agentsclimarketplace
Sign in

Keep

Skill zhijunio/skills/keep

Log in via Keep Open API and fetch runs into Garmin-compatible running.json (VDOT, training load, period stats, optional per-km segments). Use for Keep run sync, fetch_keep_run, running.json, or exporting Keep running data.From its SKILL.md

Install
npx -y skills add zhijunio/skills --skill keep

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.3 KB, 288 tokens by cl100k_base, as published. Nobody here has run it

Keep run sync

Pull Keep runs into Garmin-style running.json via scripts/fetch_keep_run.py.

Aligned with upstream fetch-keep-run.py — sync from there when updating behavior.

When to use

  • User mentions Keep API, running.json, VDOT, training load, fetch_keep_run.py
  • Incremental sync or --full export

Hard rules

  1. Credentials via env or CLI — never repeat passwords in chat or logs.
  2. Set --output explicitly in this repo (default path targets Jekyll site layout).
  3. Preserve running.json key names for downstream Garmin consumers.

Workflow

  1. Read references/usage.md for env, flags, output shape.
  2. Run script; use --limit 1 --debug on first API/field issues.
  3. Report merge result (new runs count, output path) — not raw credentials.

Validation

python3 -m py_compile keep/scripts/fetch_keep_run.py

References

  • references/usage.md — CLI, credentials, output, debug

What ships with it: 4 files

24.4 KB alongside SKILL.md, 1 of them executable

evals/

references/

scripts/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.