Dashboards
Specify the dashboards for "$ARGUMENTS": few tiles, each answering a question someone asked.
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-dashboards","workflow":"analytics","phase":5,"project":"<project>","event":"skipped","artifact":"05-dashboards.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 5 (Dashboards) 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-dashboards","workflow":"analytics","phase":5,"project":"<project>","event":"refused","artifact":"05-dashboards.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-dashboards","workflow":"analytics","phase":5,"project":"<project>","event":"started","artifact":"05-dashboards.md","note":""}.
Read .singularskills/analytics/<project>/02-metrics.md for the metric names and definitions and .singularskills/analytics/<project>/03-data.md for which metrics are fit to show. Read .singularskills/analytics/<project>/01-questions.md for the questions and audiences when it exists.
Process
Name the audiences: who looks at each dashboard (the decision-makers in
01-questions.md, the team, leadership), how often, and what they do after looking.Choose the tiles per audience: for each, the question it answers (from
01-questions.md), the metric by its02-metrics.mdname, and why this audience needs it. Cut any tile that answers no question, and any metric03-data.mdmarks not usable.Specify each tile:
- Chart — a line for a trend over time, a bar for comparing categories, a single number with its comparison for a headline; no pie charts for more than three parts
- Comparison — target, previous period or same period last year
- Filters and segments — only those in the metric's definition
- Refresh — how often, and the latest complete period it shows
- Alert — a threshold that should make someone act, and who, where one makes sense
- Query — optionally, the SQL behind the tile in the user's dialect, following the metric's definition
Order each dashboard: the primary metric first, inputs next, guardrails last; at most about eight tiles per dashboard.
Write the artifact to
.singularskills/analytics/<project>/05-dashboards.mdwith one section per dashboard: Audience, Tiles (a table: question, metric, chart, comparison, filters, refresh, alert) and Queries, and a final Cut section listing tiles considered and cut, with why.
Output
The dashboard specs written to .singularskills/analytics/<project>/05-dashboards.md. Present a summary to the user highlighting:
- The dashboards and their audiences
- The alerts and who acts on them
- The tiles cut, and why
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-dashboards","workflow":"analytics","phase":5,"project":"<project>","event":"finished","artifact":"05-dashboards.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-dashboards
workflow: analytics
phase: 5
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>