Stats
Actions
Tags
Cross-entity karmaIQ regression diff between two services or APIs. Manual slash invocation. Returns the same four-verdict output as the canary gate.
How this skill is triggered — by the user, by Claude, or both
Slash command
/karmaiq-promotion-gate:diff <service-a-or-api> <service-b-or-api><service-a-or-api> <service-b-or-api>This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
`$ARGUMENTS` should contain two tokens: side A and side B. Each may be:
$ARGUMENTS$ARGUMENTS should contain two tokens: side A and side B. Each may be:
If only one token, ask for the missing side.
Delegate to the karmaiq-canary-gate subagent via the Task tool. Pass this prompt:
Run a cross-entity regression_diff between side A =
$0and side B =$1over the last 15 minutes. Pass both names raw — do NOT pre-resolve. Return verdict, top drivers, recommendation, and the pipeline JSON block.
If the user supplied a service-only on both sides (and they're different services), warn that whole-service cross-diff is blocked server-side: "Whole-service cross-diff is not supported. Supply at least one api/interface_id on either side, or use /karmaiq-promotion-gate:canary <svc> for a single-service canary verdict."
When the subagent returns, present output verbatim. Verdict is load-bearing — do not paraphrase.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
npx claudepluginhub codekarma-tech-public/codekarma-mcp-plugin --plugin karmaiq-promotion-gate