agentleFS
dennisonbertramdennisonbertram/claude-mac-guardian/skills/daily-health-report/SKILL.md

daily-health-report

Skill1 starsChanged 7 months agoMITView on GitHub

This skill should be used when the user asks to "generate daily report", "mac health report", "show me my status", "open health dashboard", "daily mac check", or mentions a unified macOS status report. Orchestrates every claude-mac-guardian skill, aggregates today's JSON, renders a dark-mode HTML dashboard, and opens it in the default browser.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Ensure the data and reports directories exist: mkdir -p ~/.mac-guardian/data ~/.mac-guardian/reports.

    line 16
  2. Distinctive:

    When running inside Claude Code, prefer invoking the skills via Claude's planner (one user-visible step per skill).

    line 29
  3. Distinctive:

    No other transformation is done — the template is self-contained (Tailwind via CDN, vanilla JS rendering).

    line 70
  4. Very specific:

    Do not call render-single.sh from this orchestrator.

    line 74
  5. Distinctive:

    Never re-run a skill that already has a JSON file for today unless the user explicitly asks to refresh.

    line 75
  6. Distinctive:

    Read-only. No system state is modified.

    line 79
  7. Distinctive:

    If a sibling skill prompts the user (none should by default), pass the prompt through verbatim.

    line 80

≈ “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

daily-health-report

Orchestrator skill. Invokes every sibling skill in the suite, aggregates their JSON output, and renders a unified dashboard HTML file from template.html.

When to invoke

Trigger on phrases like: "generate daily report", "mac health report", "show me my status", "open health dashboard", "daily mac check".

Procedure

  1. Ensure the data and reports directories exist: mkdir -p ~/.mac-guardian/data ~/.mac-guardian/reports.
  2. Invoke each collection skill, in this order, and wait for each to complete writing its JSON envelope. The list:

    • machine-security-check
    • malware-scan
    • network-diagnostics
    • wifi-debug
    • bluetooth-debug
    • disk-usage
    • performance-check

    When running inside Claude Code, prefer invoking the skills via Claude's planner (one user-visible step per skill). If a skill fails, continue with the remaining ones — a single skill's failure must not block the dashboard.

  3. Render the combined HTML report: bash ${CLAUDE_PLUGIN_ROOT}/scripts/render.sh. This reads all JSON files in ~/.mac-guardian/data/ dated today except daily-health-report-*.json, injects them into ${CLAUDE_PLUGIN_ROOT}/skills/daily-health-report/template.html, and writes ~/.mac-guardian/reports/report-<ISOdate>.html.
  4. Open the report: bash ${CLAUDE_PLUGIN_ROOT}/scripts/open-report.sh.
  5. Also write a tiny envelope for the orchestrator itself so it appears in history:

    {
      "skill": "daily-health-report",
      "timestamp": "<ISO8601 UTC>",
      "severity": "info",
      "summary": "Aggregated N skill results for <ISOdate>.",
      "findings": [],
      "raw": { "report_path": "<path to HTML>" }
    }

    Write to ~/.mac-guardian/data/daily-health-report-<ISOdate>.json.

  6. Report to the user:
    • report path
    • number of skills succeeded vs failed
    • overall severity (derived by the dashboard itself — you do not need to recompute)

Retention

render.sh prunes reports/ to the most recent 30 HTML files. No pruning for data/ (small JSON files; leave history intact).

Template substitution

render.sh uses awk to substitute these sentinels in template.html:

  • __MG_MACHINE__ — scutil --get ComputerName
  • __MG_GENERATED__ — ISO-8601 UTC timestamp
  • __MG_DATE__ — today's ISO date
  • __MG_PAYLOAD__ — JSON array of all skill envelopes

No other transformation is done — the template is self-contained (Tailwind via CDN, vanilla JS rendering).

Handoff

  • Do not call render-single.sh from this orchestrator.
  • Never re-run a skill that already has a JSON file for today unless the user explicitly asks to refresh.

Safety

  • Read-only. No system state is modified.
  • If a sibling skill prompts the user (none should by default), pass the prompt through verbatim.

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.