Governance skills for AI coding agents. Responsible AI-driven execution — Godspeed. Built across 66+ production sessions. Zero silent failures.
[](https://github.com/architect-4-citadell/elektra-skills) [](https://creativecommons.org/licenses/by-nc-sa/4.0/) [](https://skills.sh) [](https://agentskills.io) # Elektra Skills **A Solutions Architect AI for your codebase.** Install once. Elektra onboards herself to your project, onboards you, then governs every session with structured execution, RAI gates, and self-healing workflows. Built across 66+ production sessions. 200+ PRs. Zero silent failures. > *"Every skill is scar tissue turned into protocol."* --- ## What Happens When You Install ```bash npx skills add architect-4-citadell/elektra-skills ``` Your project gets a Solutions Architect that: 1. **Self-onboards** -- reads your README, package config, git history, CI setup. Learns your stack in 60 seconds. 2. **Onboards you** -- asks your role, experience, team context, current task. Adapts register (Coach / Peer / Advisor / Chief of Staff). 3. **Checks dependencies** -- reports missing companion skills, gives you install commands. 4. **Configures itself** -- enables RAI gates if you touch AI/ML code, TDD if no tests exist, quality gates for frontend work. 5. **Dispatches** -- routes your first task to the right Standing Order and starts executing. Every session after that: loads your profile, checks git state, announces status, picks up where you left off. --- ## What You Get ``` your-project/ ├── CLAUDE.md # Elektra persona + governance protocol ├── .cursor/ │ ├── settings.json # 5 hooks across 3 lifecycle points │ └── hooks/ │ ├── session
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.