Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 80 149 files from 1 774 authors, of which 62 489 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Parallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section.
Unified codebase intelligence. Handles all questions about structure, logic, risk, and dependencies. Combines natural-language Q&A with deterministic lookups and pre-edit blast radius checks.
Pre-deploy and post-deploy checklist skill. Ensures env vars, migrations, CI, rollback plan, smoke tests, and monitoring are verified before and after every deployment.
Use when asked to audit a module, check its health, or assess whether it should be refactored. Runs structural query, risk check, and test generation automatically.
Unified development and design standards. Enforces code quality (complexity < 8), strict naming conventions, and the mandatory use of approved UI component libraries.
Unified Git workflow. Manages the entire task lifecycle: branch creation (sprint), atomic commits (git-os), and PR opening (pr-create).
USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep research, news, images, videos, places, custom ranking
USE FOR getting local business/POI details. Requires POI IDs obtained from web-search (with result_filter=locations). Returns full business information including ratings, hours, contact info. Max 20 IDs.
USE FOR news search. Returns news articles with title, URL, description, age, thumbnail. Supports freshness and date range filtering, SafeSearch filter and Goggles for custom ranking.
USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions grounded in web search context. Max 20 IDs per request.
Web search using the Brave Search CLI (`bx`). Use for ALL web search requests — including "search for", "look up", "find", "what is", "how do I", "google this", and any request needing current or external information. Prefer this over the built-in web_search tool whenever bx is available. Also use for: documentation lookup, troubleshooting research, RAG grounding, news, images, videos, local places, and AI-synthesized answers.
USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic applications.
USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.
USE FOR AI-grounded answers via OpenAI-compatible /chat/completions. Two modes: single-search (fast) or deep research (enable_research=true, thorough multi-search). Streaming/blocking. Citations.
USE FOR web search. Returns ranked results with snippets, URLs, thumbnails. Supports freshness filters, SafeSearch, Goggles for custom ranking, pagination. Primary search endpoint.
USE FOR video search. Returns videos with title, URL, thumbnail, duration, view count, creator. Supports freshness filters, SafeSearch, pagination.
USE FOR query autocomplete/suggestions. Fast (<100ms). Returns suggested queries as user types. Supports rich suggestions with entity info. Typo-resilient.
USE FOR spell correction. Returns corrected query if misspelled. Most search endpoints have spellcheck built-in; use this only for pre-search query cleanup or "Did you mean?" UI.
小红书 / 抖音 / 快手 / 视频号 自媒体「(compose 素材打底 →) 找对标 → 拆爆款 → 套自己」四命令闭环。给我的账号 / 选题方向 / 原始素材（文档/图片/视频），吐出"可发的下一条笔记初稿"。当用户说"找对标"、"拆这条爆款"、"对着这条仿写"、"下一条该写什么"、"我这个号缺爆款选题"、"帮我写一条对标 XX 的笔记"、"我有素材帮我写一条能爆的"、"这份文档/这组图/这段视频能出一条爆款吗"时调用。诊断模式（"为什么不爆"）走 references/diagnostic-mode.md。
Use when the user wants a complete, publication-grade research paper on a specific topic — produces 200+ real citations, 4–8 publication-grade figures, and 7 sections of substantive prose compiled to PDF in one pass. No skeleton stage.
Generate beautiful, high-resolution mindmaps from Markdown unordered lists. Outputs interactive HTML, HD PNG, and PDF with colorful branch themes.
Use when the user wants an end-to-end AI4S research pipeline — broad direction or specific topic in, full research package out (exploration + literature survey + experiment + paper). Meta-skill that chains the four downstream skills in order. Pure markdown, no Python runtime.
Use when the user has a vague research direction and wants to explore feasible specific topics. Outputs a structured analysis with candidate topics, innovation/feasibility scoring, and a pre-survey of 20–30 representative works. Single-stage, no Python runtime.
Use when the user wants a comprehensive literature survey on a specific research topic. Outputs a complete PDF survey (6–20 pages, 60+ real citations, 100+ recommended) with LaTeX source, topic-specific publication figures, and a classified literature table. Single-stage, no Python runtime.
