Loading...
Loading...
Found 837 Skills
AI consultation CLI quick reference. Use when running consult commands to check syntax for general queries, protocol reviews, and stats across Gemini, Codex, and Claude.
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
Manage host-mode duoduo runtime settings and diagnostics. Use when the user asks to inspect or change daemon status, daemon config, daemon logs, Codex runtime enablement, debug log level, telemetry persistence, cadence frequency, or other persistent host-mode settings stored in ~/.config/duoduo/.env. Also trigger for Chinese requests such as 帮我启用 codex runtime, 打开 debug log, 关闭 telemetry, 调 cadence 频率, or 看看 duoduo daemon 配置.
Install and run a local quota reporter that probes Codex quota windows plus Claude CLI usage metadata, posts the latest status to a shared dashboard, and sets up an hourly scheduled run. Use this whenever a teammate wants to join the shared quota dashboard, report their own Codex or Claude usage, install the hourly reporter, or verify that reports are reaching the shared service. Trigger on requests about Codex quota, Claude CLI usage, token usage, usage monitoring, hourly usage reporting, shared quota dashboards, Vercel quota dashboards, or Turso-backed quota collection.
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
Generate slide images sequentially from DESIGN.md and slide prompt JSON using Codex native image generation, saving each output into the workspace with page-number filenames.
Expert skill for using wanman, the open-source local agent matrix runtime that coordinates multiple Claude Code or Codex agents on your machine.
Drive the Codex review cycle on an open PR. Polls Codex comments, classifies severity (P0/P1 blocking, P2/nit ignored), applies fixes via subagent or escalates to a different worker on round 3, labels needs-human and stops on round 4. Auto-merges when all merge gates are green.
Manage installation, version tracking, and update checks for Claude Code, Codex, and OpenClaw Skills. Supports installation from local paths or GitHub repositories, automatically identifies .codex/.claude/.openclaw target directories, records installation time, source URL, and version number for each Skill, and checks for GitHub updates.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Unified setup hub: project init, tool setup, 2-agent config, harness-mem, codex CLI, and rule localization. Use when user mentions setup, initialization, new projects, workflow files, CI setup, LSP setup, MCP setup, codex setup, opencode setup, 2-Agent setup, PM coordination, Cursor setup, harness-mem, claude-mem integration, cross-session memory, localize rules, adapt rules. Do NOT load for: implementation work, reviews, build verification, or deployments.
Configure project memory files (CLAUDE.md, AGENTS.md, CODEX.md) for persistent context, coding standards, architecture decisions, and team conventions. Reference for the 4-tier memory hierarchy, cross-platform compatibility, and quick-add commands.