codex-skills-index

nadavyigal's avatarfrom nadavyigal

Entry point for Codex-discoverable skills used by the Run-Smart AI coach.

⭐1stars🔀0forks📁View on GitHub🕐Updated Jan 3, 2026
[Tool Routing and Orchestration]

When & Why to Use This Skill

This Claude skill serves as the foundational management hub and discovery index for the Run-Smart AI coach ecosystem. It establishes a standardized framework for AI skills by defining shared contracts, safety guardrails, and telemetry protocols. By providing a structured entry point, it ensures that all integrated skills adhere to consistent operational standards, safety requirements, and performance monitoring, facilitating seamless orchestration and reliable AI-driven interactions.

Use Cases

  • Skill Discovery: Enabling AI agents to dynamically locate and invoke specific capabilities like plan generation or performance insights through a unified catalog.
  • Safety Compliance: Enforcing mandatory safety guardrails and medical disclaimers across all fitness-related AI interactions to prevent unauthorized medical advice.
  • Standardized Telemetry: Implementing a consistent logging framework to track AI skill usage, safety flags, and user feedback for system-wide observability.
  • Contract Validation: Ensuring that data exchanged between different AI components matches predefined schemas to prevent integration errors and maintain system stability.
namecodex-skills-index
descriptionEntry point for Codex-discoverable skills used by the Run-Smart AI coach.
short-descriptionCatalog of AI skills, contracts, telemetry, and guardrails for Run-Smart.

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

  1. Load shared references in _index/references/ (contracts, telemetry, conventions, smoke-tests).
  2. Select the appropriate skill directory based on the user’s need (plan generation, adjustment, insights, etc.).
  3. Validate request/response payloads against the schemas in contracts.md and 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 SafetyFlag objects when thresholds are crossed and log via ai_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_invoked
  • ai_plan_generated
  • ai_adjustment_applied
  • ai_insight_created
  • ai_safety_flag_raised
  • ai_user_feedback