codex-skills-index
About
This skill serves as the central catalog and entry point for all Run-Smart AI coach skills, defining their shared conventions, contracts, and safety guardrails. Developers should use it before invoking any skill to understand common schemas and telemetry, or when onboarding a new skill to ensure compliance. Its key capabilities include providing shared references for validation and enabling Codex to discover available skills.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/codex-skills-indexCopy and paste this command in Claude Code to install this skill
Documentation
Purpose
Defines the shared conventions, contracts, safety posture, and telemetry used by all Run-Smart AI skills. This index allows Codex to discover available skills and the rules they follow.
When Codex should use it
- Before invoking any Run-Smart skill to understand shared schemas, safety guidance, and telemetry.
- When onboarding a new skill to ensure compliance with common contracts.
Invocation guidance
- Load shared references in
_index/references/(contracts, telemetry, conventions, smoke-tests). - Select the appropriate skill directory based on the user’s need (plan generation, adjustment, insights, etc.).
- Validate request/response payloads against the schemas in
contracts.mdand skill-specific schemas.
Shared components
- Contracts:
_index/references/contracts.md - Telemetry:
_index/references/telemetry.md - Conventions:
_index/references/conventions.md - Smoke tests:
_index/references/smoke-tests.md
Safety & guardrails
- No medical diagnosis. If pain/dizziness/severe symptoms appear, advise stopping activity and consulting a qualified professional.
- Prefer conservative adjustments under uncertainty.
- Emit
SafetyFlagobjects when thresholds are crossed and log viaai_safety_flag_raised.
Integration points
- Skills are invoked from chat flows (
v0/app/api/chat/route.ts,v0/lib/enhanced-ai-coach.ts), plan generation APIs (v0/app/api/generate-plan/route.ts), background jobs (plan adjustment), and post-run screens.
Telemetry events (standard)
ai_skill_invokedai_plan_generatedai_adjustment_appliedai_insight_createdai_safety_flag_raisedai_user_feedback
GitHub Repository
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.