Plugin Claude Code
Plugin marketplace listing 1 plugin: aicoach-framework.
Plugin Claude Code
Plugin marketplace listing 1 plugin: aicoach-framework.
Plugin Claude Code
Multi-agent AI coach for endurance & strength athletes — runs entirely inside Claude Code.
Instructions file
Instructions for airbone42/360-data-athlete, covering 360° data athlete — multi-agent coach (framework), role: head coach, for plugin consumers (pointer), session start (mandatory) and mandatory read fields after fetchcontext.py.
Agent
Post-activity coaching analyst. Produces personal coaching feedback after a session: overview, strengths, growth areas. Max 250 words. Builds on the factual chronicle from data-scientist.
Agent
Consistency auditor for the coach knowledge base. Analyses drift between config/ files, sub-agents in agents/, prompts in prompts/, the exercise mapping, and external sources (intervals.icu NOTEs). Reads scanner JSON from scripts/auditconsistency.py, adds semantic checks, and writes a structured report to data/audits/.
Agent
Implements fixes for consistency-audit findings. Receives ONE finding (or a batch of identical category) as a YAML block, proposes a concrete diff, gets athlete approval, and executes the change. Fresh context — no live coach session.
Agent
Technical data reporter. Produces factual, neutral reports from training data — no interpretation, no coaching. Primarily for lap chronicles (HR-zone transitions, running dynamics, surface), but usable for any data-based analysis task.
Agent
Periodic exercise-selection reviewer. Re-challenges whether the current exercises still serve the athlete's goals and fitness level — invoked only when the re-evaluation trigger fires (recovery week, periodization phase change, or staleness). Fresh context, advisory only — never a silent swap. Produces…
Agent
Mental companion for the athlete. Situationally direct or reflective — depending on context. Responsible for pre-workout motivation, setback processing, and constructive analysis framing. Reads config/ files itself.
Agent
Sports-physiotherapist consultation. Evaluates injuries, symptoms and training load from a physiotherapeutic perspective. Provides diagnosis-likelihood ranking, rehab-protocol suggestion, load management, and red flags. Not a substitute for an in-person examination — makes that explicit.
Agent
Semantic plan validator. Checks the day plan context-sensitively against training paradigms, pillar rotation, stimulus adequacy, exercise logic, and progression consistency. Fresh context — no live coach session. Invoked in the /training flow after the specialists and before the push.
Agent
Strategic daily planner. Decides WHAT is trained (types, intensity, duration). Reads config/ files itself. Output: plan directive JSON with coachingnotes + workouts[]. Launch this agent as a teammate when you need a day plan.
Agent
Sport-science research specialist. Resolves a coach-flagged uncertainty by consulting the local research library first, then peer-reviewed literature / recognised coach sources via web search. Persists a schema-conform document under framework/research/, updates the index, and returns TL;DR + sources + derivation +…
Agent
Strength, plyo and core specialist. Translates the planner directive into a concrete training structure with exercises, sets, reps and weights. Handles WeightTraining / Workout without the ninja tag. Reads config/ files itself. Output: JSON with structure, focus, durationnote.
Agent
Run and endurance specialist. Translates the planner directive into a concrete training structure with intervals.icu format. Handles Run and Ride workouts. Reads config/ files itself. Output: JSON with structure, intervalsicu, focus, durationnote.
Agent
Ninja athletics specialist. Translates the planner directive into a progressive ninja training session built on the 5 pillars (Grip, Pull, Push, Core, Explosive Power). Handles workouts with the ninja tag. Reads config/ files itself. Output: JSON with structure, focus, durationnote.
Agent
Sports-orthopaedist consultation. Evaluates injuries from an orthopaedic and sports-medical perspective. Focuses on structural diagnosis, imaging indication (MRI, ultrasound), clinical tests, and return-to-sport criteria. Not a substitute for an in-person examination — makes that explicit.
Agent
Video form-check specialist. Analyses training videos for execution quality and sports-physiological soundness. Combines movement analysis with biomechanics knowledge and actively challenges whether the exercise + approach is optimal for the athlete.
Command
Command "analyse" from airbone42/360-data-athlete, covering /analyse — activity analysis, arguments, workflow, step 1: load athlete knowledge + activity (parallel) and step 2: fetch athlete context.
Command
Scans the coach system for contradictions between config/ files, sub-agents, prompts, the exercise mapping, and external sources (intervals.icu NOTEs). Findings are refined by the config-auditor (fresh context) and written as a markdown report to data/audits/. Fixes go through the config-fixer (fresh context) after…
Command
Shows the current fatigue status of all sport-relevant muscles, grouped by body part.
Command
Fetches and fast-forward-merges the configured default branch from origin into the current working copy. Works against whatever remote is configured (Gitea, GitHub, …) — the command itself is generic.
Command
Resolves a concrete sport-science question with verifiable evidence and persists the finding to framework/research/. Two entry points.
Command
Build the training plan for today (or a given date).