agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/ops-status-report/SKILL.md

ops-status-report

Skill3 starsChanged 6 months agoMITView on GitHub

Generate a recurring status snapshot of a folder-based workspace (clients, pipeline files, recent activity, command health checks) ending in an Attention Needed section that surfaces what is stalled or overdue. Read-only except for the report file. Use when the user says "status report", "weekly report", "what's going on in this workspace", or "ops snapshot".

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Look for an ops-report.config.md file in the project root.

    line 12
  2. Distinctive:

    Run every configured section.

    line 28
  3. Distinctive:

    If everything is genuinely fine, Attention Needed is one line saying so.

    line 49
  4. Distinctive:

    Read-only except the report file itself.

    line 57
  5. Distinctive:

    No em dashes in any output.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Step 3: Deliver

Show the Attention Needed section in chat with the report path. If the user wants this on a schedule, suggest their scheduler of choice run the skill weekly.

Rules

  • Read-only except the report file itself. The report never fixes what it finds; it names it.
  • Numbers come from counting, not estimating. If something could not be counted, the report says so.
  • No em dashes in any output.

Output

A dated ops report file plus the Attention Needed highlights in chat.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.