LLM & Agents

Code review practices with technical rigor and verification gates. Practices: receiving feedback, requesting reviews, verification gates. Capabilities: technical evaluation, evidence-based claims, PR review, subagent-driven review, completion verification. Actions: review, evaluate, verify, validate code changes. Keywords: code review, PR review, pull request, technical feedback, review feedback, completion claim, verification, evidence-based, code quality, review request, technical rigor, subagent review, code-reviewer, review gate, merge criteria. Use when: receiving code review feedback, completing major features, making completion claims, requesting systematic reviews, validating before merge, preventing false completion claims.

This skill should be used when the user asks about "writing specs", "specs.md format", "how to write specifications", "sprint requirements", "testing configuration", "scope definition", or needs guidance on creating effective sprint specifications for agentic development.

Technical exploration within existing projects. USE WHEN user says "think through", "explore options", "investigate", "how should we approach", or needs to evaluate approaches before implementation. Creates exploration documents in project's explorations/ folder. Not for new project ideas—use ideation skill for that.

Validate all checkpoints from an agent run directory in parallel. Spawns test-validator agents for each checkpoint and summarizes results. Invoke with /validate-run <run_path> [problem].

Use when creating test plans, reviewing test coverage, defining quality gates, writing E2E test scenarios, or validating acceptance criteria. Invoked for quality assurance, testing strategy, and verification activities.

Terraform infrastructure-as-code patterns for AWS and Azure provisioning. Use when creating or modifying .tf files, writing Terraform modules, managing remote state (S3, Azure Storage), working with terraform commands (init, plan, apply, destroy), configuring providers (AWS, Azure, Google Cloud), or implementing infrastructure best practices like module design, workspace strategies, and state locking.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches code-reviewer subagent to review implementation against plan or requirements before proceeding

Meta-skill for writing and maintaining Claude Code skills. Use when creating new skills, updating existing skills, or reviewing skill quality. Enforces progressive disclosure and size limits.

Analyze checkpoint tests and suggest missing edge cases. Use after writing tests or when reviewing test coverage. Invoke with /edge-cases <problem> <checkpoint>.

Audit Solana programs (Anchor or native Rust) for security vulnerabilities. Use when reviewing smart contract security, finding exploits, analyzing attack vectors, performing security assessments, or when explicitly asked to audit, review security, check for bugs, or find vulnerabilities in Solana programs.

Specialized agent that crafts high level designs and plans

Iteratively craft a CUSTOMER.md document that precisely defines your ideal customer profile (ICP). This is the foundational document from which everything else (product, features, brand) derives. Uses parallel research agents and multi-choice workflow with feedback cycles.

Analyze checkpoint tests and suggest missing edge cases. Use after writing tests or when reviewing test coverage. Invoke with /edge-cases <problem> <checkpoint>.

A meta-skill that helps create new Agent Skills by providing templates, best practices, and validation guidance.

Repository packaging for AI/LLM analysis. Capabilities: pack repos into single files, generate AI-friendly context, codebase snapshots, security audit prep, filter/exclude patterns, token counting, multiple output formats. Actions: pack, generate, export, analyze repositories for LLMs. Keywords: Repomix, repository packaging, LLM context, AI analysis, codebase snapshot, Claude context, ChatGPT context, Gemini context, code packaging, token count, file filtering, security audit, third-party library analysis, context window, single file output. Use when: packaging codebases for AI, generating LLM context, creating codebase snapshots, analyzing third-party libraries, preparing security audits, feeding repos to Claude/ChatGPT/Gemini.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Create ECS component editors using IComponentEditor interface, ComponentEditorRegistry.DrawComponent wrapper, VectorPanel for vectors, and UIPropertyRenderer for simple properties. Covers registration in DI container and manual change detection patterns.

Convex backend development patterns, validators, indexes, actions, queries, mutations, file storage, scheduling, React hooks, and components. Use when writing Convex code, debugging Convex issues, or planning Convex architecture.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible rewrites. Actions: improve, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, prompt optimization, token efficiency, LLM prompt, AI prompt, clarity, structure, system prompt, user prompt, few-shot, chain-of-thought, instruction tuning, prompt compression, token reduction, prompt rewrite, semantic preservation. Use when: improving unclear prompts, reducing token consumption, optimizing LLM outputs, restructuring verbose requests, creating system prompts, enhancing prompt clarity.