Use when you need to empirically test whether hypothesized symmetries actually hold in your data or model. Invoke when user mentions testing invariance, validating equivariance, checking if symmetry assumptions are correct, debugging symmetry-related model failures, or needs data-driven validation before committing to equivariant architecture. Provides test protocols and metrics.
Verify a CVlization training pipeline example is properly structured, can build, trains successfully, and logs appropriate metrics. Use when validating example implementations or debugging training issues.
Analyze ML model architecture from papers and code. Use when understanding model structure for implementation.
End-to-end ML system design for production. Use when designing ML pipelines, feature stores, model training infrastructure, or serving systems. Covers the complete lifecycle from data ingestion to model deployment and monitoring.
Identify and document model hyperparameters from papers. Use when setting up training configurations.
Verify a CVlization inference example is properly structured, builds successfully, and runs inference correctly. Use when validating inference example implementations or debugging inference issues.
Use when you have implemented an equivariant model and need to verify it correctly respects the intended symmetries. Invoke when user mentions testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if model is actually equivariant, or diagnosing why equivariant model isn't working. Provides verification tests and debugging guidance.
Execute model training with optimization algorithms. Use when running training loops on datasets.
Create comprehensive business context profiles through guided interview. Use when the user wants to build or update their business profile, needs help defining their offerings, positioning, or brand identity.
Create detailed Ideal Client Profile through guided interview. Use when the user needs to define their target audience, understand their customers' problems and language, or build an ICP for content targeting.
Find and evaluate Claude skills for specific use cases using semantic search, Anthropic best practices assessment, and fitness scoring. Use when the user asks to find skills for a particular task (e.g., "find me a skill for pitch decks"), not for generic "show all skills" requests.
View and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples, view transcripts, or analyze agent behavior from a completed evaluation run.
Engineers effective prompts using systematic methodology. Use when designing prompts for Claude, optimizing existing prompts, or balancing simplicity, cost, and effectiveness. Applies progressive disclosure and empirical validation to prompt development.
Write content in Dhruv Baldawa's authentic voice and style. Use when creating blog posts, LinkedIn posts, emails, documentation, technical writing, opinion pieces, or any written content that should sound like Dhruv. Triggers on requests like "write this as me", "draft in my voice", "write a blog post", "create a LinkedIn post", "help me write", or any content creation where the user wants their personal voice applied.
Analyze writing samples to create a comprehensive voice DNA profile. Use when the user wants to capture their unique writing voice, needs to create a voice profile for AI content, or is setting up a new writing system.
This skill should be used when the user asks to "generate article images", "create images for an article", "run image generation", "generate illustrations from prompts", or mentions article hero images, prompt markdown files, or batch image generation.
Edit articles to read more naturally by removing LLM-generated prose patterns. Use this skill when asked to "humanize an article", "make writing sound more natural", "remove AI patterns", "edit for natural voice", or when working with drafts in articles/drafts/ that need polish.
Validate that a connector's CDC/incremental sync implementation correctly tracks offsets and filters records.
Implement a Python connector that conforms to the LakeflowConnect interface for data ingestion.
Comprehensive security risk analysis for Claude skills. Use when asked to analyze security risks, review security stance, audit skills for vulnerabilities, check security before deployment, or evaluate safety of skill files. Triggers include "analyze security," "security risks," "security audit," "security review," "is this skill safe," or "check for vulnerabilities."
Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clarity-Gated Documents) and validates SOT (Source of Truth) files.
Inline workflow executor for proxy providers (ZenMux, custom API providers). Executes workflow steps directly in the main context WITHOUT spawning Task subagents. Use this skill when: - Running looplia workflows via ZenMux or other proxy providers - Task subagents fail with "invalid_model" errors - You need inline execution without context isolation Architecture: Each workflow step is executed INLINE (no Task tool) - read skill, execute mission, write output, then proceed to next step. All steps share the main context. v0.6.6: Created for cross-provider compatibility with ZenMux.
