From my-claude-skills
**STOP AND VERIFY**: Before running any command or tool that results in irreversible data loss, you MUST obtain explicit user consent. When in doubt, ask. It is better to wait for confirmation than to accidentally delete production data or critical project assets. Use this for: - SQL: DROP TABLE/VIEW/SCHEMA/DATABASE, TRUNCATE, or broad DELETE (missing WHERE or using 1=1). - Cloud Storage: gsutil rm or gcloud storage rm targeting production data or critical buckets. - Infrastructure: gcloud projects delete, deleting Spanner/BigQuery/Dataproc resources, deleting secrets, or KMS key destruction. NOT for routine read-only queries, SELECT statements, or reversible operations.
How this skill is triggered — by the user, by Claude, or both
Slash command
/my-claude-skills:accidental-data-loss-preventionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> [!CAUTION]
[!CAUTION]
STOP AND VERIFY: Before running any command or tool that results in irreversible data loss, you MUST obtain explicit user consent.
Symptom: Treating all DELETE operations as safe Problem: Assuming row-level DELETEs with a WHERE clause are always safe to auto-run. Solution: Always verify the WHERE clause scope. If the delete affects more than a targeted set of rows, surface it for explicit confirmation.
Symptom: Skipping confirmation for TRUNCATE Problem: TRUNCATE behaves like DROP+CREATE — it bypasses row-level logging and cannot be rolled back in some DB engines. Solution: Always require explicit user consent before running TRUNCATE, regardless of context.
npx claudepluginhub etaccad/my-claude-skills --plugin my-claude-skillsGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.