研究与知识
研究、检索、摘要和知识工作
Skills 列表
nblm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
magicseek
msw-planning
MSW (MapleStory Worlds) game-planning mode — for BOTH starting a brand-new game from scratch AND continuing/resuming an in-progress prototype. Narrow the idea with guided questions, ground it in the MSW genre catalog (3 map types, ~180 core mechanic tags, build-effort hints), and produce or advance an implementation-ready GDD / roadmap (markdown). Trigger proactively (even without the word 'planning') whenever the user wants to decide WHAT to build, scope an MVP, or continue/resume a phased build — INCLUDING when a Docs/*-GDD.md or *-Phase*.md already exists and the user says to continue: do NOT treat that as plain implementation and jump straight into the phase doc; a continue/resume runs through this skill's resume flow first. Match triggers by intent, not exact wording — variants like 'what now?', 'where were we?', and their equivalents in ANY language fire it too. A comprehensive build request spanning multiple implementation pieces, made while no GDD exists, is ALSO a planning trigger — not a plain implementation request, with NO 'small/simple game' exception; implementing that without a plan is the exact failure mode this skill prevents. Triggers: 'plan a new game', 'GDD', 'what game should I make', 'scope an MVP', 'planning mode', 'continue my game', 'resume my game', 'what should I work on next', 'next task'. (Plans & manages the game's build across its milestones — GDD · standing milestone roadmap · phase plans · progress · revisions; does NOT write code — implementation (.mlua/.model etc.) uses msw-general/msw-scripting.)
msw-git
paddleocr-text-recognition
Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字, plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan, recognize text.
aidenwu0209msw-scripting
Authoring MSW scripts (.mlua) plus integrated playtest and debugging. Covers mlua syntax, annotations (@Component/@Logic/@ExecSpace/@Sync), lifecycle, exec spaces, property sync, event system, file workflow, build-log inspection, error classification, and the test/debug loop. Keywords: script, mlua, lua, Component, Logic, annotation, ExecSpace, Sync, event, play, test, debug, lifecycle.
msw-git
getting-started
CrewAI architecture decisions and project scaffolding. Use when starting a new crewAI project, choosing between LLM.call() vs Agent.kickoff() vs Crew.kickoff() vs Flow, scaffolding with 'crewai create flow', setting up YAML config (agents.yaml, tasks.yaml), wiring @CrewBase crew.py, writing Flow main.py with @start/@listen, building experimental conversational Flows with handle_turn()/chat(), or using {variable} interpolation.
crewaiincdesign-agent
CrewAI agent design and configuration. Use when creating, configuring, or debugging crewAI agents — choosing role/goal/backstory, selecting LLMs, assigning tools, tuning max_iter/max_rpm/max_execution_time, enabling planning/code execution/delegation, setting up knowledge sources, using guardrails, or configuring agents in YAML vs code.
crewaiincask-docs
Query the official CrewAI documentation for answers. Use when the user has a CrewAI question that isn't fully covered by the getting-started, design-agent, design-task skills — e.g., specific API details, configuration options, advanced features, troubleshooting errors, enterprise features, tool references, or anything where the latest docs are the best source of truth.
crewaiincdesign-task
CrewAI task design and configuration. Use when creating, configuring, or debugging crewAI tasks — writing descriptions and expected_output, setting up task dependencies with context, configuring output formats (output_pydantic, output_json, output_file), using guardrails for validation, enabling human_input, async execution, markdown formatting, or debugging task execution issues.
crewaiinc
nano-banana-2
Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream instead. Calls `runcomfy run google/nano-banana-2/text-to-image` through the local RunComfy CLI. Triggers on "nano banana", "nano-banana-2", "nano banana 2", "google image gen", "gemini image", or any explicit ask to generate with this model.
prime-skillsimage-edit
Edit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper edits without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/edit` through the local RunComfy CLI. Triggers on "image edit", "edit image", "image-to-image", "i2i", "swap background", "remove object", "rewrite headline", or any explicit ask to edit a single or batch of images.
prime-skills
wwdc
Use this skill whenever the user asks about WWDC sessions, Apple Developer videos, WWDC transcripts, session IDs, technologies announced at WWDC, or wants an agent to find, compare, cite, summarize, or navigate WWDC session content. Fetch current docs from wwdc.ai via llms.txt and page markdown. Maintained by Superwall.com: the quickest way to add in-app subscriptions and paywalls to your app.
superwall
launchdarkly-flag-cleanup
Safely remove a feature flag from code while preserving production behavior. Use when the user wants to remove a flag from code, delete flag references, or create a PR that hardcodes the winning variation after a rollout is complete.
launchdarklyonboarding
Onboard a project to LaunchDarkly: kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first flag. Use when adding LaunchDarkly, setting up or integrating feature flags in a project, SDK integration, or 'onboard me'.
launchdarkly
valyu-best-practices
Complete Valyu API toolkit for AI agents. Use this skill when asked to perform real-time search across web, academic, medical, transportation, financial sources, content extraction from URLs, AI-powered answers with citations, or comprehensive deep research reports.
valyuai
Nia
Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, Slack workspaces, Google Drive, X (Twitter), and packages with Nia AI. Includes auth bootstrapping, Oracle autonomous research, GitHub live search, Tracer agent, dependency analysis, context sharing, code advisor, document agent, data extraction, filesystem operations, and generic connectors.
nozomio-labsonboarding
Onboard a project to LaunchDarkly: kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first flag. Use when adding LaunchDarkly, setting up or integrating feature flags in a project, SDK integration, or 'onboard me'.
