analytics-readout

Write the decision readout — the answer to each question in one line, the recommendation, the confidence and why, what would change it, and what to watch — for the decision-maker named at the start. U

SKILL.md

GitHub

Readout

Turn the analysis for "$ARGUMENTS" into a memo the decision-maker can act on in five minutes.

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-readout","workflow":"analytics","phase":6,"project":"<project>","event":"skipped","artifact":"06-readout.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 6 (Readout) 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-readout","workflow":"analytics","phase":6,"project":"<project>","event":"refused","artifact":"06-readout.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-readout","workflow":"analytics","phase":6,"project":"<project>","event":"started","artifact":"06-readout.md","note":""}.

Read .singularskills/analytics/<project>/04-analysis.md for the answers and their limits. Read .singularskills/analytics/<project>/01-questions.md for the decisions, their decision-makers and deadlines. Read .singularskills/analytics/<project>/02-metrics.md and .singularskills/analytics/<project>/03-data.md when they exist.

Process

  1. Write for the decision-maker named in 01-questions.md, in their terms, one memo per decision.

  2. Lead with the recommendation: the option you recommend and the one-sentence reason.

  3. Give the answers: each question's answer in one line, with its uncertainty, taken from 04-analysis.md without changing a number.

  4. Rate the confidence as high, medium or low, with why: the size of the effect against its uncertainty, the data caveats from 03-data.md and 04-analysis.md, and whether the answer is observational.

  5. Say what would change the recommendation: the result, the data or the event that would make you recommend otherwise.

  6. Say what to watch after the decision: the metrics (by their 02-metrics.md names) and the threshold that would mean the decision is not working.

  7. Write the artifact to .singularskills/analytics/<project>/06-readout.md with sections, per decision:

    • Recommendation
    • Answers
    • Confidence
    • What would change this
    • What to watch

Output

The readout written to .singularskills/analytics/<project>/06-readout.md. Present the recommendation and confidence for each decision, and what to watch.

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-readout","workflow":"analytics","phase":6,"project":"<project>","event":"finished","artifact":"06-readout.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-readout
workflow: analytics
phase: 6
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>