Productivity

A Codex Skill that turns vague website ideas into structured project briefs and staged web-building plans.

The SprintFleet Method — run a portfolio of projects across multiple AI models with Claude

A collection of Claude skills I've created which help my workflows

Codex skill for safely operating H Cluster development machines and offline GPU workloads.

A Codex skill that suggests subagent lineups before Codex starts. Spots tasks worth delegating, recommends a 1-4 role lineup, and waits for your approval.

Agent-neutral project orchestration skill from idea to delivery

记录数据一键导出 Excel/CSV（带样式）：表头冻结、斑马纹、是/否，中文防乱码。适合运营报表、数据导出、日志归档。

多环境配置合并校验工具（默认/系统/任务三层）：按优先级合并校验、自动修冲突、出 diff、可回滚。适合 dev/test/prod 多环境管理的后端与运维。

A Codex skill for transparent, project-local memory that stays small, preserves durable lessons, and audits its own rules.

A Codex Skill that reduces avoidable token usage through progressive repository exploration, deterministic output compaction, artifact offloading, duplicate-work prevention, bounded retries, and compact task checkpoints.

Practical Codex skills distilled from real workflows, with clear provenance and community contributions.

Recently updated agent-skill-related GitHub repository: teammrvdl/claude-skills.

Reusable Codex skill for initializing AI product management workflow directories.

Standalone Codex skill project for safely publishing local Git repositories to GitHub.

Codex skill for drafting and polishing emails across tones and contexts.

Codex skill for CICIEC Stage 3 CI evidence, online judge, and score iteration workflows

Shareable Agent Skills for practical learning workflows.

Reusable personal Codex skills and workflow tools.

Hackathon Project for a script based claude skill for routine organization

An agent skill for Codex and Claude Code that explores GitHub directions, compares open-source projects, and validates reusable code at the depth you request.

Show your browser a task once. Get a self-healing Agent Skill any agent (Claude, OpenAI, …) can run.

Route complex Codex tasks to model-specific background workers with bounded concurrency and lead-agent verification.

This is an AI coding agent Skill that provides framework-agnostic project memory, enabling agents to preserve architecture, decisions, and conventions across sessions.

AI agent skill for cross-vendor model review and tiered task dispatch.