LLM & Agents

Validate skills against agentskills.io specification. Use when adding new skills to the marketplace, reviewing skill PRs, checking skill compliance, or running quality gates on skills. Validates frontmatter fields (name, description, license, compatibility, metadata, allowed-tools), directory naming, line limits, and structure.

Coverage Gaps audit worker (L3). Identifies missing tests for critical paths (Money 20+, Security 20+, Data Integrity 15+, Core Flows 15+). Returns list of untested critical business logic with priority justification.

Analyze test coverage, identify gaps, detect dead code, and improve test quality. Use when user asks to check coverage, review tests, find untested code, or improve test robustness.

Set up Claude Code cloud/mobile environments for AILANG development. Use when starting a new cloud session, when tools are missing (Go, make, gh), or when user says "setup cloud", "setup environment", or mentions mobile Claude Code.

File templates for Claude Agent SDK project scaffolding. Used by /agent-sdk:agent-scaffold command.

Use when implementing real-time features requiring reliability, especially LLM streaming. Applies AnyCable patterns for message delivery guarantees, presence tracking, and Action Cable migration.

Digital forensic skill for recovering passwords and sensitive data from disk images, deleted files, and binary data. This skill should be used when tasks involve extracting passwords from disk images, recovering deleted file contents, analyzing binary files for fragments, or forensic data recovery scenarios. Applies to tasks mentioning disk images, deleted files, password fragments, or data recovery.

Use when creating new skills, editing existing skills, or verifying skills work - applies TDD to documentation by testing with subagents before writing

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

This skill guides Cloudflare Workers and Pages development with Wrangler CLI. Use when creating Workers, configuring D1 databases, R2 storage, KV namespaces, Queues, or deploying to Cloudflare Pages.

Guidance for building gRPC-based key-value store services in Python. This skill should be used when tasks involve creating gRPC servers, defining protocol buffer schemas, or implementing key-value storage APIs with gRPC. Covers proto file creation, code generation, server implementation, and verification strategies.

Guidance for optimizing LLM inference request batching and scheduling problems. This skill applies when designing batch schedulers that minimize cost while meeting latency and padding constraints, involving trade-offs between batch count, shape selection, and padding ratios. Use when the task involves grouping requests by sequence lengths, managing shape compilation costs, or optimizing multi-objective scheduling with hard constraints.

Advanced patterns for generating high-quality Claude Code commands. Used by /new-command.

Integration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDK

This skill provides guidance for semantic similarity retrieval tasks using embedding models (e.g., MTEB benchmarks, document ranking). It should be used when computing embeddings for documents/queries, ranking documents by similarity, or identifying top-k similar items. Covers data preprocessing, model selection, similarity computation, and result verification.

Creates 4 root documentation files (CLAUDE.md, docs/README.md, documentation_standards.md, principles.md). L3 Worker invoked by ln-110-project-docs-coordinator.

This skill provides guidance for compiling software (particularly SQLite) with gcov code coverage instrumentation, installing to custom prefixes, and making binaries available system-wide. Use when tasks involve compiling C/C++ projects with coverage flags, installing software to non-standard locations, or ensuring PATH availability for installed binaries.

This skill implements test-driven development workflow using the red-green-refactor cycle. Use when building new features or fixing bugs that require test coverage. Framework-agnostic methodology that works with any testing framework and programming language. Triggers on requests to implement features using TDD, write tests first, or follow test-driven development practices.

Guide for designing effective Letta agents. This skill should be used when users need help choosing agent architectures, designing memory blocks, selecting models, or planning tool configurations for their Letta agents.

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates