Turn Claude into the athlete's coach: an AskUserQuestion-driven conversation about goals, equipment, schedule, injuries and preferences that produces a validated hevy-periodizer training config, then ongoing weekly reviews, mid-course adjustments, and evidence-grounded answers. Pairs with the hevy-periodizer engine, which does the load arithmetic.
Plugin hevy-coach from marketplace atelier in RachidChabane/atelier. Commands read from the repo's manifest — 1 month ago.
training-adjustThis skill should be used when the user says life has interfered with training — "I'm travelling", "I hurt my back", "I only have 30 minutes", "I missed two weeks", "my gym closed", "I want to swap an exercise", "I'm stuck on this lift" — or asks to change part of their program without rebuilding it
training-onboardingThis skill should be used when the user asks to "set up my training", "build me a program", "be my coach", "start training", "make me a training plan", "onboard me", or opens a project containing a hevy-periodizer config that is missing or incomplete. It drives a coaching conversation — goals, equip
training-week-reviewThis skill should be used when the user asks to "review my week", "how did my training go", "check in on my training", "what's next week", "I finished my week", or asks why a prescribed weight or rep count changed. It reads the engine's deterministic review, forms a coaching opinion on the parts the
Migrate a project off `claude -p` onto a tmux-driven interactive Claude Code backend so usage stays on the Claude subscription pool. Anthropic announced this billing split for 2026-06-15 then paused it — `claude -p` still draws from the subscription today, so this is contingency preparation, not a live cost fix.
1 skill
Drive a fresh repo through Stage-1 planning artifacts (vision, roadmap, requirements, open questions, architecture options, decisions) and prepare hand-offs for design system + pitch deck, information architecture, screen design, and implementation slate. Stage 2 creates and publishes a Claude Design design system via its setup form first, then generates a deck that inherits it. Resumes from whatever already exists in docs/.
1 skill
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
Real-time graph intelligence — personalized PageRank, streaming delta updates, witness-signed reasoning, and federation-distributable vectors
1 skill
Build, train, evaluate, and use open source AI models, datasets, and spaces.
26 skills · 1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and external agent monitoring.
19 skills
Personal knowledge brain for your coding agent — hybrid search, synthesis, and durable cross-session memory, plus a curated brain-first skill set.
80 skills · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.