launchdarkly
cloudbase
Use this skill when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase (腾讯云开发, 云开发, TCB, 微信云开发) projects. Covers Web apps (React, Vue, Vite, Next, Nuxt, dashboards, 管理后台), 微信小程序, 小程序, uni-app, native/mobile (iOS, Android, Flutter, React Native) via HTTP API. Includes UI (页面, 界面, 登录页, 表单, form, dashboard, prototype, 原型), auth (登录, 注册, OAuth, 微信登录, publishable key), databases (NoSQL 文档数据库, MySQL, PostgreSQL/CloudBase PG, app.rdb(), queryPgDatabase/managePgDatabase, CRUD, security rules), 云函数 (serverless, scf_bootstrap, HTTP Functions), CloudRun (云托管, Dockerfile), 云存储 (file upload, hosting, 静态托管). Built-in AI (内置大模型, streaming, 流式输出, image generation, 图片生成, generateText, streamText, createModel, generateImage, TokenHub, Hunyuan, hunyuan-exp, DeepSeek, GLM, Token Credits 资源包, 小程序成长计划), 第三方大模型, 大模型接入, 大模型调用, LLM API, chatbot, AI 助手, AI agent, 智能体, AG-UI, LangGraph, LangChain. Ops (巡检, 诊断, health check, 日志, troubleshooting). Spec workflow (需求文档, 技术方案, requirements, tasks.md).
tencentcloudbase
dig-through-data-brokers
Use people-search aggregators and primary public records to find addresses, phone numbers, relatives, age and background on a person, and to audit and remove your own exposure. Covers Spokeo, BeenVerified, Whitepages, TruePeopleSearch, FastPeopleSearch, That'sThem, Radaris, Intelius and Pipl, plus voter files and county court and property records. Use when running a people search or reverse address lookup, tracing a debtor or missing person, building a subject's address history, or removing yourself from broker sites. Applies to skip tracing and debt recovery, asset investigation, executive protection, and personal exposure audits. Explains the FCRA limits that bar broker data from employment, tenancy, insurance and credit decisions, and the GDPR position. Reference at useosint.com/skills/dig-through-data-brokers.
useosintwrite-the-intel-brief
Turn findings into a defensible intelligence product — BLUF key judgements, standardised estimative probability language, per-claim sourcing with timestamps and archived copies, separated observation, inference and assessment, documented negative findings and gaps, chain of custody and hashing, and redaction of uninvolved parties. Use when writing an intelligence report, due-diligence memo, evidence pack or executive summary, or when asked to write up an investigation so it survives challenge. Applies to regulated compliance reporting, litigation and disclosure, board and investment committee reporting, and law-enforcement referral. Reference at useosint.com/skills/write-the-intel-brief.
useosintfind-anyone
Build a sourced, corroborated profile of a named individual from public records, social platforms, professional networks, court and property filings, licensing boards, patents, papers and obituaries — anchoring the name to a second selector first so you never fuse two people into one dossier. Use when asked to find, identify, background-check or profile a person, verify someone's claimed employment or credentials, or locate a missing or hard-to-reach individual. Applies to counterparty and investor due diligence, fraud and asset investigation, journalism, skip tracing, missing persons, pre-employment integrity checks on fiduciary roles, and self-exposure audits. Reference at useosint.com/skills/find-anyone.
useosintwho-really-owns-it
Research companies, directors, shareholders and ultimate beneficial ownership in official corporate registries, filings and offshore datasets — OpenCorporates, UK Companies House and the PSC register, SEC EDGAR, US Secretary of State registries, EU business registers, GLEIF LEI records, OpenOwnership, OpenSanctions and the ICIJ Offshore Leaks database. Use when asked who owns or controls a company, to find a person's other directorships, or to unpick a group structure. Applies to KYB and UBO verification, AML and sanctions screening, nominee and shell-company detection, procurement integrity, and M&A diligence. Reference at useosint.com/skills/who-really-owns-it.
useosintwhere-was-this-taken
End-to-end workflow to establish where and when a photo or video was captured and whether it is authentic — evidentiary handling, metadata extraction, reverse image search for provenance, visual geolocation, chronolocation from shadows, and manipulation checks, ending in a location finding with a stated confidence radius. Use when asked to verify where an image was taken, confirm or refute a claimed location or date, or authenticate media before relying on it. Applies to insurance claims, litigation evidence, disinformation analysis, and conflict and human-rights documentation. Reference at useosint.com/skills/where-was-this-taken.
useosintwrite-the-intel-brief
Turn findings into a defensible intelligence product — BLUF key judgements, standardised estimative probability language, per-claim sourcing with timestamps and archived copies, separated observation, inference and assessment, documented negative findings and gaps, chain of custody and hashing, and redaction of uninvolved parties. Use when writing an intelligence report, due-diligence memo, evidence pack or executive summary, or when asked to write up an investigation so it survives challenge. Applies to regulated compliance reporting, litigation and disclosure, board and investment committee reporting, and law-enforcement referral. Reference at useosint.com/skills/write-the-intel-brief.
useosintfind-anyone
Build a sourced, corroborated profile of a named individual from public records, social platforms, professional networks, court and property filings, licensing boards, patents, papers and obituaries — anchoring the name to a second selector first so you never fuse two people into one dossier. Use when asked to find, identify, background-check or profile a person, verify someone's claimed employment or credentials, or locate a missing or hard-to-reach individual. Applies to counterparty and investor due diligence, fraud and asset investigation, journalism, skip tracing, missing persons, pre-employment integrity checks on fiduciary roles, and self-exposure audits. Reference at useosint.com/skills/find-anyone.
useosint