>

Deep analysis and investigation

Business logic, race conditions, and AI security analysis

>-

<Role>

You are Cortex — the ML/AI engineer on the Engineering Team.

emelia

Write internal communications using company formats. Use when writing status reports, leadership updates, company newsletters, FAQs, incident reports, project updates, or any internal communications.

Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.

Analyze MaxText training job performance using tgs_tagger, TraceLens, and IRLens. Use when the user asks to analyze a training run, profile traces, HLO IR, TGS metrics, GPU utilization, or mentions tag_tgs, TraceLens, IRLens, xplane, or performance analysis.

Configures TrueFoundry AI Gateway for unified OpenAI-compatible LLM access. Covers auth (PAT/VAT), model routing, rate limiting, and budget controls.

Breaks complex systems into atomic components, maps their relationships, and reconstructs them in optimized configurations to identify bottlenecks, critical failure points, and redesign opportunities. Use when dealing with complex systems that need simplification, identifying bottlenecks or critical failure points, redesigning architecture or processes for better performance, breaking down problems that feel overwhelming, analyzing dependencies to understand ripple effects, or when optimization requires understanding how parts interact.

多代理内容生产线。自动化从选题研究到内容创作的全流程。Keywords: 内容创作, 文案, content creation, copywriting.

Use this skill to act as the agent defined in agents-orchestrator.md for tasks matching that role.

Changelog Automation workflow skill. Use this skill when the user needs Automate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

>

Generate a comprehensive, user-editable schema reference file for the data warehouse.

Reviews working copy changes and drafts a concise 1-line commit message. Use when the user wants a commit message or asks to describe/commit changes.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

Comprehensive best practices guide for building CLI applications in Rust using clap. Contains 42 rules across 8 categories, prioritized by impact to guide CLI design, argument parsing, and testing.

Interactive guide to soda-gql features and patterns

Improve a specific repo's corpus conformance by fixing its top diverging cops in parallel using worktree-isolated teammates.

Git Commit Command

Developer productivity workflows - PR review, CI monitoring, deploy tracking, code metrics

Produce a short, actionable execution plan before a large refactor or migration.

Generate AI videos, images, and audio with Runway API. Use when generating video from images, text-to-video, video-to-video, character performance, text-to-image, text-to-speech, sound effects, or voice processing with Runway.

Generate technical implementation plans from feature specifications. Use after creating a spec to define architecture, tech stack, and implementation phases. Creates plan.md with detailed technical design.

Generate PRODUCT_SPEC.md through guided Q&A. Use as the first step when starting a new greenfield project.

Etalon memory architecture with Knowledge Graph (PARA), session isolation, memory decay, and QMD hybrid search

COBOL for mainframe and legacy business systems. Use for .cob files.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

Niko Memory Bank System - Plan Phase - Implementation Planning

Quickly scaffold production-ready FastAPI endpoints for client workflows. Use when building new APIs for QuickBooks, ShipStation, or webhook integrations.

Creates or adds Cursor agent lifecycle hooks. Use when the user asks to create a hook, add a hook, set up a lifecycle hook, or automate something on agent stop, afterFileEdit, afterAgentResponse, or other Cursor hook events. Hooks live in .cursor/hooks/ and are registered in .cursor/hooks.json.

Use this skill when committing VCSDD pipeline artifacts to git. Provides conventional commit message format, phase tag patterns, and atomic staging strategies.

Meta-skill for Claude Code to validate and polish Codex skills under `.codex/skills/` by running the skill-polisher and reviewing structural integrity. Use when auditing Codex skills, enforcing standardization, or running integrity sweeps across the Codex skill set.

Fix a specific bug or problem in the codebase. Analyzes code to find and fix issues without creating plans. Use when user reports a bug, error, or something not working. Always suggests test coverage and adds logging.

My Kit standalone utilities — handles code audits.

Initialize a new SDD change set after user-approved naming

Search the web for real-time information. Note: International search APIs (DuckDuckGo, Brave, Google) are blocked in China. Use Bing or Baidu API instead.

Fastify is a high-performance Node.js web framework focused on speed

Autonomous navigation agent for Oracle of Secrets. Uses static map data and dynamic RAM state to localize Link and route him to destinations.

Build software features end to end in an existing repository. Use when the user asks to build, implement, add, create, wire up, or ship code changes, including backend, frontend, APIs, and automation tasks.

Change the Routing Solution routing profiles/vehicle types. To be used as part of customize-main skill

An example skill template showing the SKILL.md format. Use this when you need to understand skill structure.

Refactoring technique to improve code readability by renaming methods to better reflect their purpose and functionality

Patrick Lencioni's organizational health framework based on four disciplines - building cohesive leadership, creating clarity, over-communicating, and reinforcing through systems

Audit Python codebases for security, performance, correctness, and architecture antipatterns. Run optional trusted runtime checks (syntax, tests, lint, typing) plus static rule scans, then output a 0-100 health score with actionable fixes. Use when users ask to inspect a Python project, run a Python health check, review backend code quality, or perform a pre-release audit.

AI behavioral guideline for autonomously detecting work session boundaries and proposing updates to current_focus.md. The AI monitors conversation flow for natural breakpoints and acts without explicit invocation.