Кассационная жалоба по single-document ветке Ф5d. Sonnet-main оркестрирует, Opus-subagent анализирует существенные нарушения по контракту 3.1a, Sonnet-subagent оформляет .docx…
Persona casting agent for rapid generation, persistence, lifecycle management, and inter-agent sync. Generates personas from diverse inputs, manages via a registry, evolves…
Diagnose and fix CAST AI agent, API, and autoscaler errors. Use when the CAST AI agent is offline, nodes are not scaling, or API calls return errors.
Configure CAST AI autoscaler policies and node templates for cost optimization. Use when enabling Phase 2 automation, setting spot instance policies, or configuring node…
Configure CAST AI Workload Autoscaler for pod-level right-sizing and VPA. Use when enabling workload autoscaling, configuring resource recommendations, or tuning pod CPU and…
Query CAST AI cluster savings report and node inventory. Use when verifying CAST AI connectivity, viewing cluster cost savings, or listing managed nodes after onboarding.
Optimize CAST AI autoscaler performance, node provisioning speed, and API efficiency. Use when nodes take too long to provision, autoscaler is not reacting fast enough, or…
Production readiness checklist for CAST AI cluster onboarding. Use when going live with CAST AI autoscaling, validating Phase 2 setup, or preparing for production cost…
Configure CAST AI webhook notifications for cluster events and audit logs. Use when setting up alerts for node scaling, cost threshold events, or integrating CAST AI events with…
Connect to A2A protocol agents from Castella. Communicate with agents, display agent cards, send messages, handle responses, and stream results.
Render A2UI JSON as native Castella widgets. Parse A2UI messages, handle actions, progressive rendering, data binding, and connect to A2UI-enabled agents.
Build chat interfaces and agent management UIs with Castella. Create chat components, display tool calls, manage multiple agents, and build agent hubs.
Build desktop, web, or terminal UIs with Castella. Create widgets, components, layouts, manage reactive state, handle events, and use the theme system.
Enable AI agents to introspect and control Castella UIs via MCP. Create MCP servers, expose UI resources, handle MCP tools, and use semantic IDs.
Use when adding the HTTP layer for a resource that already has (or will get) a service layer — chains casting-a-service-layer first if the service is missing
Automate Castingwords tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
The castle guard of Thornfield Castle — a helpful guide who knows the Guard's Motto. Use when someone wants to talk to the castle guard or asks about Thornfield Castle.
Castmagic integration. Manage data, records, and automate workflows. Use when the user wants to interact with Castmagic data.
Calendario de catalizadores en cobertura — resultados, guidance, capital markets days, dividendos, regulatorios.
Browse the AIWG model catalog — list available AI models, fetch model details, and search by capability or name
Validate product data integration between Adobe Commerce and an AEM Edge Delivery Services storefront.
Periodically reconciles catalog-audit migration recs: queries prod DB to verify each migration's effects landed, then flips shipped:false→true on the rec.
Create or update AgnosticV catalog files (common.yaml, dev.yaml, description.adoc, info-message-template.adoc)
Catalog and classify materials using standard library systems. Covers descriptive cataloging, subject headings, call number assignment using Dewey Decimal and Library of Congress…
docs_internal/references/SampleCodes_GWpy/ の13,711件レガシーコードカタログを 検索・参照し、gwexpy の新機能開発・サンプルノートブック作成・ギャップ分析に活用する。 API_MAPPING.md v2（5カテゴリ）との連携で GWpy / scipy / numpy / pandas 等あらゆる…
검증 통과한 디자인 팩을 GitHub 공개 레포로 구조화하고, 팩을 탐색·필터·복사할 수 있는 Next.js 카탈로그 웹사이트로 빌드해 Vercel에 배포하는 방법론 스킬. catalog-publisher 에이전트가 사용한다.
Maintain calendar of upcoming catalysts for portfolio positions and watchlist. Earnings dates, ex-div dates, regulatory events, macro releases.
Help with Catalyzed API - datasets, tables, pipelines, queries, vector search. Use when building Catalyzed integrations.
Use CodSpeed when an agent needs benchmark runs compared in CI and surfaced on pull requests before performance regressions merge.
Run a fast typo pass across source files and documentation so common misspellings are fixed before they spread through reviews and releases.
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.
Start or refresh domain onboarding for the current project. Generates persona, lexicon, signaling, anti-patterns, first-week plan, and a project-specific playbook for a chosen…
Snapshot agent behavior, compare outputs and tool-call paths, and block releases when a model or prompt change quietly shifts behavior.
VS Code の未要約リリースを GitHub から検出し、まとめて日本語で要約して Obsidian Vault に保存する。各バージョンの要約は「注目ポイントを冒頭で深掘り → カテゴリ別の表で全変更を一覧」の構成。「最新まで追いついて」「VS Code のアップデート確認して」と頼まれた時に使う。
Monitor Catchtable for open reservation slots and attempt booking using a logged-in Chrome session.
Summarize recent changes from git history for context recovery, handoffs, and sprint review
Progressive code reading tool — prefer this over the Read tool when reading source code files. Instead of loading the entire file, first get a structural overview (classes,…
Structured clarifying interview to align on intent before non-trivial work. Load when handling /catechism, or whenever a request is vague, multi-interpretable, has unclear scope,…
API de Categorias da Tray. Utilize quando o desenvolvedor precisar gerenciar a árvore de categorias da loja, incluindo consulta hierárquica, criação de subcategorias, reordenação…
Эксперт categorical encoding. Используй для ML feature engineering, one-hot, target encoding и embeddings.
Assign recorded transactions to the correct accounts using double-entry principles
Analyze and categorize Bluesky accounts by topic using keyword extraction. Use when users mention Bluesky account analysis, following/follower lists, topic discovery, account…
Branch skill for building and improving categories. Use when creating new categories, validating category structure, improving existing categories, or migrating categories to new…
Expert-level category theory knowledge for rigorous mathematical reasoning. Use when working with categorical structures, functors, natural transformations, adjunctions, limits,…
CATS integration. Manage data, records, and automate workflows. Use when the user wants to interact with CATS data.
Automate Cats tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
CatSharp Scale Galois Connections between agent-o-rama and Plurigrid ACT via Mazzola's categorical music theory
Sonify GF(3) color streams via CatSharp scale. Maps Gay.jl colors to pitch classes and plays through sox. Includes metairony mode and Hydra flow grokking.
Interact with Cat Town — a Farcaster-native game world on Base. Covers KIBBLE staking (stake, claim, unlock, unstake, leaderboard, deposit history); live world state (season,…
Analyze cause-and-effect relationships in the Semantica knowledge graph — causal chains, interventions, counterfactuals, and causal influence scores.
Determine cause-and-effect relationships using propensity scoring, instrumental variables, and causal graphs for policy evaluation and treatment effects
Expert causal reasoning and mental model construction for diagnosis and prediction in complex domains
Causal inference specialist for causal discovery, counterfactual reasoning, and effect estimationUse when "causal inference, causal discovery, counterfactual, intervention effect,…
Causal reasoning in historical analysis. Covers distinguishing immediate from underlying causes, tracing chains of causation across time scales, identifying unintended…
Systematic Fishbone analysis exploring problem causes across six categories
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or…
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode.
Terse output mode for Claude Code agents. Injects the Caveman system prompt to force compact phase reports, emoji-only status, single-line summaries, and a minimal final table.
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix.