Top Agent Skills

Prüft Reseller-AGB auf rechtliche Risiken, strukturiert nach Normen, Beweislast und Gegenargumenten, und liefert eine Schnittstellenkarte mit Kollisions-, Zuständigkeits- und Nachweisfragen.

Generates and analyzes proteins using ESM3 and ESM C language models, covering sequence generation, structure prediction, inverse folding, embeddings, and function conditioning with local or cloud-based Forge API inference.

Provides scikit-learn compatible algorithms for time series machine learning, including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.

编辑文本以去除 AI 生成痕迹，使其更自然、更有人味。基于维基百科的 AI 写作特征指南，识别并修复夸大象征、宣传语言、模糊归因等模式。

为Y2K时尚品牌撰写具有戏剧性风格的文案，强调不墨守成规、独立自主的态度以及态度是审美基石的品牌理念。

Organizes files and folders by analyzing structure, finding duplicates, and proposing logical groupings, with user approval before any changes.

Systematically explore a web application to find bugs and UX issues, producing a structured report with screenshots, repro videos, and detailed steps for each finding.

Adopts an interactive question-asking persona that guides users through self-reflection by generating follow-up questions based on their answers, without offering advice or apologies.

Parses betting odds HTML tables with Java and Jsoup, extracting company names, odds values, and change timestamps using specific CSS selectors.

Defines, exposes, and debugs WordPress abilities through the Abilities API, with guidance on installation and documentation.

Provides an MCP server for managing infrastructure with Pulumi, enabling infrastructure-as-code operations through AI agents.

Solve Advent of Code puzzles and algorithm challenges with a TDD workflow, algorithm selection guidance, and input parsing patterns.

Audits and fixes technical SEO, on-page metadata, structured data, Core Web Vitals, llms.txt, and AI-search optimization for ChatGPT, Perplexity, and AI Overviews, including E-E-A-T signals and programmatic SEO.

Finds and safely removes dead code across a codebase: unreachable paths, unused exports, functions, variables, CSS selectors, dependencies, env vars, and commented-out blocks. Builds an import graph, verifies no dynamic references, and runs build and tests after cleanup.

Audits deployment readiness across CI/CD, containers, monitoring, IaC, secrets, CDN, and DNS, scoring each area and identifying critical gaps, with optional auto-fix via chained sub-skills.

Assesses a project against all five SOC 2 Trust Service Criteria, producing a control-by-control PASS/PARTIAL/FAIL matrix with evidence references, remediation roadmap, and evidence collection checklist for audit readiness.

Generates or updates CHANGELOG.md from git history, parsing conventional commits, grouping by version tags, and formatting into keep-a-changelog sections with comparison links.

Gates a git branch before merge by running code review, security, test, and accessibility passes on the diff, then emits a single verdict.

Validate SKILL.md files against a quality rubric, scoring schema and instruction structure out of 100 and reporting a pass/fail verdict with specific fixes.

Interrogates a plan against real third-party documentation, extracting hard constraints and asking doc-cited questions before producing a constraints appendix.

Analyzes dependencies between stories, code modules, tickets, or specs to compute an optimal implementation order with parallel batches, cycle detection, and critical path analysis.

Scans a project for stack signals and pain points, searches the skills-hub registry and local skills, scores candidates, and presents a ranked shortlist with install commands.

Generates a complete mobile test suite for Flutter, React Native, iOS, or Android apps, covering unit, widget, integration, snapshot, accessibility, and platform-specific tests, then runs them with a self-healing loop.

Builds and reviews Apex code that constructs SOQL/SOSL at runtime, inspects schema metadata, and accesses fields dynamically, with guidance on injection prevention and FLS enforcement.

Routes Salesforce, Force.com, and Lightning Platform questions to the correct skill package from a library of over 1,000 domain-specific skills, covering Apex, SOQL, Flow, LWC, and more.

Design, create, and manage Salesforce sharing rules to grant record access beyond the role hierarchy, covering owner-based, criteria-based, and guest user rules.

Configure the Data Table screen component in Salesforce Screen Flows for row selection, including single/multi-select, column setup, and downstream consumption of selected rows.

