Skill rating

Advisor mode: audit a codebase, rank what is worth doing, and write self-contained handoff plans that a fresh agent executes. Never edits source itself. Use for "what should we improve", "find improve

Kubernetes operations: debugging, security, RBAC, and infrastructure tooling.

AI image generation: Gemini and Nano Banana backends; single/series/batch workflows with prompt-to-disk.

Run benchmark-selected GPT-5.6 work through the Codex CLI.

Code quality: cleanup, linting, formatting, quality gates.

Pull request lifecycle: commit, codex review, sync, review, fix, status, cleanup, and PR mining. Use when user wants to commit changes, get a second-opinion code review from Codex, push changes, creat

Tracked lightweight execution with composable rigor flags: --trivial, --discuss, --research, --full. Covers zero-ceremony inline fixes (typo, spelling fix, small mistake in a single file, ≤3 edits) th

Mandatory rules for agents in git worktree isolation.

Research: structured investigation, fact-checking, explanation traces.

Writing: voice creation and validation, prose editing, anti-AI cleanup, professional communication, translation.

Audit CVE/vulnerability source coverage for a technology stack. Maps each component (container, library, base image, runtime) to authoritative CVE feeds, flags gaps, and produces audit-ready reports.

Video editing pipeline: cut footage, assemble clips via FFmpeg and Remotion.

Content operations: editorial calendar, marketing, publishing, social media management.

Code review: systematic single-file, parallel multi-reviewer, full-repo audit, PR diff review.

Verify cross-component wiring and data flow.

Design a CLI interface: args, flags, help, output, errors, exit codes, config.

Maximize information density: preserve all instructions, remove prose filler.

GitHub: notification triage, profile rule extraction.

Debugging: guided diagnosis of application bugs, and post-mortem of failed agent sessions.

Domain-specific: SAP Commerce, OpenSearch detection, WordPress validation, enterprise search.

Review and fix temporal references in code comments.

Convert PDF, Office, HTML, data, media, ZIP to Markdown.

Extract video transcripts: yt-dlp subtitles to clean paragraphs.

Assessment: read-only inspection, codebase overview, value analysis, health checks, ADR consultation, decision analysis, multi-perspective critique.

Data analysis and reference enrichment.

Jev-driven browser automation: Jev picks operations, programs execute, a text model writes field values only when Jev cannot pick one from the goal.

Make a trailer, promo, teaser, sizzle reel, launch or gameplay video for one of our browser games (Road to AEW / ROAD TO THE BIG TIME, 5 Star Booker, or any game built the same way) from the real game

Design React interfaces with the full shadcn/ui catalog. The agent writes a brief, Jev picks components and a style recipe from bounded catalogs, then the agent implements, renders, and reviews agains

Broad Jev interrogation: generate up to 50 context-specific questions about a plan, spec, design, code artifact, or any topic — using all primitive shapes and structured forms to surface hidden proble

Collect, filter, and freshness-qualify news items.

Interactive guide to workflow system: agents, skills, routing, execution patterns.

Deterministic palette/matrix pixel art (not AI). Use for procedural tile art, color-quantized output, matrix sprites.

Detect documentation drift against filesystem state.

Generate headlines, titles, and subject lines: charge, volume, tighten.

Manage multiple Claude Code accounts: add, list, check, launch, and install shell aliases for 10+ isolated CLAUDE_CONFIG_DIR profiles.

Validate content framing on joy-grievance spectrum.

Process: retrospectives, session handoff, pair programming, subagent-driven development, condition-based waiting.

Security: review git changes for vulnerabilities, threat-model a system's attack surface, audit supply-chain risks.

Request router: picks the agent, skill, and pipeline with /do's rules, then uses Jev to validate the requested outcome and attach extra skills.

Generate headless Claude Code cron jobs with safety.

FFmpeg-based video creation from image and audio.

CPU-only motion data processing pipeline for game animation: BVH import, contact detection, root decomposition, motion blending, FABRIK IK. No GPU required.

Constructive critique via 5 HackerNews personas with claim validation.

Plan multi-part content series: structure, cross-linking, cadence.

Frontend: UI design, distinctive visual styles, HTML artifacts, Three.js 3D.

Background memory consolidation — overnight review, merge, and injection payload for memory files.

Anti-rationalization enforcement for maximum-rigor task execution.

Improve architecture across modules by deepening interfaces.

Standalone WebGL fragment shaders for card visual effects: holographic foil, shimmer, rarity glow.

Statistical rule discovery from Go codebase patterns.