Data analysis, machine learning, LLM apps, and prompt design (8.9K skills)
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
The English summary is being prepared. Showing the original description.
How to design contextual inputs for an always-on AI agent with episodic memory. Covers what data to feed the agent, how to structure observations and triggers, ambient context capture (screen, audio, calendar), context window budgeting, and retrieval strategies that keep the agent grounded in what's actually happening. Activate on: "what should the agent observe", "context inputs for agent", "ambient context capture", "agent triggers", "agent input design", "screenpipe integration", "context window budget", "what data to feed my agent", "/always-on-agent-inputs". NOT for: memory architecture and storage (use always-on-agent-architecture), application ideas (use always-on-agent-applications), safety concerns (use always-on-agent-safety).
The English summary is being prepared. Showing the original description.
Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.
The English summary is being prepared. Showing the original description.
Introduce people to AI, agentic AI, and AI skills with appropriate pedagogy for any audience. Covers LLM analogies, progressive complexity paths, aha-moment demos, audience-tailored explanations, workshop design, and overcoming emotional barriers to AI adoption. Activate on 'explain AI', 'introduce AI', 'AI workshop', 'AI demo', 'teach AI', 'AI literacy', 'onboard to AI', 'AI evangelism', 'explain agentic', 'explain skills to', 'AI training session', 'AI onboarding'. NOT for teaching ML engineering (use ai-engineer), not for building AI features (use ai-engineer), not for prompt engineering (use prompt-engineer), not for building training data pipelines.
The English summary is being prepared. Showing the original description.
Analyze development-set disagreements between human annotations and one Coval text LLM judge, then propose a focused prompt revision. Use coval-calibrate-metric for independent trust measurements.
The English summary is being prepared. Showing the original description.
Set up and connect a new Coval agent for evaluation. Guides through agent type selection, endpoint configuration, system prompt, and default resource attachment. Use when user says "set up an agent", "connect my agent", "create an agent", "add an agent", or "configure agent endpoint".
The English summary is being prepared. Showing the original description.
Comprehensive overview of ALL Coval platform resources, their hierarchy, relationships, API endpoints, and ID formats. Use when user asks about Coval resources, data model, how things relate, what endpoints exist, or needs context about the platform structure before making API calls.
The English summary is being prepared. Showing the original description.
Build or improve a Coval dashboard with metric visualizations backed by real data. Creates new dashboards from scratch or rebuilds existing ones by analyzing usage patterns, metric frequency, and data density. Use when user says "create a dashboard", "build a dashboard", "improve my dashboard", "add widgets", "visualize my metrics", "make a performance dashboard", or "dashboard for my runs".
The English summary is being prepared. Showing the original description.
The cross-repo scheduling system (sch_* tables, matrx-scheduler). Use when touching features/scheduling/**, /schedules or /administration/scheduling, migrations/sch_*.sql, a scheduled agent, cron, trigger, lease, or claim, or debugging ghost tasks, missed fires, double-runs, or stuck claims.
The English summary is being prepared. Showing the original description.
SSR-first Next.js App Router doctrine with zero layout shift. Use when creating a page or data-fetching UI, fixing CLS, layout shift, or hydration mismatches, placing 'use client', Suspense, or skeleton boundaries, awaiting params/searchParams/cookies, adding server-only guards or cache() dedup, or choosing Route Handlers vs Server Actions.
The English summary is being prepared. Showing the original description.
Context and scope-tagging UI. Use when adding a context picker to a surface, tagging an entity to scopes, setting or filtering by the active (working) context, showing per-entity context status, prompting for context on upload, or editing context-assignment/**, active-context/**, or appContextSlice.
The English summary is being prepared. Showing the original description.
Recipe for an agent building a small custom web app (an Applet) for one person or business on THEIR OWN store tables, live at aimatrx.com/applets/<slug>. Use when asked to build an app, portal, calendar, tracker, dashboard screen or client view on someone's tables/data in AI Matrx. NOT for platform features (use build-sub-feature) or tables the platform keeps for itself (defineTypedTable).
The English summary is being prepared. Showing the original description.
The staged pipeline that turns any API, provider payload, scrape, or computed result into registered, rendered platform kinds. Use on 'create kinds for X', 'distill X into kinds', 'point yourself at API X', or as a stage (A/B/V/D/C) of a running data-to-kinds run. NOT for consuming existing kinds (use aidream's workflow-io-kinds / matrx-frontend's shape-system).
The English summary is being prepared. Showing the original description.
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
The English summary is being prepared. Showing the original description.
