# Personal Fitness Trainer

> Assesses user fitness goals, queries appropriate strength training exercises, constructs a custom workout routine, and registers it using wger-agent tools.

- Skill: `knuckles-team/personal-fitness-trainer` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add knuckles-team/personal-fitness-trainer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/knuckles-team/personal-fitness-trainer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Knuckles-Team (https://skillmd.com/u/knuckles-team)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/knuckles-team/personal-fitness-trainer

---


# Personal Fitness Trainer Workflow

**CONCEPT:HEALTH-001**

Assesses user fitness goals, queries appropriate strength training exercises, constructs a custom workout routine, and registers it using wger-agent tools.

## Steps

### Step 0: Fitness Trainer
**Agent**: `data-collector`
**Tools**: `graph_query`

Conduct the user's fitness and muscle group intake assessment. Query the wger exercise database using wger_exercise tool with search query and muscle group parameters to discover target exercises.
Expected: `intake, exercises`

### Step 1: Wger Agent
**Agent**: `analyzer-agent`
**Tools**: `graph_analyze`

Create and configure a personal strength routine. Call the wger_routine tool to create a new routine, and then configure its workout days and exercises using the wger_routineconfig tool.
Expected: `routine, configuration`

### Step 2: KG Persistence [depends_on: wger-agent]
**Agent**: `analyzer-agent`
**Tools**: `graph_write`

Persist workflow results as nodes and edges in the Knowledge Graph.
Create appropriate typed nodes with metadata and link to existing domain entities.

## Output
- Personal Fitness Trainer results persisted in KG
- Structured report (MD/PDF)
- Audit trail with timestamps and agent attributions

## Human Oversight Required
✅ Critical decisions require human review and approval.

## Execution

Run this workflow as a dependency-ordered DAG. Steps with no unmet `depends_on` run in parallel; dependents run after their prerequisites complete.

- **Run first (in parallel):** Step 0 — Fitness Trainer; Step 1 — Wger Agent
- **After level 0:** Step 2 — KG Persistence

**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.