Tighten pack metadata so installs match the documented audit scope

The repo had drift between the public summary, the installed prompt defaults,
and the actual skill contracts. This update widens the default prompt metadata
to match the skill specs, sharpens the README summary, and adds ignore rules so
local install smoke tests and OMX state stop dirtying the checkout.

Constraint: Keep the repo small and avoid reintroducing deleted eval or verification scaffolding
Rejected: Add a new manifest or restore scripts/evals | extra repo surface without solving the immediate prompt-metadata drift
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep README copy and agents/openai.yaml prompts aligned with the skill contracts whenever the skill surfaces change
Tested: git check-ignore for .omx and generated hidden */skills/ paths; npx skills add https://github.com/jasperdevs/computer-doctor --list --full-depth; isolated temp install of --all; architect, security, and code-review validation passes
Not-tested: Clearing stale external skills.sh cache for the historical virus-scan page

Author: jasperdevs

.gitignore

@@ -0,0 +1,3 @@
+.omx/
+skills-lock.json
+/.*/skills/

README.md

@@ -1,7 +1,7 @@
 <div align="center">
   <img src="./computerdoctor-v2.png" alt="computer-doctor graphic" width="220" />
   <h1>computer-doctor</h1>
-  <p>A small skill pack for auditing machine health, security posture, update hygiene, and developer-tool setup.</p>
+  <p>A small skill pack for auditing machine health across security, startup, performance, storage, software quality, updates, and developer-tool setup.</p>
 </div>
 
 ## Install

skills/computer-doctor/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
   display_name: "Computer Doctor"
   short_description: "Run a broad machine audit across security, startup, performance, storage, software, updates, and developer tools"
-  default_prompt: "Use $computer-doctor to ask for Audit mode or YOLO mode first, then audit this machine as a working environment and report the highest-impact findings."
+  default_prompt: "Use $computer-doctor to ask for Audit mode or YOLO mode first, then audit this machine across security posture, startup behavior, performance, storage, software quality, updates, and developer tooling, and report the highest-impact findings."

skills/security-scan/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
   display_name: "Security Scan"
   short_description: "Check malware signals, suspicious persistence, protection coverage, and obvious security issues"
-  default_prompt: "Use $security-scan to ask for Audit mode or YOLO mode first, then inspect antivirus coverage, suspicious processes, persistence, and obvious malware signals."
+  default_prompt: "Use $security-scan to ask for Audit mode or YOLO mode first, then inspect antivirus coverage, firewall status, suspicious processes, persistence, risky permissions, and obvious malware or unwanted-software signals."

skills/update-audit/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
   display_name: "Update Audit"
   short_description: "Review operating-system, app, driver, runtime, package-manager, and core-tool updates"
-  default_prompt: "Use $update-audit to ask for Audit mode or YOLO mode first, then inspect operating system, apps, drivers, runtimes, package managers, and core tools for outdated versions or upgrade opportunities."
+  default_prompt: "Use $update-audit to ask for Audit mode or YOLO mode first, then inspect operating system, apps, drivers, runtimes, package managers, and core tools for outdated versions, weak choices, or obvious upgrade and replacement opportunities."