ops-status-report

Ops Status Report

A workspace full of markdown and folders holds an honest status report nobody compiles. This skill compiles it: what is active, what is overdue, what went quiet. The Attention Needed section is the whole point; everything else is supporting evidence.

Step 0: Load the report config (once)

Look for an ops-report.config.md file in the project root. If it does not exist, interview the user about what "status" means in their workspace, then offer to save it. The config defines a list of sections, each one of these shapes:

FOLDER_SCAN     A folder where each subfolder or file is a tracked item,
                plus which line or frontmatter key holds its status
FRONTMATTER_TALLY  A folder of markdown files, which keys to tally
                (e.g. status), and which date key flags overdue items
RECENT_ACTIVITY A folder to check for files created or modified in the
                last N days
COMMAND         A read-only command whose output summarizes a tool
                (e.g. a CLI status command), and what failure means
REPORTS_FOLDER  Where finished reports are saved

Step 1: Collect (read-only)

Run every configured section. Rules of collection:

• Missing files or folders are findings ("item X has no status file"), not errors to silently skip.
• Dates that cannot be parsed are listed as-is, never guessed.
• A COMMAND that fails gets one line with the reason ("not run: missing .env"), and the report continues.

Step 2: Write the report

Save to REPORTS_FOLDER/ops-report-<YYYY-MM-DD>.md:

# Ops Report: <date>

## <One section per config entry>
Tables for tallies, lists for activity, short summaries for commands.

## Attention needed
Three to five bullets maximum, ordered by cost of ignoring them:
overdue items first, then untracked items, then things that went quiet.

If everything is genuinely fine, Attention Needed is one line saying so. Invented urgency kills trust in the report faster than a missed item.