AI Ml AI Skills

Use when building XGBoost models on tabular data and returning feature importance ranking outputs. Supports binary classification and regression with automatic task detection, train-test split,…

Use when evaluating Carl Icahn-style activist investments: undervalued assets, poor governance, capital allocation fixes, buybacks, asset sales, board pressure, and control catalysts.

Configure asset import settings

Keep a live thesis honest: pillar status, evidence ledger, monitoring triggers, drift detection. Triggers on thesis tracker, thesis update, is the thesis still intact, post-earnings thesis check,…

Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands…

Für AGB im Leasingvertrag Fortwirkung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route:…

Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.

解析外部 URL 内容，并沉淀为可阅读的文本结果。

Audit a content library, docs site, or blog for AI-generated filler that's eroding trust and search performance — and triage what to fix, rewrite, or delete. Use when asked to find slop in a content…

Help users establish high-impact goals that bridge the gap between abstract company vision and daily execution while maintaining radical focus.

Create or review Terraform infrastructure and plans. Use for cloud resources, IAM, networking, state management, and infrastructure changes.

多角色对话配音：按 cast 和逐行对白为不同角色分配音色与情绪，合成多声线音轨和带角色名字幕。 当用户说“多角色/双人/剧本/对话配音、多人对白、不同角色不同声音、有声剧配音”时使用。 单一公共音色用 tts-voiceover；克隆本人音色用 voice-clone；整部短剧制作由 short-drama 编排。

Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality…

[Deprecated] Use when building frontend Web apps that talk to CloudBase Relational Database via @cloudbase/js-sdk – provides the canonical init pattern so you can then use Supabase-style queries from…

Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies…

Discover and load tools progressively as needed (reduces token overhead)

Build a balance sheet (bilan) from a Well workspace. Use when the user asks for a balance sheet, bilan, assets/liabilities/equity, or financial position at a point in time.

Executive communication style for all-hands emails. Balances transparency with appropriate messaging.

Automates Navigator plugin updates. Detects current version, updates plugin, verifies installation, updates project CLAUDE.md, and validates new features. Auto-invoke when user mentions upgrading…

Create and manage messaging profiles with number pools, sticky sender, and geomatch features. Configure short codes for high-volume messaging. This skill provides Java SDK examples.

Run code quality tools: PHP-CS-Fixer for style, PHPStan for static analysis, and type safety checks

Access Claude MPM functionality and manage multi-agent orchestration

Use whenever answering anything version-sensitive — library/framework/SDK APIs, package versions, model IDs, pricing, CLI flags, config, or "latest/newest" anything. Verify against current sources…

Spot patterns appearing in 3+ domains to find universal principles

Test an Angular app that embeds CometChat — what to mock vs exercise for real, TestBed setup for standalone kit components, avoiding real network in unit tests, and a two-account manual pass for…

Developer experience (DX) engineering, SDK design patterns, API ergonomics, CLI tooling design, documentation-driven development, and developer onboarding. Use when designing SDKs, improving API…

Builds ML, responsible-AI, and multimodal models. Use when doing data science or explaining fairness, privacy, speech, vision-language, or diffusion mechanics.

Use when creating cinematic sequences, narrative animations, or when applying animation principles to video storytelling and visual narrative.

Fetch unresolved review comments from a PR and evaluate with receive-feedback skill

Managing dependencies, CI/CD, advanced GitHub Actions workflows, containers, secrets, and operational config. Use for build, workflow, or environment work.

This skill should be used when the user asks to "set up ci for fluent", "github actions for servicenow", "deploy fluent from a pipeline", "fluent pull request checks", "automate now-sdk", or reports…

Guides the agent through upgrading a Capacitor plugin to a newer major version. Covers dependency alignment, native platform changes, example app verification, and multi-version jumps. Do not use for…

Create repository onboarding guides with architecture, key files, setup, debugging, and contribution workflows for a defined audience.

Patrones de pruebas en Rust incluyendo pruebas unitarias, de integración, async, basadas en propiedades, mocking y cobertura. Sigue la metodología TDD.

Execute a natural-language browser intent via page-agent (browser_act) when the target is easier to describe than to select — degrades gracefully when page-agent or an OpenAI-compatible LLM provider…

Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment.…

Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (check_syscall, lsmod, hidden_modules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify…

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures…

The house format and rules for writing or updating an agentmemory skill. Use when adding a new skill, restructuring an existing one, or reviewing a skill contribution for consistency.

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to…

Iterative improvement loop — refine a target across multiple Algorithm cycles toward ideal state. USE WHEN loop, iterate, refine, multiple passes, keep improving, revisit, rework.

Helm chart expert for Kubernetes package management, templating, and dependency management

Comprehensive SEO analysis for any website or business type. Full site audits, single-page analysis, technical SEO (crawlability, indexability, Core Web Vitals with INP), schema markup, content…

Use when working with WizTelemetry Tracing extension for KubeSphere, including installation, configuration, and tracing query API

Structure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a…

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8).…

Read, inspect, edit, or create PowerPoint `.pptx` presentations, including text extraction, template-preserving changes, slide review, and generation from a brief.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices". Focuses on…

Update an existing handoff document with current session progress. Applies section-specific merge rules: append-only for Work Done (never deletes history), replace for Status and Next Steps, merge for…

Add strategic color to features that are too monochromatic or lack visual interest, making interfaces more engaging and expressive. Use when the user mentions the design looking gray, dull, lacking…

Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user…