Maintain living architecture maps and interaction flows.

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.

**Purpose:** Manage persistent memory files (STATUS.md, ROADMAP.md, DECISIONS.md, JOURNAL.md) for AI-assisted development across sessions.

Step-by-step guide for testing the launchd service skill on existing nahuatl projects.

This skill enforces a consistent, mobile-first UI.

Fix a specific failing test case in this repo by identifying the root cause, adding a minimal repro under tests/, explaining the cause, applying a targeted fix, re-running the test, and reporting any new failures uncovered.

Three.js post-processing - EffectComposer, bloom, DOF, screen effects. Use when adding visual effects, color grading, blur, glow, or creating custom screen-space shaders.

Look up Microsoft Purview documentation and guidance from Microsoft Learn. Use this skill ONLY when the user's question does NOT match a diagnostic symptom in dlm-diagnostics. Use dlm-diagnostics first for troubleshooting issues like retention policy errors, archive problems, inactive mailboxes, etc. Use asklearn for general questions like: how do I create a retention policy, how do I set up eDiscovery, how do I enable audit logging, how do I configure communication compliance, how do I set up information barriers, how do I use insider risk management, how do I manage records, or how do I configure adaptive scopes.

Build type-safe global state in React with Zustand. Supports TypeScript, persist middleware, devtools, slices pattern, and Next.js SSR with hydration handling. Prevents 6 documented errors. Use when setting up React state, migrating from Redux/Context, or troubleshooting hydration errors, TypeScript inference, infinite render loops, or persist race conditions.

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, need real-world precedents, confidence <75%, or require reasoning from specialized AI models.

直近の内容を markdown 形式で保存

Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.

Handle vulnerability reports with coordinated disclosure, timely patches, and clear communication.

Generate weekly KPI report (3PL/WMS) from shipments/events

Integrate Excel (.xlsx) data into Playwright codegen scripts by replacing hardcoded values with config-driven lookups, loading data with polars, and validating every step with Playwright CLI plus the Playwright CLI skill. Use for Playwright automation updates that require Excel-backed data, config.yaml centralization, or CLI-based validation/reporting.

Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.

Clean Architecture guidance for Triatu: layering, dependencies, and where code belongs. Use when adding new modules, moving code across layers, or updating architecture decisions and docs.