Stats
Actions
Tags
From maxexpresskit
Use when the agent is about to perform a risky operation (destructive shell, deploy, schema migration, money write, force-push). Reminds to record HITL approval and points at compliance/ templates.
How this skill is triggered — by the user, by Claude, or both
Slash command
/maxexpresskit:complianceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Auto-activates when the agent is about to run a classified risky op:
Auto-activates when the agent is about to run a classified risky op:
rm_rf — destructive shell deletiondeploy — kubectl apply, docker compose up, terraform apply, etc.schema_migration — file in migrations/money_write — INSERT/UPDATE/DELETE against money tablesforce_push_main — git push --force to main / mastercompliance/HITL_TEMPLATE.md. If not, prompt the user to run /mek-init.compliance/DECISION_LOG.md with date, operator, op category, and short rationale.Quiet-by-default. The hook will WARN. To escalate to a hard block, set mek.toml > [compliance.gates] > <op> = "block".
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub mbachaud/maxexpresskit --plugin maxexpresskit