Use when the user wants a paper audited for integrity issues — image misuse, numerical anomalies, logical gaps — and needs a reviewable evidence report. Works on external papers (PDF / DOI / arXiv) and on outputs from a local paper-writer run. Single-stage skill.
Use when the user has a research question and needs a complete experiment package — design document, runnable code, results (measured or simulated with honest provenance), publication-grade figures, structured report. Single-stage, no Python runtime.
SwiftUI frontend visual design skill. Creates beautiful, distinctive iOS/macOS interfaces that avoid generic AI slop patterns. Covers design direction, layout systems, typography, color, spacing, brand integration, and design review. Use when designing new SwiftUI views, reviewing UI quality, creating iOS prototypes, choosing visual styles, improving app aesthetics, or when the UI looks generic or AI-generated.
微信发信能力：通过 Windows 桌面微信发送文本、图片URL或本地文件。适合各类 Agent 在本机直接发送一次性消息。触发词：给[某人]发微信、通知[某人]、把这个用微信发给[某人]、用微信发个图片、把本地文件发给[某人]
| 拉片：把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面。 分工刻在骨子里：**能量的都由代码量**（切点来自 ffmpeg 场景检测，时长是切点相减， 运动量是逐帧差分的中位数），模型只判断它真正该判断的四件事（景别 / 类别 / 运镜 / 画面）， 然后每一条判断都被代码当场对账——**声称推拉摇移却实测几乎不动，门直接拦**。 看片走联系表（每镜起手帧 + 收尾帧各拼一张大图，一屏二十几个镜头，a/b 对照就是运镜）， 不是一张张翻。检测漏刀多刀用 recut 补刀并刀，自动重编号重算时长，手改边界过不了门。 产出 shots.json + Markdown 镜头表 + **单页交互式拉片报告**：内嵌播放器（播放时同步高亮镜头、 点镜头跳转）、镜头节奏带、可搜索可筛选可排序的镜头表（列表 / 卡片两种视图、首尾关键帧并排、 点图开大图）、景别类别运镜分布、出场人物、质量门、导出 JSON。单文件零依赖，离线双击能开。 14 道质量门全部由脚本确定性检查。 零依赖、零 API key，只要 node 和 ffmpeg。 Use when asked to 拉片、拆镜头、分析视频镜头、镜头时长、景别、运镜、镜头表、 video shot breakdown、shot list from video。
Precise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before any interface change, continuous refactoring task, sprint work estimation, or when navigating unfamiliar or large legacy codebases. Requires Python 3.10+ and shell. Use nexus-mapper instead when building a full .nexus-map/ knowledge base.
Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead.
Generate Mermaid diagrams (.mmd) and export to PNG/SVG/PDF using mmdc CLI or Kroki API. USE THIS SKILL when user mentions diagram, flowchart, sequence diagram, class diagram, ER diagram, state machine, architecture, visualize, git graph, 画图, 架构图, 流程图, 时序图. PROACTIVELY USE when explaining ANY system with 3+ components, API flows, authentication sequences, class hierarchies, database schemas, or state machines. Supports 12+ diagram types with fully automatic layout.
Required for 4+ step requests; add tasks at start and update status after each step.
Analyze text content and produce statistics including word count, line count, character count, most frequent words, and readability metrics. Works on any plain text input provided inline or from a file path.
Evaluate mathematical expressions and unit conversions. Handles arithmetic, percentages, exponents, and common unit conversions (temperature, distance, weight). No external dependencies.
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.
> Collaboratively design, implement, review, and refine software features with a human developer using an iterative pair programming workflow. Prioritize understanding, explicit approval, small reviewable changes, and synchronized specifications.
> Build Spring Boot 4.x applications following the best practices. * When developing Spring Boot applications using Spring MVC, Spring Data JPA, Spring Modulith, Spring Security * To create recommended Spring Boot package structure * To implement REST APIs, entities/repositories, service layer, modular monoliths * To use Thymeleaf view templates for building web applications * To write tests for REST APIs and Web applications * To write ArchUnit tests for testing architecture * To configure the recommended plugins and configurations to improve code quality, and testing while using Maven. * To use Spring Boot's Docker Compose support for local development * To create Taskfile for easier execution of common tasks while working with a Spring Boot application
> This skill will add jspecify dependency, configure Maven or Gradle build to automatically use jspecify for checking Nullability issues.
