Browse reusable Agent Skills, each with a clear purpose and practical guidance.
⚡ Test analysis skill. Best for: 'what's tested', 'find test coverage', 'audit test quality', 'missing tests', 'edge cases'. Uses claudemem AST with callers analysis for efficient test discovery.
⚡ Comprehensive analysis skill. Best for: 'comprehensive audit', 'deep analysis', 'full codebase review', 'multi-perspective investigation', 'complex questions'. Combines all perspectives (architect+developer+tester+debugger). Uses Opus model with full claudemem AST analysis.
Inspect raw CryEngine file data (bones, nodes, materials, geometry, skinning) using the CgfConverterTestingConsole. Use when debugging conversion issues, verifying chunk data, or comparing source data against renderer output.
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating with Grok, Gemini, GPT-5, DeepSeek, MiniMax, Kimi, GLM, or Claudish proxy for code review, consensus analysis, or multi-expert validation. NEW in v3.2.0 - Direct API prefixes (mmax/, kimi/, glm/) for cost savings. Includes dynamic model discovery via `claudish --top-models` and `claudish --free`, session-based workspaces, and Pattern 7-8 for tracking model performance. Trigger keywords - "grok", "gemini", "gpt-5", "deepseek", "minimax", "kimi", "glm", "claudish", "multiple models", "parallel review", "external AI", "consensus", "multi-model", "model performance", "statistics", "free models".
Spawn, probe, and stop Mini Diarium's live Windows Tauri dev app with WebView2 CDP enabled, then hand control to agent-browser for real UI inspection. Use this whenever the user wants to manually test the real desktop UI, drive the dev app, verify a bug or preference in the actual window, inspect localStorage, take a real screenshot, or "actually try it in the app" instead of relying only on unit tests or WDIO. Triggers: manually test the UI, drive the dev app, verify in the real UI, agent dev mode, spawn the dev app, open the running app and check, inspect the live Tauri window.
Use when inspecting a PyTorch model or pipeline to identify tunable submodules, detect dynamic shapes, and determine the recommended tuning mode before optimization.
Use when a Vivado synthesis or implementation run fails, or when the user asks "why did the build fail / what's wrong with this vivado log". Surfaces only the actionable error/critical-warning lines from large Vivado outputs (vivado.log, synth_1/runme.log, impl_1/runme.log, *.rpt) so the diagnosis fits in context. Trigger when the user shares a Vivado log path, mentions "synthesis failed", "implementation failed", "timing failure", "BRAM exhausted", or pastes raw Vivado output.
Minimize an AD bug by systematically stripping a failing DynamicPPL model down to its root cause. Use when a model + AD backend gives wrong gradients or errors.
Perform code review. Quality analysis. Acceptance criteria verification. Best practices review.