agentsclimarketplace

Setup

Skill agenkin/telemetrydeck-analytics/skills/setup

Interactive first-run setup for the TelemetryDeck analytics CLI — prompts for email/password, mints a bearer, lets the user pick an app.From its SKILL.md

Install
npx -y skills add agenkin/telemetrydeck-analytics --skill setup

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

2 things to look at

  • 2 stars2 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.
  • runs commandsInstructs the agent to run 3 commands, including `tdq doctor` and 2 more.

SKILL.md

1.6 KB, 352 tokens by cl100k_base, as published. Nobody here has run it

Setup

tdq login requires a real TTY for interactive prompts. Claude Code's Bash tool is not a TTY, so attempt the login and handle the two cases:

Case 1 — credentials not yet stored (first run)

Running tdq login via Bash will fail with:

stdin is not a TTY — cannot prompt for email.
Run `tdq login` directly in your terminal.

Tell the user: open a terminal and run tdq login. Walk them through what to expect:

  1. TelemetryDeck email prompt
  2. Password prompt (hidden)
  3. Numbered app picker — type the number next to their app and press Enter
  4. A login summary is printed on success

Once they confirm it completed, run tdq doctor via Bash to verify the token is live.

Case 2 — credentials already stored, only app selection needed

If email + password are already in the keychain (e.g. re-setup after switching apps), the non-TTY error will be on the app picker step. The CLI prints the app list before exiting. Read the app names and UUIDs from the error output and ask the user which app to use. Then run:

tdq login --app-id <chosen-uuid>

--app-id skips the picker entirely and works non-interactively.

Case 3 — $ARGUMENTS contains a UUID

Skip the picker immediately:

tdq login --app-id $ARGUMENTS

After any successful login

Run tdq doctor and relay the output so the user sees the end-to-end health check pass.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most project setup skills give in 352 tokens

Counted across 1,553 of the 3,091 authors here whose files we hold, read 2026-09-06

  • Write the configuration filein 36 of 1553
  • Create the directory structurein 35 of 1553, across 33 files
  • Verify the setupin 31 of 1553, across 28 files
  • Run the setup scriptin 30 of 1553, across 29 files
  • Pre-determine the required sample sizein 29 of 1553, across 12 files
  • Check if the configuration already existsin 29 of 1553
  • Document every testin 26 of 1553, across 10 files
  • Start with a hypothesisin 26 of 1553, across 11 files
  • Ask one question at a timein 22 of 1553
  • Test a single variable per testin 21 of 1553, across 9 files
  • Read product marketing context before asking questionsin 19 of 1553, across 8 files
  • Do not peek and stop earlyin 18 of 1553, across 7 files

Said here and by no other author read

  • attempt the login and handle the two cases
  • tell the user to open a terminal and run tdq login
  • run tdq doctor via Bash to verify the token is live
  • ask the user which app to use if credentials are stored
  • run tdq login with the chosen app id
  • skip the picker immediately if arguments contain a uuid

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

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.