Stats
Actions
Tags
From karmaiq-impact
Service-level blast radius. What breaks if this service goes down. Manual slash invocation when the user wants to know the cost of a deploy, restart, or removal.
How this skill is triggered — by the user, by Claude, or both
Slash command
/karmaiq-impact:service <service-name><service-name>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
The user wants the blast radius if service `$ARGUMENTS` were to fail.
$ARGUMENTSThe user wants the blast radius if service $ARGUMENTS were to fail.
${CLAUDE_PLUGIN_DATA}/../karmaiq-core/domain.txt. If unset → stop.search_catalog(catalog="graph", query="$ARGUMENTS") → resolve to node_id (use top match if unambiguous; else list options and ask).simulate_failure(node_id="<resolved>", detail="summary", failure_type="down", depth=5) — blast count by depth and type.simulate_failure(node_id="<resolved>", detail="full", failure_type="down", depth=5, top_k=20) — ranked affected nodes by QPM lost.## Service: <name>
**Blast summary**: <X services affected, Y interfaces, Z total QPM lost>
**Top affected interfaces by QPM lost**
| interface | QPM lost | depth |
|---|---|---|
<top 10>
**Amplification flags** (edges with > 2× amplification)
<list any, or "none"; one upstream request causing >2 downstream calls = cascading-load risk>
The resolved node_id is the exact key. Echo it as-is; do not reformat.
npx claudepluginhub codekarma-tech-public/codekarma-mcp-plugin --plugin karmaiq-impactCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.