Use when designing or improving prompts, commands, hooks, skills, or sub-agent instructions, including output quality, reliability, and token efficiency.
The English summary is being prepared. Showing the original description.
Access Plausible Analytics for website traffic stats. Use when checking visitor counts, pageviews, top sources, and traffic trends across sites.
The English summary is being prepared. Showing the original description.
Access Google Search Console for SEO data such as queries, clicks, impressions, rankings, and indexing status across sites. Use when diagnosing search performance or indexing issues.
The English summary is being prepared. Showing the original description.
Generate blog articles for Qiita and Zenn from GitHub release information. Use when creating release notes or technical articles that follow specific markdown formats with frontmatter. Supports generating articles from release data, creating custom formatted articles, and saving articles to specified repositories for both Qiita and Zenn platforms
The English summary is being prepared. Showing the original description.
docs/PLAN 配下の計画書ファイル（tasks.json v2）のフォーマット不整合を検出・修正し、 ダッシュボードでの表示問題を解決するスキル。 スクリプトによる自動チェック（構造・整合性・パースシミュレーション）を第一手段とし、 解決しない場合は LLM エージェントが原因を調査する。 Trigger: 計画書が壊れた, プランの修正, 計画書のフォーマット直す, /dev:fix-plan, plan fix, plan broken, ダッシュボードに表示されない
The English summary is being prepared. Showing the original description.
スキルを作成・更新・プロンプト改善するためのメタスキル。 **collaborative**モードでユーザーと対話しながら共創し、 抽象的なアイデアから具体的な実装まで柔軟に対応する。 **orchestrate**モードでタスクの実行エンジン（Claude Code / Codex / 連携）を選択。 Anchors: • Continuous Delivery (Jez Humble) / 適用: 自動化パイプライン / 目的: 決定論的実行 • The Lean Startup (Eric Ries) / 適用: Build-Measure-Learn / 目的: 反復改善 • Domain-Driven Design (Eric Evans) / 適用: ユビキタス言語 / 目的: 一貫した語彙 • Design Thinking (IDEO) / 適用: ユーザー中心設計 / 目的: 共感と共創 • Microservices Patterns (Richardson) / 適用: サービス委譲 / 目的: 疎結合な連携 Trigger: 新規スキルの作成、既存スキルの更新、プロンプト改善を行う場合に使用。 スキル作成, スキル更新, プロンプト改善, skill creation, skill update, improve prompt, Codexに任せて, assign codex, Codexで実行, GPTに依頼, 実行モード選択, どのAIを使う
The English summary is being prepared. Showing the original description.
Apple FoundationModelsフレームワークによるオンデバイスLLM — テキスト生成、@Generableによるガイド生成、ツール呼び出し、iOS 26+でのスナップショットストリーミング。
The English summary is being prepared. Showing the original description.
構造化テキストの解析において正規表現とLLMのどちらを選択するかの判断フレームワーク — まず正規表現で始め、低信頼度のエッジケースにのみLLMを追加する。
The English summary is being prepared. Showing the original description.
生のプロンプトを分析し、意図とギャップを特定し、ECCコンポーネント （スキル/コマンド/エージェント/フック）にマッチングし、すぐに貼り付けて 使える最適化済みプロンプトを出力します。アドバイザリー専用 — タスク自体は 実行しません。 トリガー条件: ユーザーが「optimize prompt」「improve my prompt」 「how to write a prompt for」「help me prompt」「rewrite this prompt」 と言った場合、またはプロンプト品質の向上を明示的に依頼した場合。中国語の 同等表現でもトリガーされます: 「优化prompt」「改进prompt」「怎么写prompt」 「帮我优化这个指令」。 トリガーしない条件: ユーザーがタスクの直接実行を求めている場合、または 「just do it」/「直接做」と言った場合。「优化代码」「优化性能」 「optimize performance」「optimize this code」と言った場合もトリガーしません — これらはリファクタリング/パフォーマンスタスクであり、プロンプト最適化 ではありません。
The English summary is being prepared. Showing the original description.
あらゆる公開ソース向けの完全自動化AI駆動データ収集エージェントを構築 — 求人、価格、ニュース、GitHub、スポーツなどあらゆるデータに対応。スケジュールでスクレイピングし、無料LLM（Gemini Flash）でデータを強化し、Notion / Sheets / Supabaseに結果を保存し、ユーザーフィードバックから学習。GitHub Actionsで100%無料で稼働。ユーザーが自動的にデータを監視、収集、追跡したい場合に使用。
The English summary is being prepared. Showing the original description.