Skip to content

cgallic/kai-cmo-harness / legacy/kai-upgrade

kai-upgrade

Verified

Update kai-marketing to the latest version. Pulls latest code, re-registers skills, shows what changed. Does NOT modify content state or MARKETING.md.

/kai-upgrade — Self-Updater

Update kai-marketing to the latest version. Safe — only updates skill definitions, knowledge files, and bin/ tools. Never touches your content state, config, or MARKETING.md.

The Skill

Step 1: Detect Install Location

Find the kai-marketing root directory:

KAI_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
echo "Install location: $KAI_ROOT"

Check if it's a git repo:

cd "$KAI_ROOT" && git rev-parse --is-inside-work-tree 2>/dev/null

If not a git repo: "This install was copied, not cloned. Re-install with: git clone https://github.com/cgallic/kai-marketing.git ~/.claude/skills/kai-marketing"

Step 2: Check Current Version

cat "$KAI_ROOT/VERSION"

Step 3: Pull Latest

cd "$KAI_ROOT" && git pull origin main 2>&1

If pull fails (network, conflicts): Show the error and suggest manual resolution.

Step 4: Show What Changed

OLD_VERSION=$(git show HEAD~1:VERSION 2>/dev/null || echo "unknown")
NEW_VERSION=$(cat VERSION)
echo "Updated: v${OLD_VERSION} → v${NEW_VERSION}"

Show recent changelog entries:

git log --oneline -10

If a CHANGELOG.md exists, show entries between old and new version.

Step 5: Re-Register Skills

cd "$KAI_ROOT" && ./setup

Step 6: Confirm

kai-marketing upgraded: v{old} → v{new}
  Skills re-registered
  Knowledge base updated
  Content state untouched
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall