AI Ml AI Skills

Turn product requirements into scoped tasks with dependencies and acceptance criteria. Use for implementation planning and prioritization.

Review generated or changed test code against universal testing rules before it ships. Best used reactively after an agent writes, edits, generates, or refactors tests, before presenting, committing,…

CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, AI…

Generate project documentation from codebase analysis — ARCHITECTURE.md, API_ENDPOINTS.md, DATABASE_SCHEMA.md. Reads source code, schema files, routes, and config to produce accurate, structured docs.…

Select and load connected skills through the Skill tool using progressive disclosure. Use before applying a connected skill's procedures or consulting its declared references and scripts.

Expert patterns for 2D/3D camera control including smooth following (lerp, position_smoothing), camera shake (trauma system), screen shake with frequency parameters, deadzone/drag for platformers,…

Guides "ship or iterate?" decisions using Shreyas Doshi's frameworks, Marty Cagan's shipping philosophy, and Tobi Lutke's reversible decision-making. Use when deciding if feature is ready, preventing…

Audit a website or UI and de-AI it — find the patterns that make it look template-generated (in both design and copy) and return specific, prioritized fixes that push it toward editorial, premium,…

Validate and release Navigator plugin to marketplace. Auto-invoke when user says "release plugin", "publish navigator", "create release", or "deploy new version".

Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides Go SDK examples.

Handle Doctrine transactions (ORM 3 wrapInTransaction), optimistic/pessimistic locking, flush strategies, and transaction boundaries

Meta Quest Passthrough Camera Access (PCA) for Unity — access the forward-facing RGB cameras on Quest 3 / Quest 3S to feed Computer Vision and Machine Learning pipelines. Use when capturing the…

Load context from paused session

Generate changelog from commits, bump version, create GitHub release, publish to npm. Use when user wants to release, publish, or ship a new version.

Scaffolds a Next.js turborepo with Blode UI, icons, Ultracite (oxlint/shadcn), workspace hooks, and GitHub/Vercel setup. Use when asked to "create a Next.js project", "bootstrap a turborepo", or…

Choose, compose and customize CometChat Angular UI Kit components — the closed component list, real @Input/@Output names, view-slot overrides via ng-template, and the surfaces that have NO kit…

Prompt patterns for consistent UI generation. Covers precise design intent communication, component specification formats, and iterative refinement patterns for LLM-driven UI development.

Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git…

Creates production-ready UI immediately from any description. Generates complete pages, components, and realistic mock data in FIRST response. Uses Next.js 16 + Tailwind + shadcn/ui. Never asks…

Designs tool runtimes for coding agents. Use when modeling tool registries, deferred loading, permission-aware execution, tool search, or remote tool rendering.

Use when animation needs musical flow—dance sequences, action choreography, comedic timing, scene pacing, or any motion that should feel rhythmic and well-composed over time.

Designing A/B tests: hypothesis docs, sample size, feature flags, significance analysis, CUPED, SRM detection, switchback experiments. Use when hypothesis validation is needed.

Configure ServiceNow Discovery — schedules, IP ranges, credential affinities, MID Server assignment, custom probes/sensors, identification rules, and run-status monitoring on discovery_* tables.

Guide to handling keyboard in Capacitor apps including visibility detection, accessory bar, scroll behavior, and input focus. Use this skill when users have keyboard-related issues.

用户画像生成、角色注册、生命周期和跨智能体同步。

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence…

Next.js 16+ y Turbopack — bundling incremental, caché en sistema de archivos, velocidad de desarrollo y cuándo usar Turbopack frente a webpack.

Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis,…

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".

Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or…

Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure…

Parse and analyze email headers (Received chain, Return-Path, Message-ID) to trace the true origin of a phishing email and validate SPF, DKIM, and DMARC results to confirm or rule out sender spoofing.…

List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants…

Renders the current session's output (analysis, research, red team, report, plan) as an extremely well-designed, self-contained HTML artifact via a deterministic renderer — the model distills content…

Docker expert for containers, Compose, Dockerfiles, and debugging

This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats, naming conventions,…

Local SEO analysis covering Google Business Profile optimization, NAP consistency, citation health, review signals, local schema markup, location page quality, multi-location SEO, and…

KubeSphere OpenPitrix application management Skill. Use when users ask about KubeSphere App Store, OpenPitrix, Helm/YAML application templates, application repositories, app versions, app releases,…

AI Berkshire skill: 微信公众号文章：作者-编辑-读者三Agent协作. Source: skills/wechat-article.md.

Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图",…

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for…

Deterministic citation-count and provenance gate for meta-paper-write. Checks the citation_map summary against the numeric paper citation target without trusting an LLM verdict.

Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.

无线/硬件:WiFi PMKID/WPS/Evil Twin,BLE,Zigbee,NFC,SDR,UART/JTAG/SPI,侧信道,故障注入。Use when attacking WiFi, BLE, RFID, SDR, or hardware interfaces.

Creates comprehensive Technical Design Documents (TDD) with mandatory and optional sections through interactive discovery. Use when user asks to "write a design doc", "create a TDD", "technical spec",…

Generate comprehensive tests for specified code

协同编排知识域。多Agent协同、任务分解、并行执行、冲突解决。当魔尊需要多Agent协作、任务编排、并行处理时使用。

Select and customize OpenMed's seven bundled privacy policy profiles for de-identification, and build custom surrogate generators. Use when the user asks which policy fits HIPAA Safe Harbor vs Expert…

Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find…

Author HTML compositions that the `render_video` tool turns into deterministic MP4 video — animated charts and dashboards, data explainers, text/quote cards, kinetic typography, product teasers, and…

Synthesize GitHub delivery context into a concise Basic Memory project update. Use in CI after `bm ci collect` prepares a ProjectUpdateContext; return only structured AgentSynthesis JSON for `bm ci…