← Back to Skills Marketplace
dsdevq

Workout Claw

by Denys · GitHub ↗ · v0.3.0 · MIT-0
cross-platform ✓ Security Clean
105
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install workout-claw
Description
Log workouts, track progress, compute PRs, edit/delete sessions via a local CLI. Local-first, JSON storage.
README (SKILL.md)

workout-claw

Local-first gym workout tracker. Plain-JSON storage at ~/.workout-claw/. Invokable as a CLI by an agent — no MCP server, no daemon.

When to invoke

User describes a workout session, asks about progress, or wants to see a PR. Examples that should trigger this skill:

  • "I just did chest day — bench 4x10 at 60, incline DB 4x12 at 20, triceps 4x12 at 40"
  • "Log today's workout"
  • "What's my bench PR?"
  • "Show my back workouts from the last 4 weeks"
  • "What did I do at the gym today?"

How to invoke

Use the workout-claw CLI via Bash. All commands output YAML to stdout, errors to stderr.

Log a workout

workout-claw log "bench 4x10@60, incline-db-press 4x12@20, triceps-pushdown 4x12@40"

Optional flags:

  • --muscle \x3Cgroup>back | legs | chest | shoulders | arms | core | full | cardio | other. If omitted, inferred from weekday (Mon=back, Wed=legs, Fri=chest per ~/.life/domains/health.md).
  • --cardio "\x3Centry>" — e.g. "incline-walk 20min @4.5kmh i6" (minutes, speed kmh, incline)
  • --note "\x3Ctext>" — free-text note
  • --date YYYY-MM-DD — override date
  • --time HH:MM — override time

Input syntax

\x3Cexercise> \x3Csets>x\x3Creps>@\x3Cweight> per entry, comma-separated for multiple exercises.

  • Multi-word exercise names use dashes: incline-db-press, barbell-row
  • Bodyweight: pullups 4x10@bw
  • All weights in kg

Query history

workout-claw history --muscle chest --weeks 4
workout-claw history --exercise bench

Get a PR

workout-claw pr bench

Returns best estimated 1RM via Epley formula: weight × (1 + reps/30).

Cross-day muscle volume (v0.3+)

workout-claw volume --muscle back --weeks 4
workout-claw volume --muscle chest --weeks 8

Aggregates volume per exercise, not per session. Pullups on chest day count toward back volume; triceps-pushdown counts toward arms. Returns total kg lifted, sets, reps, days trained, and a per-date breakdown.

This is the right query for tracking weekly volume per muscle group — far more accurate than history --muscle X which is session-grain.

Summary of today

workout-claw summary
workout-claw summary --date 2026-05-15

Most recent session

workout-claw last

Returns the latest session across all dates — useful for "what did I do at the gym?" without naming a date.

Delete a session

workout-claw delete \x3Csession-id>

Session IDs come from the id field in any log / summary / last output. No confirmation prompt — the CLI is non-interactive by design.

Edit a session

workout-claw edit \x3Csession-id>

Opens the session JSON in $EDITOR (defaults to vi). On save: validates JSON, refuses to save if the id was changed. On parse error: original session unchanged. Useful for fixing typos in exercise names or set counts without a full delete + re-log.

Agent note: edit requires an interactive editor, so the agent should not invoke this in a Telegram round-trip. Instead, when a user asks to fix a logged workout via Telegram, prefer delete + log again, or hand back the session ID and tell the user to run workout-claw edit \x3Cid> from their terminal.

Data location

  • ~/.workout-claw/logs/\x3Cdate>.json — one JSON file per day, array of sessions
  • Schema: see src/lib/types.ts in the workout-claw repo

Notes for the agent

  • After logging, relay the YAML summary back to the user in a readable form (don't dump raw YAML)
  • If the user names an exercise that doesn't match the dash-naming convention, normalize before invoking (e.g. "incline DB press" → incline-db-press)
  • Session-level --muscle is inferred from weekday — only set explicitly if the user names a non-standard split (e.g. arm day on a Tuesday). Per-exercise muscle tags are inferred automatically at log time via name lookup (pullups→back, bench→chest, etc.), so no extra input is needed.
  • When user describes cardio separately, use --cardio flag. When they describe both lifting + cardio in one breath, use both.
  • For "how much back/chest/leg volume?" questions, prefer volume --muscle X over history --muscle X — volume aggregates per-exercise, history filters per-session.
Usage Guidance
Before installing, make sure you trust the separate `workout-claw` CLI that this skill will call. Expect workout logs to be stored locally under `~/.workout-claw/`, and double-check session IDs before using delete commands.
Capability Analysis
Type: OpenClaw Skill Name: workout-claw Version: 0.3.0 The workout-claw skill bundle describes a legitimate local-first workout tracking utility. It uses a CLI tool to manage JSON-based logs in `~/.workout-claw/` and provides clear instructions for the agent to handle logging, history queries, and volume calculations. No indicators of malicious intent, data exfiltration, or harmful prompt injection were found in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
The described capabilities—logging workouts, querying history, computing PRs, and editing/deleting sessions—match the stated workout-tracking purpose.
Instruction Scope
Instructions are mostly scoped to the workout CLI, but the delete command has no confirmation prompt, so users should be precise about session IDs.
Install Mechanism
This is an instruction-only skill with no install spec or code files, yet it assumes a local `workout-claw` executable is available; that executable is outside the reviewed artifacts.
Credentials
No network access or credentials are requested. Local workout data storage is purpose-aligned, but it may include personal health notes and references a local health configuration file.
Persistence & Privilege
The skill persists workout logs under the user's home directory and supports local mutation through edit/delete, but it discloses no daemon, background service, or elevated privilege requirement.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install workout-claw
  3. After installation, invoke the skill by name or use /workout-claw
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.3.0
- Added new `volume` command for cross-day muscle volume tracking, aggregating volume per exercise (not session). - Clarified difference between `volume --muscle X` (preferred for weekly volume tracking) and `history --muscle X`. - Expanded and refined CLI invocation examples and flags, including support for logging cardio and custom session notes. - Updated agent/usage guidance, emphasizing correct trigger behavior and input normalization for exercise names. - Improved documentation on session editing (`edit` command), with caution for Telegram/integrated agent usage. - General documentation and clarity improvements throughout the SKILL.md.
Metadata
Slug workout-claw
Version 0.3.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Workout Claw?

Log workouts, track progress, compute PRs, edit/delete sessions via a local CLI. Local-first, JSON storage. It is an AI Agent Skill for Claude Code / OpenClaw, with 105 downloads so far.

How do I install Workout Claw?

Run "/install workout-claw" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Workout Claw free?

Yes, Workout Claw is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Workout Claw support?

Workout Claw is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Workout Claw?

It is built and maintained by Denys (@dsdevq); the current version is v0.3.0.

💬 Comments