Claude Skills by HenrikBrehm

Lints an existing user-supplied prompt for prompt-engineering defects and prompt-injection risks. Produces a diagnostic report with rule IDs, severity, line/column, quoted evidence, rationale, and optional JSON output. Does not rewrite prompts or impose prompt frameworks.

Secure-by-default builder for Claude Code. Use when scaffolding new projects or repos, writing or modifying authentication / authorization / session / password code, file uploads, SSRF-prone server-side fetches, secrets / env handling, deployment configs, Dockerfiles or docker-compose, GitHub Actions / CI workflows, dependency installs (`package.json`, `requirements.txt`, `Cargo.toml`, etc.), or pre-commit / pre-push reviews ("about to commit", "ready to push", "going public"). Skip for routi...