Log workouts, plan routines, track progress, and get intelligent coaching for any fitness level.

Manage gym operations including membership pricing, retention strategies, staffing, equipment lifecycle, class scheduling, compliance, and growth planning fo...

Guide users buying home gym flooring through space, subfloor, activity, and noise questions to determine the exact material type, thickness, and format they...

Gamify your gym sessions with XP, levels, achievements, and workout streaks

Operational assistant for independent climbing gyms and bouldering studios — membership management, churn reduction, route-setting coordination, youth progra...

Read completed workouts (summaries and full per-set detail), browse and export the exercise catalog, and push custom training programs to your Speediance (Gy...

Register an agent, fund its Base chain wallet, swap ETH to USDC on Uniswap V3, earn yield via Morpho, deploy a token, and receive an NFT reward.

Gym for your bot's brain. Simulates endorphin and flow states — triggers on exercise commands, intense task completion, or social highs. Makes your 🦞 think...

Aggregate per-location gym data from bayclubs.com — name, full address, phone, email, weekly operating hours, and the club-specific amenity list — across all 33 Bay Club locations for a wellness/health platform.

Comprehensive training system offering personalized periodized programs for strength, endurance, fat loss, hypertrophy, injury rehab, and race prep based on...

Reference tool for devtools — covers intro, quickstart, patterns and more. Quick lookup for Gymlog concepts, best practices, and implementation patterns.

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or …

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when …

Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-onc…

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use…

Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integra…

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or …

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when …

Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers du…

Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-onc…

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use…

Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integra…

Workout planning, macros, and body metrics via wger/USDA.

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from nvidia/skills

Rebuild a body that's been sitting in a chair for years. Fix posture, build functional strength, and recover mobility. No gym required. For people who are de...

半饱 — 生活的高潮所在。A mindful eating companion for desk workers. Track meals with photos, understand your body's needs, no gym guilt.

Fitness accountability for the Lofy AI assistant — workout logging from natural language, meal tracking with calorie/protein estimates, PR detection with Epley formula, gym reminders based on weekly targets, and progress reports. Use when logging workouts, meals, tracking fitn…

Your AI strength coach that customizes workouts from gym photos, tracks progress, adapts to injuries, and plans smart splits with no subscription needed.

Track workouts, log sets, manage exercises and templates with workout-cli. Supports multi-user profiles. Use when helping users record gym sessions, view history, or analyze strength progression.

Log a strength training session and insert it into the life_db database. Use when the user shares their gym session, exercises, sets, reps, weights, RPE, res...

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyz…

Your AI personal trainer that creates custom workouts from your gym photo, tracks progress and PRs, adapts training splits and exercises around injuries, and...

Use this skill when the user wants to poll gym venue availability, inspect or modify the `venue_polling.py` order-signing flow, or run the bundled signature...

Manage and track gym workouts, routines, nutrition, and progress using the wger API for viewing, creating, updating, and reporting fitness data.

Manage gym routines, log workouts, track nutrition, update goals, and generate fitness reports via the wger API integrated with OpenClaw automation.

Personal health coach for gym and daily reminders with weather-aware outfit suggestions.

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyz…