dust Elasticsearch

  by @dust-tt

  Create, migrate, or query Elasticsearch indices in `front`. Use when adding a new front Elasticsearch index, changing mappings or settings, wiring indexing logic, or exposing Elasticsearch-backed analytics/search endpoints.

• Dust Translate

  by @dust-tt

  Translate or fix Dust product UI and Slack bot translations in the Lingui catalogs (`front/locales/*/**/messages.po`, `sparkle/src/locales/*/messages.po` and `connectors/locales/*/messages.po`). Use after `npm run i18n:extract`…

• Dust Hive

  by @dust-tt

  Information about dust-hive, a CLI tool for running multiple isolated Dust development environments. ALWAYS enable this skill when the working directory is under a repository's `.hives/` directory or `~/dust-hive/`, when its…

• Dust I18n

  by @dust-tt

  Make front and sparkle UI strings translatable with Lingui. Use when adding or changing user-visible text in `front/components`, `front/hooks` or `front/lib` React code or in `sparkle/src` components, when wrapping existing…

• Dust Webhook Source

  by @dust-tt

  Implement a new built-in webhook source provider in `front`. Use when adding a webhook provider such as Linear, GitHub, or Fathom, including provider research, OAuth prerequisites, provider-specific types and client code, preset…

• Dust Mcp Server

  by @dust-tt

  Step-by-step guide for creating new internal MCP server integrations in Dust that connect to remote platforms (Jira, HubSpot, Salesforce, etc.). Use when adding a new MCP server, implementing a platform integration, or…

• Dust Posthog Tracking

  by @dust-tt

  Track user interactions as PostHog events while implementing features in `front`, so their usage can be analysed later. Use when adding or changing a user-facing feature, flow, or surface, or when the user mentions PostHog,…

• Dust Llm

  by @dust-tt

  Step-by-step guide for adding support for a new LLM in Dust, and for deprecating or removing the model it supersedes (including the agent-config repoint migration). Use when adding a new model, updating a previous one, or…

• Dust Db Migration

  by @dust-tt

  Step-by-step guide for creating and running SQL schema migrations in `front` or `connectors` using the `npm run migration:*` tooling (pg-schema-diff + Umzug). Use when adding or removing columns, tables, or indexes that require…

• Dust Audit Log Event

  by @dust-tt

  Add a new audit log event in `front`. Use when instrumenting a new user or system action for WorkOS audit logging, including schema creation, `AuditAction` updates, and the correct emit call after the mutation path.

• Transcription Memory Reconstruction

  by @NxcoreAI

  Reconstruct a complete, searchable memory from an untrusted meeting or conversation transcript. Use for EverRoom background transcription-summary jobs when the caller requires the fixed memory JSON contract.

• Dust React Hook Form Writer

  by @dust-tt

  Write and refactor React forms using react-hook-form with Zod validation. Use when creating new form components, converting existing forms to react-hook-form, or implementing form validation patterns.

• Dust Writing React Effects

  by @dust-tt

  Writes React components without unnecessary useEffect. Use when creating/reviewing React components, refactoring effects, or when code uses useEffect to transform data or handle events.

• Document Export

  by @NxcoreAI

  One-shot export of a fixed Room document version to Feishu or Notion via the preinstalled lark-cli / OpenConnector channel, with explicit auth and confirmation gates.

• Dust Breaking Changes

  by @dust-tt

  CRITICAL guideline - Never introduce breaking changes to the private API without explicit user approval. Always warn and ask for validation first.

• Dust Temporal

  by @dust-tt

  Step-by-step guide for creating Temporal workflows in Dust. Use when adding background jobs, async processing, durable workflows, or task queues.

• Room Enrichment

  by @NxcoreAI

  Organize a newly created Context Room from its title and description into structured room info. Use for room-enrich tasks.

• Correction

  by @NxcoreAI

  Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.

• Document Cursor Completion

  by @NxcoreAI

  Complete a rich-text document at the cursor using the EverRoom FIM protocol. Use for editor cursor-completion requests.

• Parsing Workflow

  by @NxcoreAI

  Parse and validate one authorized Office or PDF file version without overstating unsupported multimodal coverage.

• Draft Create

  by @NxcoreAI

  Draft a brand-new document from the instruction and material, returning the title and chunked body markdown.

• Room Proposals

  by @NxcoreAI

  Recommend Context Rooms to create from a user description, uploaded materials, and extracted entity anchors.

• Brief Refresh

  by @NxcoreAI

  Regenerate a Context Room brief from the room's current documents and context. Use for brief-refresh tasks.

• Dust Test

  by @dust-tt

  Step-by-step guide for writing focused, practical tests for Dust codebases following the 80/20 principle.

• Dust Swagger

  by @dust-tt

  MANDATORY guideline - Always keep Swagger documentation in sync when modifying API endpoints or schemas.

• Entity Extraction

  by @NxcoreAI

  Extract searchable entities and a concise summary from a document for EverRoom knowledge routing.

• Rewrite

  by @NxcoreAI

  Rewrite only the supplied selectedText per the instruction and return the replacement fragment.

