Latest Agent Skills

Dynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents.

Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.

When the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages, feature pages, lead capture forms, or contact forms. Also use when the user says 'CRO,' 'conversion rate optimization,' 'this page isn't...

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

Expert jq usage for JSON querying, filtering, transformation, and pipeline integration. Practical patterns for real shell workflows.

Scaffold a New DirectLake Semantic Model (TMDL) (preview)

Extract Warehouse DDL & Metadata

Delete a Fabric Workspace (with safety hook)

Provision a New Fabric Workspace

Create a Lakehouse in a Fabric Workspace

Deploy a Data Pipeline to Fabric

Deploy a Notebook to a Fabric Workspace

Read/Write Permission Test on a Fabric Warehouse

Scaffold a New Power BI Semantic Model (TMDL)

Poll a Fabric Pipeline Run to Terminal State

List Available Fabric Capacities

Clone a known-good report + retarget bindings (preview)

Execute a Fabric Data Pipeline

Live Edit a Power BI Model via MCP

Databricks Job & Notebook Lineage (Lite)

ade-ops setup — START HERE on a fresh clone. Scenario-aware onboarding for Databricks with Power BI and/or Microsoft Fabric.

Deploy SQL Scripts to a Fabric Warehouse

Inventory Items in a Fabric Workspace

Parallel Fabric Workspace Metadata Extraction

Databricks Workspace Status

Ad-Hoc Raw Upload to Databricks

Databricks → Fabric migration assessment + execute

Execute SQL on a Databricks SQL Warehouse

Publish a Power BI Semantic Model to Fabric

Extract Lineage from Fabric Artifacts

Execute Databricks Notebooks / Jobs

Incremental page addition to existing PBIR report

Execute Stored Procedures on a Fabric Warehouse

Autopilot operator

Send Structured Feedback to the Framework Maintainers

Power BI Report (PBIR) Deploy Only

Build a New PBIR Report (preview)

Project Status Overview

Reviewer Role Session

Public-recording safety overrides

Push to Remote Environment

Pull Remote State

Production Role Session

Interactive Project Setup

Compare Local vs Remote State

Developer Role Session

Protocol-level two-agent paper writing workflow. Use when the user wants Codex to plan and review from global context while DeepSeek writes or revises the manuscript through the global deepseek-agent skill, with muxing-style-review used for explicit prose style checks.

Chrome-dependent academic paper fetching and BibTeX curation. Use when the user provides a planNN.md, paper list, citation list, or literature plan and wants Codex to use Google, Google Scholar, publisher pages, DBLP, arXiv, and the user's Chrome-accessible permissions to fetch the best available PDFs and create or update references.bib.

Convert configured local Markdown collections to PDFs and upload the generated PDFs to Feishu/Lark Drive. Use when Codex needs to run or maintain a recurring local Markdown-to-PDF publishing workflow, inspect a private rules file, dry-run source/category mappings, invoke an external open-source Markdown PDF converter, or upload generated PDFs to a Feishu Drive folder.

Chrome-dependent academic literature scouting and idea planning. Use when the user gives a research idea, topic, question, or draft direction and wants Codex to browse Google, Google Scholar, and academic sources through the Codex Chrome plugin, identify relevant papers, explain what can be borrowed from them, and write a planNN.md before collecting PDFs or BibTeX.

Orchestrate a full theory-first idea discovery pipeline. Use when the user wants the analysis counterpart of idea-discovery: literature context, proof-oriented idea generation, novelty checking, DeepSeek critique, and an analysis plan instead of an experiment-first workflow.

Generate and rank theory-first or proof-oriented research ideas. Use when the user wants non-experimental research ideas, theoretical methods, proof programs, theorem candidates, impossibility results, convergence/sample-complexity analyses, or "analysis" variants of idea creation.

21-rule prose review workflow for technical and academic Markdown/LaTeX excerpts. Use when the user asks for muxing-style-review, wants a complete agent-style check combining check-human.md with agent-style audit-only evidence, wants a compact-rule check, wants a DeepSeek/Codex manuscript draft checked for clarity, evidence, citation discipline, terminology, AI-tell prose, or wants an A/B draft comparison. Prefer a dedicated review subagent when available for non-trivial reviews. Use the sibling style-review skill for the upstream post-hoc audit/polish workflow.

Coordinate proof runs across three interfaces: exhaust actionable local proof work first, package exact unresolved obligations for a provider-neutral external solver only when justified, and keep the user informed and in control of consequential choices.

Independent DeepSeek-backed adversarial proof-audit step for existing theorem, lemma, proposition, or proof artifacts in Markdown, LaTeX, or proof logs. Use when asked to check, audit, verify, red-team, or adversarially review a proof; when a completed proof task needs a correctness pass; or when a broader proof workflow dispatches an independent reviewer to find gaps, hidden assumptions, counterexamples, or unjustified steps.

Install or update Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path, then surface any per-skill install.md guidance. Use when a user asks to list installable skills, install a curated skill, update an installed skill, or install a skill from another repo (including private repos).

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.

Store and inspect source-indexed proof material extracted from papers, notes, PDFs, or LaTeX sources. Use when Codex needs stable material IDs, source locations, reusable abstractions, proof skeletons, tags, and public attribution before any proof ideas are cooked into proof-usage.

Call a DeepSeek-backed OpenCode agent as a separate critique, writing, or revision agent from Codex. Use when Codex needs to delegate adversarial research critique, novelty skepticism, method review, manuscript prose, LaTeX section drafting, academic text revision, or paper-writing feedback loops to DeepSeek.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.