Freeletics

Build me a focused fitness, activity and general wellbeing workflow for the personal core of Freeletics. Requirements:

- Use React Native with Expo, TypeScript, SQLite, and HealthKit or Health Connect only when explicitly enabled. Model user-entered activities or observations, daily summaries, preferences, and exports; keep stable source IDs and timestamps.
- Paid product context: Build a moderate bodyweight routine planner from a fixed safe exercise library. Build only this DIY scope: Log bodyweight workouts, plan moderate routines from a fixed safe exercise library, and show trends without diagnosing, shaming, or enforcing restrictive goals.
- Create optional logs for activity, sleep, mood, energy, and personal notes with editable units.
- Show weekly patterns and consistency with neutral language and no diagnostic or body-image judgments.
- Add reminders that can be muted, data export, account-free local use, and full deletion.
- Use a native mobile screen with input, current state, and result review. Required input or access: iOS or Android device; optional HealthKit or Health Connect permission.
- Recovery: Request health-platform permissions per data type and work fully without granting them.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A duplicate health import cannot double-count an entry; deleting a record must remove it from the daily summary.
- Out of scope: adaptive coaching models, content, mobile experience, community, and brand; wearable hardware data. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for Freeletics

## Project scope
Log bodyweight workouts, plan moderate routines from a fixed safe exercise library, and show trends without diagnosing, shaming, or enforcing restrictive goals.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Freeletics, build a moderate bodyweight routine planner from a fixed safe exercise library. The hard boundary is adaptive coaching models, content, mobile experience, community, and brand, plus hardware data, content, coaching, and trust.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- iOS or Android device
- optional HealthKit or Health Connect permission
- local storage

## Stack and architecture
- Use React Native with Expo, TypeScript, SQLite, and HealthKit or Health Connect only when explicitly enabled.
- Model user-entered activities or observations, daily summaries, preferences, and exports; keep stable source IDs and timestamps.
- Interface for this fitness, activity and general wellbeing workflow: a native mobile screen with input, current state, and result review.

## Security and data integrity
- Request health-platform permissions per data type and work fully without granting them.
- Validate imported records and file paths; keep user data within the storage location named in the prompt.
- State the practical limit: adaptive coaching models, content, mobile experience, community, and brand.

## Agent implementation rules
- Project rule, data: Model user-entered activities or observations, daily summaries, preferences, and exports; keep stable source IDs and timestamps.
- Project rule, behavior: Create optional logs for activity, sleep, mood, energy, and personal notes with editable units.
- Project rule, recovery: Request health-platform permissions per data type and work fully without granting them.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this fitness, activity and general wellbeing operation with sample or user-owned data: Create optional logs for activity, sleep, mood, energy, and personal notes with editable units.
- Show a concrete result or export: Add reminders that can be muted, data export, account-free local use, and full deletion.
- State the practical limit: adaptive coaching models, content, mobile experience, community, and brand.

## Engineering roadmap
1. Phase 1, architecture and data: Use React Native with Expo, TypeScript, SQLite, and HealthKit or Health Connect only when explicitly enabled. Model user-entered activities or observations, daily summaries, preferences, and exports; keep stable source IDs and timestamps.
2. Phase 2, implement: Create optional logs for activity, sleep, mood, energy, and personal notes with editable units.
3. Phase 3, implement: Show weekly patterns and consistency with neutral language and no diagnostic or body-image judgments.
4. Phase 4, review and output: Add reminders that can be muted, data export, account-free local use, and full deletion.
5. Phase 5, recovery and acceptance: Request health-platform permissions per data type and work fully without granting them. Verify this invariant with a saved fixture: A duplicate health import cannot double-count an entry; deleting a record must remove it from the daily summary. State the practical limit: adaptive coaching models, content, mobile experience, community, and brand.

## Paid-product capabilities outside this build
- adaptive coaching models, content, mobile experience, community, and brand
- wearable hardware data
- coach network
- clinical validation
- large content library and social network

## Implementation prompt
Build me a focused fitness, activity and general wellbeing workflow for the personal core of Freeletics. Requirements:

- Use React Native with Expo, TypeScript, SQLite, and HealthKit or Health Connect only when explicitly enabled. Model user-entered activities or observations, daily summaries, preferences, and exports; keep stable source IDs and timestamps.
- Paid product context: Build a moderate bodyweight routine planner from a fixed safe exercise library. Build only this DIY scope: Log bodyweight workouts, plan moderate routines from a fixed safe exercise library, and show trends without diagnosing, shaming, or enforcing restrictive goals.
- Create optional logs for activity, sleep, mood, energy, and personal notes with editable units.
- Show weekly patterns and consistency with neutral language and no diagnostic or body-image judgments.
- Add reminders that can be muted, data export, account-free local use, and full deletion.
- Use a native mobile screen with input, current state, and result review. Required input or access: iOS or Android device; optional HealthKit or Health Connect permission.
- Recovery: Request health-platform permissions per data type and work fully without granting them.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A duplicate health import cannot double-count an entry; deleting a record must remove it from the daily summary.
- Out of scope: adaptive coaching models, content, mobile experience, community, and brand; wearable hardware data. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.