• Room Overview

  by @NxcoreAI

  Generate a source-grounded Context Room overview from Room facts and applied user corrections.

• Draft Edit

  by @NxcoreAI

  Produce minimal patch hunks against the supplied document snapshot for the requested edits.

• Merge Name

  by @NxcoreAI

  Suggest names for a Context Room created by merging two rooms. Use for merge-name tasks.

• Canonical Schema

  by @NxcoreAI

  canonical schema 字段语义与各 provider 原始格式要点（gmail/outlook/google-calendar）。产出格式映射时使用。

• Ingest Filter

  by @NxcoreAI

  Judge whether ingested materials contain information worth retaining in EverRoom.

• Entity Registration

  by @NxcoreAI

  Create canonical Room registration material from accumulated entity evidence.

• Entity Identity

  by @NxcoreAI

  Judge whether two evidence-backed names refer to the same real-world entity.

• Analysis Method

  by @NxcoreAI

  A structured method for evidence-based analysis of supplied content

• Draft Continue

  by @NxcoreAI

  Continue a document with genuinely new appended content only.

• Diary Timeline

  by @NxcoreAI

  将当天的多源事实整理为去重、按时间排序、可追溯的日记时间线。

• Browser Workflow Skill Builder

  by @openonion

  Create robust browser automation skills for sites like LinkedIn, X/Twitter, YouTube, Stripe, or other logged-in web apps by saving page context, analyzing HTML/CSS, writing skill-local JS extract/verify scripts, and using CSS…

• Topup

  by @openonion

  Check the OpenOnion balance and open the recharge page with the user's own key pre-filled. Reports the balance in plain money, says how long it lasts at $0.10/hour of browser time, and hands over a purchase link that needs no…

• Co Mail And Drive

  by @openonion

  Read and send mail from the user's own Gmail or Outlook account, safely stage Gmail draft attachments, send from the agent's own address, manage Outlook contacts and the Outlook calendar, and work with Google Drive files — with…

• Cli Skill Design

  by @openonion

  Design a `co <thing>` CLI surface and its SKILL.md together so an agent can drive it without guessing — every command ends by naming the next one, `--help` lists everything, and every failure says what to run instead. Use when…

• Find Selling Points

  by @openonion

  Mine the codebase for capabilities worth telling people about — the surprising, user-facing ones — and prove each against source before it may be published. Use when writing or auditing marketing copy, a landing page, a README,…

• Install Connectonion

  by @openonion

  Install and set up ConnectOnion on Windows, macOS, or Linux, initialize global credentials, and verify the requested CLI capabilities. Use for "install connectonion", "set up connectonion", "get me started with co", or missing…

• Co Browser

  by @openonion

  Drive one persistent, logged-in browser from the shell with `co browser`. Use when the user asks to open a page, log into a site, scrape/extract page content, fill forms, upload files, take screenshots, or automate any browser…

• Co Inbox

  by @openonion

  Drive `co feishu` / `co lark` — a chat bot as a directory of files. Use when an agent must receive messages from a Feishu or Lark group, reply to them, or run a command per message. Covers setup by QR, the nine verbs, the…

• Oo

  by @openonion

  Connect to a remote ConnectOnion agent, set up a publishable identity, publish selected skills, or follow and sync another publisher. Use for a 0x agent address, /oo, co announce, or co sub workflows; not for ordinary…

• Ship Feature

  by @openonion

  Ship a feature end-to-end — update tests, docs, docs-site, then release to PyPI. Use when user says "ship", "ship feature", "release", or asks to publish a new version.

• Agent Identity

  by @openonion

  Verify an agent's live address and billing account before sharing a chat link, diagnosing a deploy mismatch, or deciding why two hosts share an identity.

• Dashboard

  by @openonion

  Update the agent's Control Center. Use when the user says "update my Control Center", "update my dashboard", "redesign my home", or "/dashboard".

• Co Synology

  by @openonion

  Inspect a configured Synology NAS and manage its ordinary files and sharing links with the twenty-command co syno core.

• Commit

  by @openonion

  Create git commits with good messages. Use when user says "commit", "create commit", or asks to commit changes.

• Co Google

  by @openonion

  Route Google account work to Gmail, Drive, Calendar, and YouTube CLI commands using one locally saved login.

• Review Pr

  by @openonion

  Review GitHub pull requests. Use when user says "review PR", "review pull request", or "/review-pr".

• Control Center Review

  by @openonion

  Review one captured Control Center build before runtime activation.

• Standard

  by @zhnt

  Apply the standard Coding workspace workflow with explicit inspection, scoped edits, and proportionate validation.