Design, build, and optimize dashboards for RIA practice management with AUM tracking, revenue analytics, and KPI frameworks. Use when the user asks about tracking firm-level metrics, monitoring advisor productivity, measuring organic growth rate, analyzing client retention and attrition, building executive or branch manager views, setting up exception alerts for NIGO and operational items, benchmarking against industry peers, or designing role-based dashboard access. Also trigger when users mention 'how is the practice doing', 'revenue per advisor', 'client attrition', 'net new assets', 'effective fee rate', 'practice benchmarking', 'AUM growth decomposition', or 'advisor capacity'.
Build and manage advisory fee billing operations from fee schedule design through calculation, collection, revenue recognition, and compliance disclosure. Use when the user asks about tiered or breakpoint fee schedules, billing cycle configuration, AUM valuation for billing, direct-debit vs invoice collection, GAAP revenue recognition for fees, ADV Part 2A or Reg BI fee disclosure, diagnosing billing exceptions or refunds, migrating from spreadsheet billing to automated systems, or forecasting advisory revenue. Also trigger when users mention 'fee calculation', 'billing engine', 'effective fee rate', 'household billing aggregation', 'mid-period adjustment', 'billing in advance vs arrears', 'fee compression', or 'ERISA 408(b)(2)'.
Integrate financial planning engines with the advisor technology stack — data flows between planning tools, CRM, PMS, custodians, and aggregation platforms; capital market assumption (CMA) governance and synchronization; plan-to-IPS-to-model linkage; and governed tax reference parameters in planning tools. Use when the user asks about connecting eMoney, MoneyGuidePro, or RightCapital to CRM or portfolio systems, eliminating manual re-entry between systems, keeping plan and portfolio assumptions consistent, mapping plan outputs (required return, risk capacity, withdrawal schedule) into the IPS and model assignment, or establishing plan update cadence and data-freshness rules. Also trigger on 'plan-to-IPS linkage', 'assumption synchronization', 'CMA governance', or 'planning tool integration'. For planning methodology itself — Monte Carlo modeling, Roth conversion strategy, Social Security claiming, retirement projections — use financial-planning-workflow instead.
Orchestrate the advisor workflow for assembling and delivering a comprehensive financial plan — data gathering, cash flow analysis, retirement modeling, Monte Carlo analysis, Roth conversion and withdrawal sequencing, Social Security claiming strategy, education and estate goals, scenario modeling, and prioritized recommendations. Use when the user asks about building a financial plan, structuring a planning engagement, retirement or Social Security modeling, Roth conversion strategy, scenario analysis, prioritizing competing recommendations, preparing a plan presentation, or deciding when a plan needs updating. Also trigger on 'comprehensive financial plan', 'discovery meeting', 'retirement modeling', 'Monte Carlo', 'Roth conversion', 'Social Security claiming', 'savings rate', or 'is my client on track'. For planning-tool data flows, capital market assumption governance, or connecting planning software to CRM/PMS, use financial-planning-integration instead.
Design and optimize CRM systems and client lifecycle workflows for advisory firms, covering segmentation, household management, service tiers, and retention analytics. Use when the user asks about client segmentation models, building household structures, defining service tier SLAs, scheduling reviews, tracking lifecycle stages from prospect through estate, identifying at-risk clients, analyzing wallet share, consolidating held-away assets, or evaluating CRM platforms. Also trigger when users mention 'client segmentation', 'retention risk', 'at-risk clients', 'household linking', 'multi-generational', 'service tiers', 'Redtail', 'Wealthbox', 'Salesforce for advisors', 'referral tracking', or 'contact gap'.
Design, generate, and deliver client performance reports across all channels, covering quarterly reports, tax reporting, portal integration, and compliance review. Use when the user asks about building or redesigning report templates, choosing what to include in quarterly or annual client reports, transitioning from print to digital delivery, integrating a client portal, presenting net-of-fee performance with benchmarks, managing report production timelines, or handling e-delivery consent. Also trigger when users mention 'client reporting', 'quarterly performance report', 'report customization', 'tax lot report', '1099 supplement', 'report disclaimers', 'UHNW reporting', or 'report QA process'.
