by skillsynchq · Claude Skill · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
replay is a claude skill by skillsynchq.
| Stars | 50 |
| Forks | 5 |
| Language | TypeScript |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 41.9731184121277/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-10 |
| Created | 2026-03-26 |
| Platforms | claude-code, node |
| Est. Tokens | ~40k |
Looking for a replay alternative? If you're comparing replay with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Boilerplate built for AI coding agents, tools, CLI
A skill catalogue of 36 copy-ready admin UI shapes an AI agent installs and composes into a real back-office.
🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skill
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
Web app for teams of 20+ members. In-built connections to major LLMs via API. Share chats, prompts, and agents
Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp
Explore other popular claude skill tools:
replay is an open-source claude skill by skillsynchq with 50 GitHub stars.
replay is primarily written in TypeScript. It covers topics such as ai, better-auth, chatgpt.
You can find installation instructions and usage details in the replay GitHub repository at github.com/skillsynchq/replay. The project has 50 stars and 5 forks, indicating an active community.
replay is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to replay on Agent Skills Hub include codeguide-starter-fullstack, open-dashboard, skillshub. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: