← Search

Strava CLI Skill for Muse
Fitness 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit 819485f
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: the strava-cli installed via the repo's install…

Strava CLI Skill for Muse

Ask Muse about your Strava data — activities, stats, segments, routes, gear

⚠️ Security warning / Avertissement de sécurité — the prerequisites install the companion CLI with `curl | sh` from the repo; review the install script yourself before running it. Curated by Skill Harbor — a free, open-source skill (MIT) by @eddmann, listed here with credit to its creator. Turns Muse into a query interface for your own Strava fitness data via the `strava` CLI: recent and filtered activity lists, per-activity detail (streams, laps, zones, comments, kudos), athlete profile and year-to-date/all-time stats, heart-rate and power zones, starred and explored segments with efforts, routes (list, detail, GPX/TCX export), clubs and their activities, and gear inventory — with `jq` patterns for common questions (this month's runs, total distance) and a one-call `strava context` snapshot (athlete, stats, gear, clubs, recent activities). Discovered via skills.sh. Honest note: the skill is a command reference for the strava-cli tool — you must install the CLI and complete Strava OAuth yourself (creating a Strava API app for your client ID/secret is free, but it is a developer-flavoured setup: `strava auth login`), and it reads your private fitness data, so treat the credential like a password and store it in the agent's secure vault, never in code or prompts. Skill Harbor never reviews the code, review it yourself before use. Not verified.

Version:

Quick answer

This skill turns Muse into a query interface for your own Strava data through the strava command-line tool: activities, per-activity detail, athlete stats, segments, routes, clubs and gear. It is a command reference for the strava-cli tool, so you install the CLI and complete Strava OAuth yourself first. The listing carries a security warning: its prerequisites install the companion CLI with curl | sh, so review the install script yourself before running it.

At a glance

What it isA command reference that lets Muse query your Strava account via the strava CLI: recent and filtered activity lists, activity detail (streams, laps, zones, comments, kudos), profile and year-to-date or all-time stats, heart-rate and power zones, starred and explored segments, routes with GPX/TCX export, clubs and gear — plus a one-call strava context snapshot.
Who it's forStrava users comfortable with a developer-flavoured setup, who want to ask questions about their own training data in conversation instead of clicking through the app.
What you give itYour own Strava API app (creating one for your client ID and secret is free), the strava CLI installed on your machine, and a completed strava auth login. The credential reads your private fitness data — the listing says to treat it like a password and keep it in the agent's secure vault, never in code or prompts.
What you getAnswers drawn from your Strava data: activity lists and details, stats, segment efforts, route exports, club activities and your gear inventory, with jq patterns for common questions like this month's runs or total distance.
Works withMuse querying the strava CLI on your machine; the skill itself is installed from this listing with the copy-paste install prompt. Security warning from the listing: the prerequisites install the companion CLI with curl | sh — review that script yourself before running it.
CostFree
TimePlan real setup time before the first question: installing the CLI and completing Strava OAuth are manual steps. After that, a query is one question in conversation.

Example — asking about your own training

An example of a typical use, using only the query types the skill documents — not a reported result.

  • With the CLI installed and strava auth login done, you ask Muse for a strava context snapshot: athlete, stats, gear, clubs and recent activities in one call.
  • You follow up with a filtered question, such as this month's runs, using the jq patterns the skill provides.
  • You ask for a route's detail and export it as a GPX file for your device.
⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 819485f

Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: the strava-cli installed via the repo's install script — review the script at https://raw.githubusercontent.com/eddmann/strava-cli/819485f6ba1723c2b152e6a5cad0c4e6912a369b/install.sh YOURSELF before piping it to sh (the skill installs with curl | sh); then authenticate with `strava auth login`, which needs a STRAVA_CLIENT_ID and STRAVA_CLIENT_SECRET from a free Strava API app you create yourself. Store the credentials in the agent's secure vault — never paste secrets here. Your own Strava account with training data, obviously. Install "Strava CLI Skill for Muse" for me. A command reference for the strava-cli tool that turns Muse into a query interface for my Strava data: activities (list, detail, streams, laps, zones), athlete profile and stats, HR/power zones, segments and efforts, routes with GPX/TCX export, clubs, gear, plus jq patterns for common questions and a one-call `strava context` snapshot. Repository: https://github.com/eddmann/strava-cli Pinned version: install the code at commit 819485f6ba1723c2b152e6a5cad0c4e6912a369b exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. The install script uses curl | sh — verify it only installs the CLI binary and does nothing else. STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "strava". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. run the install script after reviewing it, create my Strava API app, and run `strava auth login`). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 819485f · 2026-10-13
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : files.pythonhosted.org, pypi.org
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
819485f · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.