Claude Skills

This skill provides best practices for versioning AI prompts using semantic versioning and structured metadata. It helps developers track prompt changes, maintain changelogs, and organize different prompt versions systematically. Use this when implementing version control for production prompts in AI applications.

This skill enables version control and management for AI prompts, allowing developers to track changes, compare iterations, and maintain prompt history. It provides tools to create versioned prompt templates with parameters like style and length constraints. Use this when you need reproducible, auditable prompt workflows across different model versions or team collaborations.

This Claude Skill helps developers optimize AI usage efficiency by promoting script-first patterns, batch operations, and prepared input files. It provides effectiveness ratings for different approaches, emphasizing execution over description to maximize productivity. Use it when you need to reduce AI interaction time and get more actionable, automated outputs from Claude.

This skill provides automated model selection guidance for Claude Code based on task complexity, cost, and latency needs. It offers a decision tree and quick reference table to help developers choose between Opus, Sonnet, and Haiku models efficiently. Use it when starting new tasks to optimize performance and resource usage.

This skill optimizes AI agent usage by analyzing cached quota data to recommend the best provider for each task. It displays remaining quotas, applies routing rules based on task complexity, and flags critically low providers. Use it as a pre-gate check in `/work run` to ensure efficient resource allocation.

This skill provides commands to optimize AI agent usage by recommending the most suitable provider for tasks. It shows quota availability and routes tasks to appropriate providers based on workload queues or specific task descriptions. Developers use it to efficiently allocate AI resources across different task routes (A, B, C) and ad-hoc requests.

This skill integrates agent usage optimization with work queues by displaying real-time provider capacity and upcoming job allocations. It automatically reroutes work items when provider quotas become critically low, ensuring efficient resource utilization. Developers should use it to monitor and manage AI agent allocations within their workflow execution system.

This skill displays remaining API quota percentages for different AI providers in a formatted table with color-coded status indicators. It helps developers choose the most appropriate model based on availability and recommended use cases. The output includes cache freshness information and visual status thresholds for quick quota assessment.

This skill reads and validates a cached quota file to check Claude API usage availability. It verifies the cache exists and is less than one hour old, providing warnings if outdated or missing. Use this as the first step in agent routing to determine if Claude models are available before proceeding.

This reference skill provides a quick comparison table of AI providers (Claude models, Codex, Gemini) with their strengths and ideal use cases. It helps developers optimize agent usage by selecting the most suitable provider for tasks like architecture, coding, or bulk data processing. Use it to make informed decisions on model selection based on task requirements and constraints like quota and cost.

This Claude skill classifies development tasks into specific processing routes (A, B, C, Bulk, Long-context) based on keywords in the user's request. It helps optimize agent usage by routing simple tasks, standard implementations, complex architecture work, bulk operations, and large-context jobs appropriately. Developers use it to ensure their queries are handled by the most suitable agent with the correct scope and resources.

This skill calculates the remaining hours until daily usage limits reset at midnight UTC. It provides a shell script snippet that computes the time difference between current UTC and the next midnight. Developers should use this when implementing rate limiting or monitoring agent usage against daily quotas.

This skill provides a model selection guide based on task complexity, mapping routine tasks to Haiku, standard tasks to Sonnet, and complex tasks to Opus. It helps developers optimize costs by routing simpler tasks to cheaper models while reserving powerful models for demanding work. Use it alongside route mapping when the task nature is clear to close the gap between theoretical and observed implementation efficiency.

This skill provides default AI model routing logic for different coding task complexities, independent of quota limits. It maps simple tasks to Codex, standard tasks to Claude Sonnet, and complex architectural work to Claude Opus, with fallback options specified. Developers should use this as the baseline configuration for optimizing AI agent usage in their coding workflows.

This skill optimizes AI model selection by reading quota states and recommending the best Claude/Codex/Gemini allocation for each task. It provides quota-aware routing and headroom displays, making it ideal for work sessions with multiple queued items or when approaching quota limits. Developers should use it before starting sessions with 3+ work items or when Claude quotas drop below 50% remaining.

This mandatory workflow scans code for legal risks like client names or proprietary references before cross-review. It blocks the review cycle if violations are found, requiring fixes first. Use it as a pre-gate for PR creation, code porting, or any cross-review trigger.

This skill provides structured metrics for evaluating brainstorming sessions, including targets for questions per design, validation rates, and stakeholder alignment. It helps developers measure brainstorming effectiveness and implementation quality. Use it to establish clear success criteria and track rework during project planning phases.

This Claude Skill provides structured guidance for handling common brainstorming roadblocks like conflicting requirements or scope creep. It offers specific action templates to resolve issues such as unclear responses or analysis paralysis. Developers should use this reference skill to maintain productive brainstorming sessions within Claude Code.

This Claude Skill provides structured best practices for effective brainstorming sessions, focusing on user-centered approaches like starting with needs and validating options. It offers clear "Do" and "Don't" guidelines to maintain productive collaboration and avoid premature solutions. Developers should use this reference skill when facilitating brainstorming to ensure thorough understanding and documented decisions.

The brainstorming skill transforms initial ideas into detailed specifications through iterative questioning and collaborative dialogue. It helps developers explore design options, evaluate trade-offs, and create shared understanding before implementation. This prevents rework by systematically refining concepts into actionable plans.

This sub-skill defines version metadata and compatibility requirements for the repo-cleanup skill. It specifies the skill version, supported Python versions, and compatible operating systems. Developers should reference this to understand the runtime environment and dependencies needed for the main repo-cleanup functionality.

This skill handles repository structure documentation updates after cleanup operations. It automatically updates directory trees, removes references to deleted folders, and documents architectural changes like `.claude/` folders and consolidated scripts. Use it to maintain accurate structure sections in README files following repository reorganization.

This skill identifies legacy directories and files that should be removed or consolidated during repository cleanup. It provides a specific checklist for developers, including paths like `.agent-os/` and `.drcode/` that are obsolete or have been moved to new locations. Use this reference when cleaning up a Claude Code project to ensure proper migration and deletion of outdated assets.

This sub-skill provides shell commands for tracking file counts during repository cleanup operations, specifically for hidden folders like `.claude` and `.agent-os`. It includes verification scripts to ensure no files are lost after merging changes. Use it when consolidating or reorganizing project directories to monitor progress and validate results.