Menu
SkillsMP has collected 60 skills from nadavyigal/Running-coach-. Open a skill to review its source and details.
Showing 40 of 60 collected skills.
Plan, build, sign, test, automate, distribute, and troubleshoot professional iOS applications. Use when Codex needs to work on Swift or Objective-C iPhone or iPad apps, Xcode projects or workspaces, app extensions, signing and provisioning, Swift Package…
Build, sign, test, archive, and distribute iOS applications with modern Xcode workflows. Use when Codex needs to create or maintain an iPhone or iPad app, configure Xcode projects and schemes, add supported Xcode extensions or Swift Package plugins, automate…
iOS expert agent for RunSmart native app development. Handles SwiftUI architecture, HealthKit integration, App Store deployment, and monorepo coordination with the web app. Use when working on any iOS-related development, planning, or platform decisions.
Systematic error triage workflow for RunSmart. Use when the user asks to debug an error, investigate a failing flow, fix a broken deploy, diagnose a console issue, or mentions recurring bugs like Supabase 406, missing tables, stale production, or post-deploy…
Entry point for Codex-discoverable skills used by the Run-Smart AI coach.
Reference catalog for all running coach AI skills, shared TypeScript contracts, safety guardrails, and telemetry conventions. Use when working with any running coach feature to understand data schemas, safety patterns, or integration points.
Structured implementation workflow for turning an approved plan or spec into code. Use when the user asks to implement a plan, execute a phase, build from a spec, carry out a roadmap item, or complete a multi-step feature without re-deciding the design.
Visual regression workflow for RunSmart UI changes. Use when the user is redesigning a screen, changing layouts, swapping templates, polishing visuals, updating CSS variables, or wants to verify that a UI change did not break existing screens.
Generates structured Garmin coaching insights (daily, weekly, post-run) from derived metrics and stores them via the AI insight pipeline.
Produces a weekly Garmin-based training report with load, recovery, and next-week focus.
Implement, debug, and operate Garmin Health API sync for RunSmart. Use when working on Garmin OAuth, permissions/provisioning issues, activities/sleep sync routes, diagnose output interpretation, or Garmin support escalation requests. Trigger for errors like…
Garmin Connect OAuth integration for the RunSmart PWA. Covers the complete OAuth 2.0 flow, token storage in Dexie.js (IndexedDB), activity fetching, device lifecycle (connect/sync/disconnect), and the thin-backend architecture pattern. Use when working on…
Garmin Connect OAuth integration for the RunSmart PWA. Covers the complete OAuth 2.0 flow, token storage in Dexie.js (IndexedDB), activity fetching, device lifecycle (connect/sync/disconnect), and the thin-backend architecture pattern. Use when working on…
Use for Core Location troubleshooting - no location updates, background location broken, authorization denied, geofence not triggering
Systematic visual geolocation reasoning from images. [VAD] Analyzes photos, street views, or satellite imagery to determine location. Uses visual clue extraction, hypothesis formation, and web verification. [NÄR] Use when: geolocate, identify location, where…
Community building and user acquisition strategies for RunSmart. Covers running community engagement, Strava integration, referral programs, content-led growth, influencer partnerships, and grassroots marketing in running communities. Use when planning user…
Parallel development workflow using agent teams for RunSmart features. Spawns specialized teammates (architect, frontend, backend, QA) that coordinate via shared task lists. Use for multi-file features, epic implementation, or any development task benefiting…
Analytics setup, conversion tracking, growth metrics, and data-driven optimization for RunSmart. Covers event tracking, funnel analysis, cohort metrics, retention curves, and experiment frameworks. Use when setting up analytics, analyzing user behavior, or…
Coordinated multi-agent marketing campaigns for RunSmart. Spawns specialist teammates for copywriting, SEO, social media, email sequences, and analytics. Use for product launches, content campaigns, growth experiments, or any marketing effort requiring…
Deployment, CI/CD, monitoring, and production operations for RunSmart PWA. Covers Vercel deployment, environment management, performance monitoring, error tracking, and production incident response. Use when deploying, configuring infrastructure, or…
PWA distribution strategy for RunSmart including app store optimization, web install prompts, TWA (Trusted Web Activity) for Google Play, Apple Add-to-Home-Screen optimization, and cross-platform distribution channels. Use when planning app distribution,…
Reference catalog for all running coach AI skills, shared TypeScript contracts, safety guardrails, and telemetry conventions. Use when working with any running coach feature to understand data schemas, safety patterns, or integration points.
Master multi-agent orchestration for RunSmart using Claude Code Agent Teams. Coordinates parallel specialists across development, marketing, QA, and operations. Use when tasks benefit from divide-and-conquer: feature builds, marketing campaigns, bug…
This skill should be used when the user asks to "decide what to build", "prioritize features", "choose an approach", "evaluate options", "should I build this", "what should I ship next", or needs help making product/implementation decisions quickly without…
This skill should be used when the user asks "Should I build this feature?", "Is this idea viable?", "Am I over-engineering?", "Should I use Kubernetes?", "validate product idea", "build in secret", "tech stack too complex", "is this worth building?",…
This skill should be used for ANYTHING related to landing page development including "review my landing page", "create a landing page", "write landing page copy", "build a landing page", "improve conversion rate", "optimize landing page", "landing page CRO",…
Identifies missed training sessions and proposes plan reshuffles with motivational support. Use for weekly check-ins, when multiple sessions are skipped, or when user asks for help getting back on track.
Chat-based goal classification (habit/distance/speed/race) with constraint clarification. Use during onboarding or when user wants to update their running goals through conversation with weekly commitment discovery.
Detects unsafe training load spikes (>20-30% week-over-week) and emits safety flags. Use in nightly background jobs or when reviewing weekly training volume with conservative adjustment recommendations.
Recomputes upcoming workouts based on recent runs and user feedback. Use when recent performance deviates from plan, user provides negative feedback, or recovery signals indicate adjustment needed with deterministic safety caps.
Generates 14–21 day personalized running training plans with safe load progression. Use when user completes onboarding, requests a new plan, updates their running goals, or wants to export a training calendar.
Converts run telemetry and user notes into structured reflections with confidence scores. Use after runs to capture qualitative feedback and generate next-step guidance with safety checks for pain or abnormal heart rate.
Generates race-day pacing and fueling strategies with contingency plans. Use when user has an upcoming race, asks for race preparation advice, or wants a printable race-day plan with segment pacing and fueling schedule.
Pre-run safety gate that evaluates readiness and recommends proceed/modify/skip decisions. Use before scheduled workouts to assess recovery status, injury signals, and training load based on sleep, soreness, and recent activity.
Generates route specifications with distance and elevation constraints. Use when user asks for route suggestions, wants to explore new running paths, or needs safer surface recommendations for upcoming workouts.
Analyzes completed runs to provide effort assessment, recovery recommendations, and next-session guidance. Use immediately after user saves a run, asks "how did I do?", or requests recovery advice.
Reference catalog for all running coach AI skills, shared TypeScript contracts, safety guardrails, and telemetry conventions. Use when working with any running coach feature to understand data schemas, safety patterns, or integration points.
Translates planned workouts into execution cues, purpose explanations, and common mistakes to avoid. Use before workouts when user asks "what should I do?" or "how do I run this session?" with beginner-friendly guidance.
Identifies missed training sessions and proposes plan reshuffles with motivational support. Use for weekly check-ins, when multiple sessions are skipped, or when user asks for help getting back on track.
Chat-based goal classification (habit/distance/speed/race) with constraint clarification. Use during onboarding or when user wants to update their running goals through conversation with weekly commitment discovery.