agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/finops-toolkit/.claude/skills/support-report/SKILL.md

support-report

Skill623 starsChanged 2 months agoMITView on GitHub

Generate the FinOps toolkit support status report (customers waiting on us, triage queue, S0/S1, customer replies since the last report) and a short draft for the contributor sync Teams chat. Use when asked for a support status, support report, or the scheduled Sun/Tue support check.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Run the metrics script from the repo root (needs gh signed in):

    line 12
  2. Very specific:

    Add judgment the script can't (keep each to one line.

    line 21
  3. Very specific:

    Write the Teams draft (max 6 lines, plain text, no tables) to ~/.claude/ftk-reports/support-YYYY-MM-DD.teams.txt:

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

FTK support status report

Produce a TLDR support status for maintainers. Read-only on GitHub: never comment, label, or post there. Teams posting goes only through post-teams.mjs.

Steps

  1. Run the metrics script from the repo root (needs gh signed in):

    node .claude/skills/support-report/report.mjs
    • It compares against the last saved report in ~/.claude/ftk-reports/ (or the last 7 days if none) and saves support-YYYY-MM-DD.md and .json there.
    • "Waiting on us" means a non-maintainer spoke last, the thread isn't an answered discussion, and it isn't a maintainer-filed issue with no outside reply. Feature requests are counted separately.
  2. Add judgment the script can't (keep each to one line; link every issue, PR, and discussion as [#N](https://github.com/microsoft/finops-toolkit/issues/N)):
    • Needs a maintainer: up to 3 threads where a reply needs a decision, not just an answer. Say what the decision is.
    • v15/release risk: any waiting S0/S1 or data-loss thread. Note it for 🧰 Release Manager.
    • Wins: threads resolved or answered since the last report (optional, one line).

  3. Write the Teams draft (max 6 lines, plain text, no tables) to ~/.claude/ftk-reports/support-YYYY-MM-DD.teams.txt:

    🤖 [AI] FTK support · <date>
<N> customers waiting on us (<issues> issues, <discussions> discussions) · oldest <X>d · triage <N>
Since <last date>: <N> team replies, <N> customer replies
Needs a maintainer: #A (<decision>), #B (<decision>)
Release risk: <#N or "none">
Details: <link to the support sweep page, if one exists>
  4. Reply to whoever asked with the TLDR line plus the "Needs a maintainer" line. Nothing else.

Rules

  • Accuracy first: only state counts the script produced; never guess a thread's state.
  • Post the Teams draft only through node .claude/skills/support-report/post-teams.mjs, and only when ~/.claude/ftk-reports/teams-webhook.url exists (a maintainer creates it; that is the approval). If it doesn't exist, leave the draft for a manual paste. Never post the same draft twice (the script refuses). See teams-posting.md.
  • Public text starts with "🤖 [AI]". Plain language, sentence case.

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.

Check your setup, free