hevy-workouts
Skill541 starsChanged 2 months agoMITView on GitHub
Use when the user asks to inspect, summarize, plan, log, or update Hevy workouts, routines, exercises, or body measurements.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- build-mcpbSkill
- build-mcp-serverSkill
- code-reviewSkill
- diagnosing-bugsSkill
- improve-codebase-architectureSkill
- sentrySkill
- thermo-nuclear-code-quality-reviewSkill
- using-entireSkill
- wayfinderSkill
- hevy-cliSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the Hevy MCP connector for the user's authenticated Hevy account.
- Very specific: line 27
When the plugin is installed, connect or authorize the hevy server in Claude's connector settings.
- Very specific: line 33
Use the tools and resources exposed by the hevy server for Hevy requests.
- Very specific: line 38
Prefer get-training-summary for a high-level trend across workouts and body measurements.
- Distinctive: line 39
Use focused list and detail tools when the user asks about a particular workout, routine, exercise, or date.
- Distinctive: line 45
Treat create and update tools as state-changing operations.
- Distinctive: line 46
Before changing Hevy data, summarize the proposed change and confirm it with the user unless the user has already given an unambiguous …
- Distinctive: line 47
Never invent completed set results, workout times, body measurements, or other missing values.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Hevy workout workflows
Use the Hevy MCP connector for the user's authenticated Hevy account.
MCP server connection
This plugin registers the remote MCP server as hevy through the repository's
.mcp.json file:
{
"mcpServers": {
"hevy": {
"type": "http",
"url": "https://mcp.hevy-mcp.dev/mcp",
"oauth": true
}
}
}When the plugin is installed, connect or authorize the hevy server in Claude's
connector settings. The authorization page asks the user for their Hevy API
key. Never put an API key in this skill, plugin files, or a conversation. If the
server is unavailable, ask the user to complete the connector authorization
instead of attempting to start a different server.
Use the tools and resources exposed by the hevy server for Hevy requests. Do
not call the Hevy API directly or invent an alternative authentication path.
Analysis and retrieval
- Prefer
get-training-summaryfor a high-level trend across workouts and body measurements. - Use focused list and detail tools when the user asks about a particular workout, routine, exercise, or date.
- State the date range and distinguish observations from recommendations.
- Cite the workout or measurement evidence used in a summary when practical.
Mutations
- Treat create and update tools as state-changing operations.
- Before changing Hevy data, summarize the proposed change and confirm it with the user unless the user has already given an unambiguous instruction to make that exact change.
- Never invent completed set results, workout times, body measurements, or other missing values. Ask the user for missing values.
- Explain that create operations can produce duplicates if retried and that update operations replace existing values.
Health context
Workout and body-measurement data is personal information. Describe trends without diagnosing medical conditions, and recommend a qualified professional for medical advice.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

