Skills

Analyze system architecture, design patterns, module boundaries, and scalability. Provide high-level design recommendations and architectural decision records (ADR).

Blender CAD modeling automation skill with STEP/IGES import, Geometry Nodes, and USD export support.

Advanced build management agent that provides high-performance incremental compilation, hot reload capabilities, and intelligent build orchestration. Features MD5-based change detection, process management, and multi-platform deployment support with tqdm progress visualization.

Diagnose LINE and Telegram credential readiness versus live roundtrip readiness through Hypura Harness without exposing tokens or raw routing ids.

Comprehensive CI/CD integration agent that manages continuous integration and deployment pipelines with automated quality assurance, multi-platform support, and intelligent workflow orchestration. Seamlessly integrates with GitHub Actions, GitLab CI, Jenkins, CircleCI, and Azure DevOps for end-to-end DevOps automation.

Advanced code analysis agent that performs comprehensive code reviews focusing on security, performance, maintainability, and best practices. Generates actionable feedback with severity levels and automated fix suggestions.

Perform codex-mcp-researcher tasks

Perform deep dependency analysis, manifest auditing, and supply-chain risk assessment across language ecosystems.

Lightweight dependency insight agent for quick manifest scans, transitive surfacing, and license notes.

Use Hypura Harness companion3d tools to drive the local browser or Electron 3D companion with local VRM, GLB, GLTF, or FBX assets.

ドラフト文書の手直し（整合性チェック・数値更新・トーン修正）と、GPT/Gemini/Claude Opus/DeepResearch向け壁打ち文書の生成・フィードバック統合を行う。提案書レビュー、壁打きセッション準備、壁打ち結果の反映、提出前チェックリストに使用する。

Production-ready code implementation agent that writes clean, maintainable, and well-tested code based on specifications. Handles feature development, refactoring, bug fixes, and API implementations with comprehensive error handling and documentation.

Git4D Runtime Checker - Validate Git for DevOps workflows with CUDA/SSE detection and runtime environment verification.

Git4D Schema Auditor - Validate Git4D configurations, schema definitions, and DevOps pipeline integrity.

Official ASI "Hakua" Auditory & Physical Actuator Substrate

Bridge Neuro API actions into safe VRChat autonomy.

Obsidianのような知識管理、Wikilink構文([[link]])による文書間リンク、バックリンク、タグ(#tag)抽出を扱うためのスキル。

Migrate a user's OpenClaw customization footprint into Hermes Agent. Imports Hermes-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.

Refresh OpenCode Zen free models and failover chain.

Intelligent multi-agent workflow orchestrator that coordinates specialized Codex skills for complex task execution. Implements official OpenAI Agents SDK patterns including guardrails, handoffs, and worker agents with MCP-centric architecture for seamless integration.

Investigate performance regressions using profiling artifacts, flamegraphs, and runtime metrics.

Provide quick performance triage from logs, benchmarks, and runtime counters.

Create, manage, and execute structured multi-step plans with MILSPEC-grade traceability, audit logging, and fail-closed gates. Use when the user asks for a plan, roadmap, phased approach, or checklist, or when a task has 3+ steps, cross-cutting concerns, risk, or requires coordination. Also triggers on keywords like plan mode, execution plan, task decomposition, phased rollout, or implementation strategy.

Python専用コードレビュー・型ヒントãEDjango/FastAPIベストãEラクチE‚£ã‚¹

Comprehensive quality assurance engineering agent that designs test strategies, identifies edge cases, validates requirements coverage, and ensures software quality. Use when testing, QA planning, test case design, acceptance criteria validation, or quality assessment is needed.

Continuous Quality Assurance service agent that monitors development activities in real-time, automatically triggering quality analysis on code changes. Provides background processing for comprehensive QA validation across parallel development environments, ensuring consistent quality standards throughout the development lifecycle.

"Before merging to main, orchestrate full-stack QC: run unit/abnormal/comprehensive tests, apply statistical + quantum-inspired optimization heuristics, and log merge decisions."

Refactor code to improve maintainability, performance, and readability. Identify code smells, extract reusable components, optimize algorithms, and reduce technical debt.

Deep research with multi-source validation, citation, and comprehensive reporting

Launch SakanaAI's AI-Scientist for autonomous scientific research. Generates ideas, executes experiments, and writes papers based on a specified template and model.

Security audit with CVE scanning, dependency analysis, and vulnerability patching

Runs the rest of a /shell request as a literal shell command. Use only when the user explicitly invokes /shell and wants the following text executed directly in the terminal.

Convert an existing codebase in the current working directory into a ShinkaEvolve task directory by snapshotting the relevant code, adding evolve blocks, and generating `evaluate.py` plus Shinka runner/config files. Use when the user wants to optimize existing code with Shinka instead of creating a brand-new task from a natural-language description.

Load top-performing Shinka programs into agent context using `shinka.utils.load_programs_to_df`, and emit a compact Markdown bundle for iteration planning.

Run existing ShinkaEvolve tasks with the `shinka_run` CLI from a task directory (`evaluate.py` + `initial.<ext>`). Use when an agent needs to launch async evolution runs quickly with required `--results_dir`, generation count, and strict namespaced keyword overrides.

Create ShinkaEvolve task scaffolds from a target directory and task description, producing `evaluate.py` and `initial.<ext>` (multi-language). Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve.

Generate comprehensive test suites including unit, integration, and e2e tests

Guide for testing Codex TUI interactively

TypeScript-specialized code reviewer focusing on type safety, generics usage, strict mode compliance, React/Next.js patterns, and Node.js best practices. Use when reviewing TypeScript code, .ts/.tsx files, or TypeScript-specific quality concerns.

Unity C#専用コードレビュー・パフォーマンス最適化ãEUnityベストãEラクチE‚£ã‚¹