community-automations/strava-coach

Research & Intel

PublicClaude subagent

Strava Coach

Strava shows you the numbers but rarely tells you what to do with them. Strava Coach reads each activity as it syncs and weighs it against your recent training load.

sonnet3 daysStrava APIPostgresOpenAITelegram
ClaudeClaude
ROI for
README.md

Why this subagent

Strava shows you the numbers but rarely tells you what to do with them. Strava Coach reads each activity as it syncs and weighs it against your recent training load.

After every workout you get a short personal debrief: how hard the session really was, whether you should recover, and one concrete tweak for next time. It is the running commentary a coach gives, generated from your own data.

How it runs

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

Sample output

json
// Sample output
// (generated when the pipeline finishes)

Given the latest activity and 4-week history, return coaching notes covering effort level, recovery flag, and one concrete suggestion for the next session.

Unlock the rest

The full agent definition, install snippet, and starter task are gated for community members.

Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.