Elektra Skills
Responsible AI Engineering & Execution Automation
A delivery-focused CLAUDE.md persona with governance hooks, RAI gates, and a 12-phase execution engine.Built across 66+ production sessions. 200+ PRs. Zero silent failures.
Works with 30+ AI coding agents
WHAT IS ELEKTRA?
A delivery-focused AI persona that lives in your .claude/ directory
Elektra is a CLAUDE.md persona with shell hooks that automatically enforce governance. Install once — every session runs through structured phases with RAI gates.
your-project/
├── CLAUDE.md # Elektra persona + coding standards
├── .claude/
│ ├── settings.json # Hook registry + enabled plugins
│ ├── hooks/
│ │ ├── session-init.sh # Session lifecycle tracking
│ │ ├── cycle-guard.sh # Plan→Build→Test→Review→Ship
│ │ ├── token-cap-guard.sh # Context window warnings
│ │ ├── rai-check.sh # RAI guardrail on edits
│ │ └── quality-gate.sh # Async lint + format checks
│ └── skills/
│ ├── standard-orders/ # 12-phase execution engine
│ ├── responsible-ai/ # 7-pillar RAI governance
│ └── autoresearch/ # Autonomous iteration loopHow it works
Session starts
session-init.sh creates lifecycle state, tracks phase + tool calls
Before every edit
Cycle guard enforces Plan → Build → Test → Review → Ship. RAI check classifies sensitive files.
After every edit
Quality gate runs async lint checks. Token guard warns at 140K/170K/190K context.
At RAI gates (P2.5, P5.5)
Files classified into tiers. Critical paths get 7-pillar checklist. No silent bypasses.
USE CASES
/SO-godspeedShip a feature across multiple sessions
12-phase execution: Context → Review → Plan → Execute → QA → Code Review → Accept → Ship. Hooks enforce the sequence — you can’t skip QA.
/SO-godspeed-resumeResume where you left off after a crash
Reads git status, branch, commits, plan checkboxes, and PR status to auto-detect your phase. If ambiguous, it asks.
/responsible-aiPrevent hallucinated financial figures
7-pillar framework: LLMs NEVER compute financial figures (deterministic only). Citations mandatory. Confidence scores surfaced. Every fallback logged.
THE PROBLEM
Why governance?
“AI wrote the code but nobody reviewed the AI”
66% of developers skip review on AI-generated code. Silent hallucinations, missing edge cases, and unverified claims ship to production.
“Tests pass but the feature was never wired up”
The #1 root cause of “done but not shipped.” Unit tests green, but the endpoint was never created. The button was never connected.
“We shipped and data leaked across tenants”
Silent failures are the most dangerous. No logs, no alerts, no confidence score. The LLM hallucinated a financial figure and nobody caught it.
We learned each of these the hard way.
— Citadel Agentic Labs
THE SKILLS
What you get
responsible-ai
v1.0.07-pillar governance framework
PII protection · Citation integrity · Hallucination prevention · Confidence scoring · Bias mitigation · Content provenance · Human-in-the-loop
"LLMs should NEVER compute financial figures. Use deterministic computation."
standard-orders
v4.1.112-phase idea-to-ship execution engine
P0 Context → P1 Review → P2 Eng → P3 Plan → P4 Execute → P4.5 QA → P5 Code Review → P6 Accept → P7 Ship → P8 Close
Every feature goes through 12 phases. You can’t skip QA. You can’t ship without review.
BATTLE-TESTED
Born from production, not theory
Production sessions
Pull requests merged
Silent failures
RAI governance gates
“Every skill is scar tissue turned into protocol.”
BUILT ON THE SHOULDERS OF
garrytan
skills.shgstack
Governor Stack — structured AI agent workflow governance
obra
skills.shsuperpowers
AI agent composition, planning, and code review skills
Anthropic
Nativedocument-skills
Official PDF, DOCX, PPTX, XLSX generation skills
skills.sh
skills.shui-ux-pro-max
50+ styles, 161 color palettes, 99 UX guidelines
affaan-m
GitHubeverything-claude-code
100+ Claude Code skills, agents, hooks, and patterns
karpathy
GitHubautoresearch
Karpathy’s autonomous iteration loop — the original inspiration
skills.sh
Ecosystemskills.sh
Open agent skills ecosystem — discovery, distribution, compatibility
GET STARTED
One command. All skills.
Commercial Use
Free for individuals and non-commercial projects. Building a commercial product with these skills?
Get a commercial licenseBuilt by Citadel Agentic Labs · citadellabs.ai