agentleFS
Pdiamondz1Pdiamondz1/hma_project_foundation/.claude/skills/maintain-app/SKILL.md

maintain-app

Skill1 starsChanged 5 months agoNo licenceView on GitHub

Use when someone asks to "maintain my app", "keep my app healthy", "watch my app for security/bugs post-launch", "set up scheduled maintenance", or says "/maintain-app". The "operate & maintain" step (path-to-production rung 7) for an already-shipped app/. On a schedule it re-runs your quality signals (npm audit / the test suite / an audit-app re-run) into ONE plain-language health report, delegates dependency/CVE patching to Dependabot/Renovate (with a ~7-day cooldown — surfaced, never auto-bumped), and opens a gated SAFE-PR only for a narrow reversible fix class (lint/format/mechanical-a11y/dead-code/doc-drift) — never for a dependency bump. Report-first: the PR is the exception, not the deliverable. It NEVER merges, deploys, publishes, or enters keys — a guard hook (plus your branch protection) enforces that. Scaffolds a local Routine (offline sandbox) + a ready-to-enable keyed CI workflow. Attended setup (one confirm gate); its own schedule — never in maintenance-loop, never in autopilot. Requires a built app/. Re-runnable. Zero-argument safe.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

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.