• Personal Ip Knowledge Builder

  by @limecloud

  将访谈稿、聊天记录、简历、公开内容、业务资料、案例和既有 DOCX/Markdown 文档，提炼成可被 AI 长期调用的个人 IP 知识库。适用于用户要求“生成个人知识库”“整理成个人 IP 成品知识库”“为创始人/专家/讲师/主播/顾问建立AI知识库”“把资料变成个人IP底层提示词/写作风格库/故事素材库/话术库”的场景。

• Brand Persona Knowledge Builder

  by @limecloud

  将品牌定位、价值观、受众画像、语气风格、内容样例、危机回应和表达禁区，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的品牌人设知识库。适用于用户要求“整理品牌人设”“沉淀品牌口吻”“把品牌资料变成可复用语气库”“维护品牌 persona pack”的场景。

• Campaign Operations Knowledge Builder

  by @limecloud

  将活动目标、用户路径、渠道分工、物料资产、时间节奏、风险预案和复盘结论等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理活动 / Campaign 运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。

• Organization Knowhow Knowledge Builder

  by @limecloud

  将团队 SOP、交付流程、角色职责、项目复盘、FAQ、决策边界和升级机制，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的组织经验知识库。适用于用户要求“整理组织知识库”“沉淀团队 SOP”“把交付经验变成项目资料”“维护组织 know-how”的场景。

• Private Domain Operations Knowledge Builder

  by @limecloud

  将用户分层、社群 SOP、触达节奏、转化话术、活动机制和服务边界等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理私域 / 社群运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。

• Live Commerce Operations Knowledge Builder

  by @limecloud

  将直播排期、货盘节奏、场控流程、主播话术、互动机制、异常预案和复盘指标等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理直播运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。

• Brand Product Knowledge Builder

  by @limecloud

  将品牌产品资料、规格参数、卖点证据、FAQ、价格权益、竞品区别和合规边界，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的产品资料知识库。适用于用户要求“整理产品知识库”“沉淀产品 FAQ”“把品牌产品资料变成项目资料”“维护产品资料包”的场景。

• Growth Strategy Knowledge Builder

  by @limecloud

  将增长目标、指标体系、渠道策略、实验计划、复盘结论、资源约束和停止条件，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的增长策略知识库。适用于用户要求“整理增长知识库”“沉淀增长策略”“把增长计划变成项目资料”“维护增长实验资料包”的场景。

• Content Operations Knowledge Builder

  by @limecloud

  将选题日历、栏目矩阵、素材资产、发布节奏、复盘结论和内容边界等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理内容运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。

• Content Post With Cover

  by @limecloud

  生成可直接发布的内容主稿（默认公众号长文风格）并自动生成 1 张头图，最终以 write_file 落盘。

• Knowledge Builder

  by @limecloud

  兼容旧版 Agent Knowledge 编译流程的 deprecated 兜底 Builder。仅用于未知或历史 pack 类型；标准 persona / data pack 必须优先委托内置专用 Builder Skill。

• Control Browser

  by @limecloud

  Research and inspect pages through Lime's managed browser session.

• Image Generate

  by @limecloud

  仅在用户显式使用 @配图/@修图/@重绘/@image，或已明确确认调用画图功能后，根据文本描述生成配图素材（非封面场景）。

• Article Writer

  by @limecloud

  内容工厂专用写作 Skill，生成批量文案、短视频脚本和图片提示词，并输出可回写的 workspacePatch。

• Presentation Generate

  by @limecloud

  根据目标说明生成一份可直接讲述、继续导出的单文件演示稿 Markdown，并落到工作区供右侧 viewer 预览。

• Knowledge Builder

  by @limecloud

  内容工厂专用知识整理 Skill，把项目资料、素材和运营经验整理成场景生成与内容生产可用的事实输入。

• Webpage Generate

  by @limecloud

  根据目标说明生成可直接预览的单文件 HTML 网页，并落到工作区供右侧 viewer 预览。

• Form Generate

  by @limecloud

  根据目标说明生成一份可直接在聊天区渲染的 A2UI 表单，复用 Lime 现有表单协议。

• Content Reviewer

  by @limecloud

  内容工厂专用复核 Skill，检查事实依据、平台适配、AI 味、风险和人工确认建议。

• Library

  by @limecloud

  【外部资产库】读取项目参考资料（/project）或风格参考（/styles）。

• Modal Resource Search

  by @limecloud

  检索图片、背景音乐、音效、视频等素材；图片优先直搜候选，其他资源走任务主链。

• Analysis

  by @limecloud

  对当前文本、对话或显式文件内容做结构化分析，并区分事实、判断与待确认项。

• Translation

  by @limecloud

  将当前文本、对话或显式文件内容翻译成目标语言，并保留原意与关键信息。

• Cover Generate

  by @limecloud

  为文章或视频生成平台封面图，并写回主稿（封面场景优先使用本技能）。

• Research

  by @limecloud

  联网信息检索与趋势调研（优先产出可引用结论，而非原始片段堆砌）。

• Broadcast Generate

  by @limecloud

  将文章整理为可转播客音频的源文本（下游负责真实音频合成）。

• Report Generate

  by @limecloud

  联网检索并产出结构化研究报告，强调结论、证据、风险与建议。

• Pdf Read

  by @limecloud

  读取本地或工作区 PDF 内容，并输出结构化解读结果。

• Summary

  by @limecloud

  提炼当前文本、对话或显式文件内容中的关键要点与结论。

• Url Parse

  by @limecloud

  解析外部 URL 内容，并沉淀为可阅读的文本结果。