AGENT SKILL

metrics-digest

Builds the Monday metrics email from the analytics CLI — pulls signups/activation/churn, compares to the prior week, flags moves over 10%. Use when asked to build, generate, or send the metrics digest or Monday metrics email.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 1
Forks
0

01 前言 Front Matter

name
metrics-digest
description
Builds the Monday metrics email from the analytics CLI — pulls signups/activation/churn, compares to the prior week, flags moves over 10%. Use when asked to build, generate, or send the metrics digest or Monday metrics email.

02 资源文件 2

03 SKILL.md 正文

Produces the fixed-format Monday email from an4. Follow the four steps in order; each one's output feeds the next.

1. Pull both weeks

Run:

an4 query --metric signups,activation,churn --last 7d --json

Then run the same query shifted back one week (via an4's date-range flags) to get the prior-week baseline. Done when you hold two JSON payloads — current and prior — each nominally covering signups, activation, and churn.

2. Reconcile against the three metrics

For each of signups, activation, churn, look it up in both payloads:

  • Present in both — compute pct_change = (current - prior) / prior. Flag it if |pct_change| > 10%.
  • Missing from either payload — do not drop the row and do not compute a delta for it. Carry it into rendering as an explicit gap (see step 4). It cannot be flagged — there is nothing to compare.

Done when every one of the three metrics is classified as computed-and-flagged, computed-and-not-flagged, or missing.

3. Assign sections

Fixed mapping, not inferred from the data:

  • Growth — signups
  • Engagement — activation, churn
  • Flags — every metric flagged in step 2, restated with prior value, current value, and signed percent change

4. Render the template

Plain text, no markdown, exactly these sections, in this order:

Subject: Metrics week of <date>

Growth
signups: <value> (<+/-pct>% vs prior week)

Engagement
activation: <value> (<+/-pct>% vs prior week)
churn: <value> (<+/-pct>% vs prior week)

Flags
<metric> moved <+/-pct>%: <prior value> -> <current value>

For a missing metric, write its line as <metric>: no data returned by CLI in its assigned Growth/Engagement section — never omit the row.

If no metric was flagged, the Flags section reads exactly None over ±10%.

<date> is the first day of the current 7-day window, formatted YYYY-MM-DD.

04 同仓库更多 Skills

StartupBros-com
StartupBros-com/hov-stack

review-adversarial-first

Operator-invoked adversarial review: 3 refute-by-default lenses plus a deterministic judge against a PR, branch, or path, then a decision on whether /ce-code-review's topic fan-out runs. Off the default merge path since the 2026-10-17 merge-and-end ruling; run only when asked for by name.

★ 1
StartupBros-com
StartupBros-com/hov-stack

memory-mine

Run one deterministic, budgeted directed-capture batch for an explicit Claude Code project store. Use manual workspace mode only when cross-agent cass sessions are intentionally in scope.

★ 1
StartupBros-com
StartupBros-com/hov-stack

papers

Search preprints from arXiv, bioRxiv, and medRxiv without API keys. Supports search, lookup, extraction, citations, enrichment, and paper downloads that bundle PDFs plus linked GitHub code.

★ 1
StartupBros-com
StartupBros-com/hov-stack

papers

Search preprints from arXiv, bioRxiv, and medRxiv without API keys. Supports search, lookup, extraction, citations, enrichment, and paper downloads that bundle PDFs plus linked GitHub code.

★ 1
StartupBros-com
StartupBros-com/hov-stack

wsl-cdp

Drive the user's real, logged-in Windows browser (Chrome, Edge, or Brave) from a Claude Code session running inside WSL2, over the Chrome DevTools Protocol - read authenticated dashboards and consoles, take real screenshots, open and read pages with the user's sessions. Use when a task needs the user's existing web logins and the session runs in WSL2, where the Claude in Chrome extension cannot work. Not for native-Windows or macOS Claude Code (use the official Claude in Chrome extension), not for anonymous scraping or CI (use headless Playwright inside WSL), not for getting past login walls (those are handed to the human).

★ 1
StartupBros-com
StartupBros-com/hov-stack

token-eater

[BETA] Spend a subscription's idle, about-to-expire credits on safe, machine-verified cleanup. You pick the service (Grok / Codex / Claude) and a token-heavy maintenance skill (de-monolithize, de-slop, simplify, dead-code); that service runs the whole skill -> gate -> self-review -> draft-PR loop on its own credits, in an isolated worktree. token-eater verifies the gate and never merges. Manual invocation only during beta.

★ 1