发现 Skills

Generate boundary value test cases for numeric ranges, string lengths, date ranges, collection sizes, and domain-specific constraints using systematic analysis techniques

Flutter app testing with widget tests, integration tests, golden tests, Mockito, bloc testing, and Flutter Driver for end-to-end scenarios.

Apply Edward de Bono's Six Thinking Hats methodology to software testing for comprehensive quality analysis. Use when designing test strategies, conducting test retrospectives, analyzing test failures, evaluating testing approaches, or facilitating testing discussions. Each hat provides a distinct testing perspective: facts (White), risks (Black), benefits (Yellow), creativity (Green), emotions (Red), and process (Blue).

Голосовые сообщения и видео-кружочки (TTS)

Data modeling with Entity-Relationship Diagrams (ERDs), data dictionaries, and conceptual/logical/physical models. Documents data structures, relationships, and attributes.

Use this skill when working with Unreal Engine animation: AnimInstance, montage playback, blend space, state machine, anim notify, IK, AnimGraph, skeletal mesh, or linked anim graphs. See references/anim-notify-reference.md for notify patterns and references/locomotion-setup.md for locomotion setup. For montage integration with GAS, see ue-gameplay-abilities.

Create runbooks, playbooks, SOPs and technical documentation. Use when the user wants to document a process, create a runbook, build operational docs, or formalize any repeatable technical procedure. Triggers on requests like 'create a runbook for...', 'document this process', 'write a playbook', 'SOP for...', or any technical documentation request.

Designs MLIR dialects and transformations. Use when: (1) building domain-specific compilers, (2) creating IR abstractions, (3) implementing multi-level lowering.

Autonomously improve a generated paper via Gemini review through the gemini-review MCP → implement fixes → recompile, for 2 rounds. Use when the user says "revise paper", "improve paper", "paper polishing loop", "auto improve", or wants to iteratively polish a generated paper.

Vast.ai API Documentation - Affordable GPU Cloud Marketplace

Create a conversation practice chat MulmoScript with a speech-bubble UI and character illustration (voiceover approach). Use when the user wants to create English conversation practice content.

Help users delegate effectively. Use when someone is struggling to let go of tasks, deciding what to delegate, building team autonomy, or balancing being hands-on vs hands-off.

Help users run effective one-on-one meetings. Use when someone is a new manager setting up 1:1s, struggling to make 1:1s productive, wants to improve career conversations with reports, or needs to handle difficult 1:1 situations.

Automate Docsumo tasks via Rube MCP (Composio). Always search tools first for current schemas.

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

Scaffolds persistent project context files through a guided interview. Use when onboarding a repository to Maestro context workflows.

Find verified AI-proficient talent using the JobArbiter CLI. Not resumes — proficiency scores backed by agent attestation and behavioral data.

Expert methodology for identifying, assessing, and mitigating technical and operational risks including security, incidents, compliance, and disaster recovery.

Debugs Kubernetes pod failures including CrashLoopBackOff, OOMKilled, ImagePullBackOff, init container failures, and CreateContainerConfigError. Use when pods crash, restart repeatedly, fail to start, or show container errors.

Debugs Kubernetes resource quota and limit issues including ResourceQuota exceeded, LimitRange violations, OOMKilled due to memory limits, and CPU throttling. Use when hitting quota limits, container resource constraint errors, or capacity issues.

USE FOR: Strategy creation, analysis, and evaluation — game-theoretic foundations, competitive analysis, decision frameworks, SWOT/PESTLE, wargaming, and their mathematical underpinnings. Use for strategic reasoning about complex multi-agent scenarios, organizational strategy, research strategy, and the mathematical planning aspects of the project's governance and optimization layers. DO NOT USE FOR: formalising strategic models in Lean (use @lean-applied-reasoning); intelligence analysis (use @applied-intelligence-analysis); game-theoretic optimization (use @math-optimization-game). TRIGGERS: strategy, SWOT, PESTLE, wargaming, decision framework, competitive analysis, game-theoretic strategy.

Create a structured session handoff document for continuity across sessions. Use when ending a work session, switching contexts, or before a break. Captures decisions, progress, code changes, and next steps so a future session can pick up where you left off without losing context.

Draft and send client onboarding questionnaires for Kaji AI Agent deployments. Generates personalized emails or documents asking clients about model preferences, use cases, integrations, communication, and security requirements. When responses come back, processes them into a must-have/nice-to-have deployment timeline and creates a ClickUp task to track the rollout.

Dev-Readiness: revisão de stories e clareza técnica para implementação.