Loading...
Loading...
Found 502 Skills
Agent Infrastructure: Bridge any skill or directory of skill collections to Claude Code (~/.claude/skills) and Codex (~/.codex/skills). Supports skills in the dbskill repository as well as absolute paths to external skills. Connect source directories via symlinks, with both ends synchronized when the source directory is modified. Supports batch bridging by skill name, relative path, absolute path, or skills directory, as well as unbridging and checking bridge status. Triggers: /dbs-bridge, /bridge, "bridge this skill", "bridge this skills directory", "connect this skill to Claude Code and Codex", "make this skill callable by both Claude and Codex", "unbridge", "check bridge status" Bridge any skill folder or directory of skill folders to Claude Code and Codex using symlinks. Supports dbskill skills and external skill directories. Use when the user wants one or many skills callable from both agents, or wants to unlink/check bridge status. Trigger: /dbs-bridge, /bridge, "bridge this skill", "bridge this skills directory", "make this skill available to Claude Code and Codex", "unlink this skill", "check bridge status"
Use this skill for cross-model code reviews using OpenAI Codex CLI via MCP. Activates on mentions of codex review, cross-model review, code review with codex, peer review, review my code, review this PR, review changes, codex check, second opinion, or gpt review.
Agent Workspace Migration. Organize any project into a long-term maintainable Agent workspace with consistent support for both Claude Code and Codex: audit rule files, identify source-of-truth skills, standardize naming conventions, and generate bridges. Triggers: /dbs-agent-migration, /agent-migration, "migrate to Codex", "migrate to Claude Code", "unify AGENTS.md", "organize skill bridges", "my Agent workspace is messy", "help me unify Claude and Codex" Agent workspace migration. Turn any project into a maintainable Claude Code / Codex dual-host workspace by auditing rule files, establishing source-of-truth skills, normalizing names, and generating bridges. Trigger: /dbs-agent-migration, /agent-migration, "migrate to Codex", "migrate to Claude Code", "fix AGENTS.md", "organize skill bridges"
Orchestrate autonomous ML research workflows with cross-model review loops, idea discovery, and experiment automation using Claude Code and Codex MCP
Expert in developing, installing, and managing tweaks for the Codex++ desktop app extension system
Generate setup scripts/configs for AI agent worktrees and isolated environments across Cursor, Codex, and Conductor. Use when wiring up a project so AI agents start with the same dependencies, env files, and tool configs as the main repo.
Generate a Codex Super Bowl merch redemption URL (tokenized) and open it. Use when a user asks to redeem Super Bowl/Codex merch, needs a redemption token, or wants the merch redemption link.
MANDATORY for code review - must use Codex CLI for all code reviews, then apply fixes based on Codex feedback. Also use for cross-verification, debugging, and getting alternative implementations.
Use when building features with **Codex** (OpenAI Codex CLI) in any codebase and the work should go through a disciplined build → review → test → fix loop. Triggers on "run the build loop", "build the next task", "continue the plan", "build this feature properly", or any request to implement work from a plan file or a direct feature prompt. Builds from the plan (or the prompt if no plan exists), runs Codex's `/review` on uncommitted changes and fixes every issue found, tests and verifies the feature end to end, fixes anything testing surfaces, and reports back once complete. Repeats until all plan tasks are checked off.
Route low-risk coding tasks to cheaper LLMs while keeping Codex for high-risk decisions, using MCP tools for cost-aware delegation
Code review closeout for Claude Code, Codex, OpenCode, and DeepSeek TUI: local dirty changes, branch vs main, parallel tests.
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.