agentsclimarketplace

Report

Skill agenkin/telemetrydeck-analytics/skills/report

Generate a short markdown analytics report answering a specific product question. Pass the question as arguments.From its SKILL.md

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

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 5 commands, including `tdq dau` and 4 more.

SKILL.md

1.9 KB, 464 tokens by cl100k_base, as published. Nobody here has run it

Report

Write a compact markdown analytics report that answers the user's question in $ARGUMENTS. This skill is the high-level wrapper: pick the right sub-query (recipe or raw TQL), run it, and turn the numbers into a narrative.

Process

  1. Parse the question in $ARGUMENTS. Identify: metric (count vs. users), dimension (if any), window, comparison target.
  2. Pick the command:
    • DAU/MAU trend → tdq dau / tdq mau
    • Breakdown by one dimension → tdq groupby <dim>
    • Which events fire → tdq events
    • Funnel / retention / multi-dim groupby / derived metric → write raw TQL and run via tdq query - (consult skills/analytics/tql/index.md for syntax).
  3. Run it — use the Bash tool. Capture the table output.
  4. Write the report using this structure:
## <question restated as a header>

**Top-line:** <one sentence with the key number and window>

**Method:** `<the exact `tdq …` invocation you ran>`

**Result:**
<markdown table — paste the CLI output directly>

**Interpretation:** <1–3 sentences: what the numbers mean, any trend or outlier, compared-to-what>

**Caveats:** Opt-in cohort only (TelemetryDeck samples self-selected users). <add channel skew / partial-period / small-sample notes if applicable>
  1. Where to save: inline in the conversation by default. If the user asks for a file, ask them where to save it; write to the absolute path they give. Suggest ~/Documents/TelemetryDeck/YYYY-MM-DD-<slug>.md. Never create new top-level folders in the current working directory.

Defaults

  • Window: last 30 days unless the question implies otherwise.
  • Format: table (markdown-ready).
  • Always include the opt-in-cohort caveat.
  • For "trending" / "growing" / "vs. last period" phrasings, add --compare prior-period.

What ships with it

Read from the repository

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

Gives 0 of the 12 instructions most docs writing skills give in 464 tokens

Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06

  • Use third-person for skill descriptionsin 54 of 1951, across 35 files
  • Start descriptions with Use whenin 43 of 1951, across 29 files
  • Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
  • Use active voicein 40 of 1951, across 36 files
  • Map file responsibilities before defining tasksin 36 of 1951, across 29 files
  • Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
  • Ask one question at a timein 35 of 1951
  • Offer execution options after saving the planin 33 of 1951, across 24 files
  • Include complete code in every stepin 33 of 1951, across 27 files
  • Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
  • Announce the skill usage at the startin 30 of 1951
  • Verify agent compliance after adding the skillin 29 of 1951, across 17 files

Said here and by no other author read

  • Parse the user question for metrics and dimensions
  • Select the appropriate tdq command
  • Capture the table output
  • Include the opt-in cohort caveat in every report
  • Add compare prior-period for trend questions
  • Ask user for path if file output requested

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.