Writes, audits, and troubleshoots Salesforce validation rules, covering formula best practices, bypass patterns, and integration pitfalls.

Routes Salesforce Flow Builder requests to the correct skill package among 63 available, covering record-triggered, screen, scheduled, and orchestration flows, bulkification, fault handling, limits, and testing.

Runs a deeper code review with the GLM-5 model via glm-review, validates findings against the actual code, and reports only confirmed issues.

Retrieves account balances from a self-hosted Sure personal finance board using its REST API.

Explains Solana's architecture and protocol internals, covering the SVM execution engine, account model, consensus, transactions, validator economics, data layer, development tooling, and token extensions using Helius blog posts, SIMDs, and Agave/Firedancer source code.

Complete guide for using pass, the standard Unix password manager, covering installation, GPG setup, store initialization, daily usage, git sync, extensions, and troubleshooting.

Manage Box files, folders, collaborations, and shared links through the Maton gateway with managed OAuth authentication.

Builds and modifies Knods visual AI workflows by parsing polling payloads, generating assistant text, and streaming responses with optional canvas action blocks.

Fetches your latest WHOOP recovery, sleep, and strain data and generates a short set of daily suggestions.

Manage Xero accounting data through the Maton gateway: contacts, invoices, payments, accounts, bank transactions, and financial reports with managed OAuth.

Indexes document metadata in SQLite and manages ephemeral key-value state in Redis for cross-session context.

Optimizes personal and business banking by assessing scenarios, structuring accounts, eliminating fees, and maximizing interest rates.

Turns Lark collaboration noise into prioritized action by triaging chat, approvals, meetings, docs, spreadsheets, calendars, and email with a default read-only counselor mode.

Reads, extracts, merges, splits, rotates, watermarks, creates, encrypts, and OCRs PDF files using Python libraries and command-line tools.

Generates and analyzes protein sequences and structures using ESM3, ESMC, and ESMFold2, with support for local and cloud inference.

Process and analyze tabular datasets larger than RAM using lazy, out-of-core DataFrames, with fast aggregations, visualization, and machine learning integration.

Runs a broad SEO audit covering technical SEO, on-page SEO, schema, sitemaps, content quality, AI search readiness, and GEO, with a weighted health score and prioritized action plan.

Guides the creation, modification, and evaluation of agent skills, including running benchmarks and optimizing descriptions for better triggering.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1, extracting events as NumPy arrays, metadata, and channel information, with support for creating and modifying FCS files.

High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.

Submit protein sequences to the Adaptyv Bio Foundry for experimental characterization (binding, thermostability, expression, fluorescence) and retrieve results using the REST API or Python SDK.

Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants, returning variants, carriers, and relatedness with allele frequencies and annotations.

Creates generative art with p5.js, starting from an algorithmic philosophy and expressing it through seeded randomness, noise fields, and particle systems.

Handles all networked operations through a real browser via CDP, including search, page scraping, login-required actions, and social media content extraction.

Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.

Defines the design tokens, component catalog, and layout patterns for the OpenFoodJournal SwiftUI app, ensuring new views stay visually consistent.

Reviews a video rough cut by generating deterministic metrics, critiquing the edit against brief and blueprint, and producing review_report.yaml and review_patch.json artifacts.

Automates browser testing and interaction with Playwright, including form filling, screenshots, responsive checks, and login flows, with automatic dev server detection.

Define el enfoque, las herramientas y el pipeline de análisis antes de escribir código, eligiendo entre SQL, Python o un enfoque híbrido según la pregunta y los datos.

Guía a un usuario nuevo a través de un ciclo SDD completo, aplicando un cambio real en su proyecto para aprender haciendo.

Lee y escribe datos en múltiples formatos con Pandas — CSV, Excel, Parquet, JSON, Feather — y elige el formato óptimo según el caso.

Guides agents to delegate tasks to specialized sub-agents using a decision tree and automatic triggers, with recursive spawning and integration with an agent-router MCP.

Search SAM.gov for contract opportunities and registered entities, and query USASpending.gov for federal award data.