Prepare advisors for client review meetings by assembling context packages, performance summaries, drift analysis, talking points, and meeting agendas. Use when the user asks about preparing for a client review, building a pre-meeting checklist, generating talking points for an upcoming meeting, identifying allocation drift before a review, automating review prep workflows, or assembling a meeting package with exhibits. Also trigger when users mention 'client meeting prep', 'review preparation', 'what should I discuss with my client', 'proactive recommendations', 'life event triggered review', 'meeting agenda', or 'compliance pre-check before review'.
Design and implement end-to-end client onboarding workflows from prospect intake through funded account, covering KYC verification, document collection, e-signature, and custodian submission. Use when the user asks about building a digital onboarding flow, integrating identity verification or CIP checks, reducing NIGO rejection rates, opening complex account types like trusts or entities, connecting to custodian APIs, designing suitability questionnaires, or comparing advisor-assisted vs self-service models. Also trigger when users mention 'new account opening', 'onboarding bottleneck', 'KYC integration', 'beneficial ownership', 'OFAC screening', 'account funding', or 'onboarding automation'.
Design and implement next-best-action engines that surface proactive, prioritized recommendations to advisors based on portfolio, life, market, and compliance events. Use when the user asks about building event-driven advisor alerts, designing trigger logic for portfolio drift or large cash movements, prioritizing competing actions across a book of business, routing NBA recommendations to the right team member, measuring NBA acceptance rates, or automating compliance-driven actions like annual review reminders. Also trigger when users mention 'next best action', 'advisor nudges', 'proactive outreach', 'what should I do for this client', 'event-driven triggers', 'action queue', 'client contact gap', 'RMD reminder', or 'advisor productivity tool'.
Manage the advisor trade lifecycle from order entry through settlement, covering block trading, allocation, pre-trade compliance, custodian routing, and error correction. Use when the user asks about designing an OMS for an RIA, executing model portfolio changes across many accounts, structuring block trades with fair allocation, configuring pre-trade compliance rules or restricted lists, routing orders to multiple custodians, handling trade errors or corrections, managing cash in trading workflows, or evaluating OMS platforms. Also trigger when users mention 'block trade', 'trade allocation', 'order management system', 'iRebal', 'Orion Trading', 'Tamarac Trading', 'best execution', 'trade error', 'mutual fund vs ETF orders', or 'audit trail'.
Select, configure, and operate portfolio management systems for advisory firms, covering model portfolios, UMA/sleeve management, drift monitoring, rebalancing, and custodian data feeds. Use when the user asks about choosing a PMS platform, building or distributing model portfolios, implementing UMA or sleeve-based management, setting drift monitoring thresholds, aggregating held-away assets, reconciling PMS with custodian records, configuring PMS-based billing, or troubleshooting custodian feed issues. Also trigger when users mention 'portfolio management system', 'Orion', 'Black Diamond', 'Tamarac', 'Addepar', 'Advent APX', 'model portfolio', 'sleeve management', 'rebalancing engine', 'custodian feed', or 'PMS migration'.
Process and manage account transfers between and within financial institutions. Use when handling full or partial ACAT transfers between broker-dealers, troubleshooting ACAT rejection codes or FINRA Rule 11870 timelines, setting up non-ACAT transfers (Fund/SERV, DTC free delivery, physical certificates), processing internal journal entries, handling retirement rollovers or Roth conversions with proper tax reporting, transferring cost basis under IRC Section 6045A, moving decedent assets to beneficiaries with date-of-death step-up, or reconciling residual credits and fractional shares after transfer completion.
Generate end-to-end investment proposals covering risk profiling, model portfolio recommendation, fee illustration, projections, and compliance review. Use when the user asks about creating a proposal for a prospect, mapping risk questionnaire scores to model portfolios, building fee illustrations with tiered costs, producing Monte Carlo or scenario projections, analyzing a prospect's current portfolio for improvement opportunities, reviewing proposals for SEC Marketing Rule compliance, or designing proposal templates for a multi-advisor firm. Also trigger when users mention 'investment proposal', 'proposal generation', 'risk profiling', 'Riskalyze', 'Nitrogen', 'fee illustration', 'transition analysis', 'current vs proposed portfolio', or 'proposal compliance review'.
