vakt

Audits local credential setup for security compliance and produces a report. Use this skill when the user needs to: - Check whether their credentials are properly stored and not leaking - Validate credential rotation age against their policy - Scan shell history, dotfiles, and git repos for exposed credentials - Check file permissions on sensitive config files - Get a compliance score before deploying credentials with export-credentials Reads ~/.agents/credential-profile.json (written by credential-best-practices). Falls back to generic checks if profile is missing. Writes ~/.agents/audit-report.json consumed by export-credentials. Works with Claude, OpenCode, Codex, Gemini, and any AI with Bash access.

Interactive wizard for setting up secure local credential management. Use this skill when the user needs to: - Learn how to store credentials securely on their machine - Set up macOS Keychain, pass, or environment variable credential stores - Establish credential rotation policies and naming conventions - Understand how to prevent credentials from leaking into shell history, dotfiles, git repos, or AI tool logs - Create a credential profile for use with audit-credentials and export-credentials Writes ~/.agents/credential-profile.json when setup is complete. Works with Claude, OpenCode, Codex, Gemini, and any AI with Bash access.

Securely export credentials from local credential stores without exposing them to the AI. Use this skill when the user needs to: - Add credentials to GitHub Secrets or other repository secrets - Deploy credentials to cloud development environments - Manage credentials across multiple repositories or services - Create secure configuration files without logging secrets The skill reads credentials from the user's local credential store (macOS Keychain, Linux pass, Windows Credential Manager, or environment), auto-detects what's available, and generates scripts to deploy them securely. Secrets never enter the AI context — this is a zero-trust approach where credentials are read and used only locally.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.