skills/being-careful/SKILL.md
Activates safety hooks that block dangerous shell commands for the rest of the session — rm -rf, DROP TABLE, force-push, hard reset, kubectl delete, and other destructive operations. Use when touching production, working with sensitive data, or doing risky operations where an accidental destructive command could cause harm
npx skillsauth add riccardogrin/skills being-carefulInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Activates session-scoped safety hooks that block dangerous shell commands. Use this when working near production systems, sensitive data, or doing anything where a misfire could cause real damage.
| Pattern | Why | Safe Alternative |
|---------|-----|-----------------|
| rm -rf, rm -f, rm --force | Irreversible file deletion | trash, targeted rm on specific files |
| DROP TABLE, TRUNCATE, bulk DELETE FROM | Destructive SQL | Review and run manually |
| git push --force, git push -f | Overwrites remote history | git push --force-with-lease |
| git reset --hard | Discards uncommitted work | git stash then reset |
| git clean -f | Deletes untracked files | git stash -u |
| git checkout -- . | Discards all working changes | Stash or commit first |
| git branch -D | Force-deletes branch | git branch -d (safe delete) |
| kubectl delete, kubectl --force | Destroys cluster resources | Review and run manually |
| docker system/volume/container prune | Removes all stopped containers/volumes | Run manually with filters |
The skill registers a PreToolUse hook on Bash that inspects each command before execution. If a dangerous pattern is matched, the command is blocked (exit code 2) and Claude sees the reason in stderr. Claude can then suggest a safer alternative.
The hooks are session-scoped — they activate when you invoke /being-careful and last until the session ends.
They do not affect other sessions or persist between sessions.
git push --force-with-lease is intentionally allowed — it's the safe alternative to force-push.rm without -rf/-f flags — targeted file removal is still permitted.drop table and DROP TABLE are both caught.data-ai
Downloads YouTube videos, transcribes audio via OpenAI Whisper, and produces summaries stored locally. Covers yt-dlp download, audio extraction, transcription, caching, and summarization. Use when a YouTube link is shared and the user wants a transcript or summary
development
Runs an adversarial code review loop that spawns independent reviewer and fixer subagents, iterating until only nitpicks remain. Scores findings by confidence, fixes real issues, and re-reviews with fresh eyes — all internal, no GitHub comments. Use when asked to review code, self-review, adversarial review, or polish code before pushing
development
Creates implementation-ready plans through discovery interviews, external research, and codebase analysis. Covers requirements, competitor research, architecture decisions, and change sequencing. Use when planning features, roadmaps, specs, or any work that needs discovery before coding
development
Generates an autonomous game design loop that iteratively expands a game concept into a comprehensive vision and implementation plan across multiple sessions. Covers mechanic exploration, system design, competitor research, and plan generation. Use when developing a game idea from seed concept to full implementation plan