Embed compliance controls into account opening and verify regulatory readiness. Use when designing CIP/KYC identity verification gates, implementing OFAC and sanctions screening at onboarding, collecting beneficial ownership certification for entity or trust accounts, building risk-based approval tiers that route applications by risk level, defining compliance screening requirements and exception tracking, adding senior investor protections (FINRA Rules 2165/4512) or trusted contact procedures, establishing CDD risk ratings and ongoing monitoring triggers, or preparing account opening procedures for SEC or FINRA examination. For the operational pipeline these controls plug into, see account-opening-workflow.
Design and operate back-office account opening pipelines from application intake through custodian submission and activation. Use when building account opening automation, reducing NIGO rejection rates from custodians or clearing firms, defining document requirements for trusts, entities, IRAs, or estate accounts, setting up multi-custodian account opening across Schwab, Fidelity, or Pershing, troubleshooting account opening failures or processing delays, or benchmarking cycle times and first-submission acceptance rates. For risk-based approval tiers and compliance screening requirements, see account-opening-compliance.
Process account maintenance requests across the account lifecycle. Use when changing a client address or contact info with identity verification, updating beneficiary designations after marriage, divorce, birth, or death, re-registering or re-titling an account to a trust or new entity, selecting tax lot methods or fixing cost basis records, applying legal or compliance holds or Reg T freezes, setting up systematic withdrawals or standing instructions, processing a death notification and estate account setup, handling a QDRO, power of attorney, or guardianship, closing accounts and managing escheatment, or designing data quality review programs.
Design and operate reconciliation processes across portfolio management, custodian, and clearing systems. Use when building a daily position, cash, or transaction reconciliation process, investigating discrepancies between internal records and custodian records, diagnosing recurring break patterns from corporate actions or pricing differences, setting tolerance thresholds for position, cash, or market value matching, implementing three-way reconciliation, designing break investigation workflows with aging and escalation, normalizing multi-custodian feeds from Schwab, Fidelity, or Pershing, reconciling cost basis or accrued income, or preparing for examinations on books and records accuracy.
Ensure investment advertising and marketing materials comply with SEC Marketing Rule and FINRA Rule 2210. Use when the user asks about performance advertising, showing backtested or hypothetical returns, net vs gross performance presentation, client testimonials or endorsements in marketing, social media posts by advisers or reps, third-party ratings in pitchbooks, or advertising recordkeeping. Also trigger when users mention 'can we show this track record', 'pitchbook compliance review', 'marketing rule violations', 'cherry-picking performance periods', 'predecessor performance portability', 'extracted performance', or ask whether a website, one-pager, or presentation needs compliance approval.
Process and manage corporate actions from announcement through settlement. Use when handling dividends, stock splits, reverse splits, mergers, or spin-offs, managing voluntary elections for tender offers, rights offerings, or exchange offers, calculating record date and ex-date entitlements under T+1 settlement, collecting and submitting elections to DTC or custodians, handling fractional shares and proration for reorganization events, adjusting cost basis and tax lots after events, reconciling expected entitlements against actual receipts, or investigating missed or incorrectly processed corporate actions.
Guide BSA/AML compliance program design, ongoing transaction monitoring, and FinCEN reporting for broker-dealers, banks, and investment advisers. Use when the user asks about suspicious activity reports, currency transaction reports, OFAC screening, structuring detection, ongoing risk-rating reviews and escalation, or FinCEN requirements. Also trigger when users mention 'large cash deposit', 'sanctions check', 'money laundering red flags', 'unusual transaction patterns', 'wire to a foreign country', 'SDN list', 'tipping off a client about a SAR', 'AML audit', 'correspondent account due diligence', or ask whether a transaction needs to be reported. (For onboarding identity verification, CIP/CDD, beneficial ownership, and initial customer risk rating, use know-your-customer.)
Claude Skills — questions
Answers built from the skills we actually parsed.