菜单
Safety guardrails — blocks destructive commands (rm -rf, DROP TABLE, force-push, git reset --hard) and optionally restricts file edits to a specific directory. Use when working on critical systems or when you want extra protection.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build a regression + eval harness for AI-written code and AI features. Generates characterization tests that lock current behavior before a refactor, scaffolds a Promptfoo eval suite for chatbots/RAG/classifiers, and wires it into the ship-gate. Use when the user wants evals, regression tests for AI code, to stop AI features drifting, or to test an LLM feature.
Run security audit — dependency vulnerabilities, secret scanning, OWASP pattern detection, HTTP headers. Use when user wants to harden their project.
Accessibility audit + auto-fix (WCAG 2.2 A/AA). Scans built/static HTML for screen-reader, keyboard, and structure failures, fixes the deterministic ones, and escalates to a rendered scan for contrast and focus. Use when the user wants to check or improve accessibility, fix WCAG issues, or pass an a11y review.
Turn the /ship scorecard into a blocking, config-as-code quality gate. Sets per-category score thresholds, hard-fails on leaked secrets or critical findings, and wires the gate into a pre-push hook and CI so nothing below the bar merges. Use when the user wants a merge gate, CI quality gate, pre-push check, or to enforce ship-readiness.
Post-deploy canary monitoring — checks site health, detects regressions, monitors for errors after deployment. Use after deploying to verify production is healthy.
Code review with principal-engineer-level depth. Reviews for correctness, performance, security, maintainability, and architecture. Use when completing tasks, reviewing PRs, or before merging.
| name | guard |
| description | Safety guardrails — blocks destructive commands (rm -rf, DROP TABLE, force-push, git reset --hard) and optionally restricts file edits to a specific directory. Use when working on critical systems or when you want extra protection. |
| argument-hint | <directory-to-protect> |
| allowed-tools | Bash, Read |
Guard protects you from accidental destructive actions by intercepting dangerous commands before they execute. It uses Claude Code's PreToolUse hooks to catch risky patterns in real-time.
Announce at start: "I'm activating Guard — destructive commands will be blocked until you explicitly approve them."
rm -rf / rm -r on important directoriesDROP TABLE / DROP DATABASE / TRUNCATEgit push --force / git push -f (to main/master)git reset --hardgit checkout . / git restore . (discard all changes)git clean -f / git clean -fdgit branch -D (force delete branch)kubectl delete (Kubernetes resource deletion)docker system prune / docker volume rm:> file / > file (truncate files)When the user specifies a directory to freeze to, Guard blocks edits outside that directory:
User: "Only edit files in src/api/"
→ Guard blocks Edit/Write calls to any path not under src/api/
Guard installs PreToolUse hooks that run BEFORE Claude executes Bash, Edit, or Write tools:
The hooks are defined in this skill's configuration and activate when the skill is loaded.
Just invoke /guard — destructive command blocking is immediate.
Tell Claude which directory to restrict edits to:
"Only edit files in packages/api/"
"Freeze edits to src/components/"
Guard will write the freeze path to .ultraship/guard-freeze.txt and enforce it on all Edit/Write operations.
"Unfreeze" or "Remove edit restrictions"
If Guard blocks something you actually need to run, explicitly confirm:
"Yes, I want to force-push to main"
"Confirmed: drop the users table"
Guard will allow explicitly confirmed destructive actions.
/investigate — Guard pairs well with investigation. No accidental fixes while diagnosing./deploy — Guard prevents accidental force-pushes during deployment./rescue — During incidents, Guard ensures rollback commands are deliberate.