Metrics

Define the metrics for "$ARGUMENTS" so that everyone who computes one gets the same number.

Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"analytics-metrics","workflow":"analytics","phase":2,"project":"<project>","event":"skipped","artifact":"02-metrics.md","note":"<reason or \"none given\">"}.

Compute with code. Perform every calculation (totals, balances, ratios, variances, projections) with a script — Bash, Python or a spreadsheet formula written to a file — and include the computation alongside the result. Never do arithmetic mentally.

Prerequisites

Part of a workflow. This skill is phase 2 (Metrics) of the Decision Analytics Cycle workflow (analytics); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or analytics when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.

Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"analytics-metrics","workflow":"analytics","phase":2,"project":"<project>","event":"refused","artifact":"02-metrics.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"analytics-metrics","workflow":"analytics","phase":2,"project":"<project>","event":"started","artifact":"02-metrics.md","note":""}.

Read .singularskills/analytics/<project>/01-questions.md for the decisions and the priority questions.

Process

1. Find metrics already defined: read .singularskills/support/<project>/ and .singularskills/finance/<project>/ artifacts and the user's existing reports. A metric defined there is referenced by its name and file, never redefined; note any conflicting definitions of the same name.

2. Build the metric tree as references/metric-definitions.md describes: for each decision area, one primary metric, the input metrics that drive it, and the guardrails that must not get worse. Keep the tree to about a dozen metrics.

3. Define each metric with every field of the template in references/metric-definitions.md: name, question, formula (in words and pseudo-SQL), unit and grain, inclusions and exclusions, window, segments, source, owner and traps. Where a field is unknown, write <unknown: …> and list it under Open questions.

4. Check every question is covered: each priority question from 01-questions.md maps to at least one metric, and each metric answers at least one question. Drop metrics that answer none.

5. Name the traps that apply to each metric from the list in references/metric-definitions.md: moving denominators, averages of averages, Simpson's paradox, survivorship, time zones and late data, definition drift.

6. Write the artifact to .singularskills/analytics/<project>/02-metrics.md with sections:

   • Metric tree — primary, inputs and guardrails per decision area
   • Definitions — one block per metric, every template field
   • Referenced metrics — metrics defined elsewhere, with their file
   • Coverage — question → metric mapping

Output

The metric definitions written to .singularskills/analytics/<project>/02-metrics.md. Present a summary to the user highlighting:

• The primary metric for each decision area
• The guardrails
• Every <unknown: …> field and conflicting definition

Record the run. After you have written the artifact, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"analytics-metrics","workflow":"analytics","phase":2,"project":"<project>","event":"finished","artifact":"02-metrics.md","note":""}.

Open the artifact with this frontmatter (agent is the agent you run in, or unknown; gate is passed when the gate ran clean and skipped under --skip-checks):

---
skill: analytics-metrics
workflow: analytics
phase: 2
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---

End the artifact with ## Decisions and ## Open questions, in this shape:

## Decisions
- <what was chosen> — <why> — <what was rejected>

## Open questions
- <what the next phase or a reviewer must settle>