Record and Replay

Record the user's actions — browser (Playwright event stream + trace) or native desktop (lightweight event/window/screenshot stream) — on macOS, Windows and Linux for up to 30 minutes, then turn the demonstration into a reusable agent skill. Use when the user asks you to watch them perform a task, record a workflow, or create/refine a skill from their demonstration. Agent-agnostic — works in Claude Code, Codex, opencode, or any agent with shell access.

48 stars 5 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add ugarchance/record-and-replay-skill --skill record-and-replay

Manual install

git clone --depth 1 https://github.com/ugarchance/record-and-replay-skill.git /tmp/record-and-replay-skill
mkdir -p ~/.claude/skills
cp -r /tmp/record-and-replay-skill/. ~/.claude/skills/record-and-replay

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Record & Replay (browser + desktop)

Record & Replay lets an agent learn a user-demonstrated workflow and turn it into a reusable skill. Two modes:

- **Browser mode** (default, richest evidence): a headed Playwright browser (system Google Chrome if available) records every user action into `events.jsonl` with multiple selector candidates, plus Playwright trace chunks (`trace-NNN.zip`). Works on macOS, Windows and Linux.
- **Desktop mode** (native apps): a lightweight single-process recorder (pynput) captures global mouse/keyboard events, active-window changes and click-moment screenshots into `desktop-events.jsonl` + `screens/` — Codex-parity (Codex records an event/context stream too, not video), ~1-3% CPU. Works on macOS, Windows and Linux (X11). See "Desktop recording" below.

Pick browser mode whenever the workflow is browser-only — its semantic selectors produce far better skills than desktop coordinates.

## Setup (once)

```bash
cd ~/.agents/skills/record-and-replay
node setup.mjs      # npm install + (Chromium only if Chrome is missing) + self-tests
node install.mjs    # link into agent skill dirs (symlink on macOS/Linux, junction on Windows)
```

Installs the `playwright` npm package. Browsers are NOT downloaded when Google Chrome is installed (the recorder uses `channel: 'chrome'`); otherwise the script downloads Chromium. Both scripts are cross-platform (Node).

## Recording Workflow

Read the full skill on GitHub

Details

Skill name: record-and-replay
Repository: ugarchance/record-and-replay-skill
License: MIT
Repo updated: 8 August 2026

FAQ

What does the Record and Replay skill do?

How do I install the Record and Replay skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ugarchance/record-and-replay-skill --skill record-and-replay. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Record and Replay popular?

It lives in ugarchance/record-and-replay-skill, which has 48 GitHub stars and 5 forks.

Related skills

R00 BehiSecc Awesome Claude Skills Datascience

Winnershitram/r17-behisecc-awesome-claude-skills-datascience

🤖 Data Science & AI/ML skill suite derived from BehiSecc/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.

AI, LLMs & Agents

Ue5 MCP

ibrews/ue5-mcp

Field manual for driving Unreal Engine 5.7 / 5.8 through MCP. Engine-level gotchas, silent-fail edges, crash patterns, and the call sequences that actually work — applicable regardless of which MCP server you're using (Epic's official ModelContextProtocol plugin, custom servers, or anything else). Auto-trigger when Unreal Engine MCP tools are detected in a session, or when the user mentions Unreal Engine, UE5, Blueprints, Niagara, MetaSound, materials, or any UE editor automation workflow. This skill contains hard-won knowledge from real debugging sessions — most entries trace back to an actua

AI, LLMs & Agents

Xxd Strip AI Meta

nevertoday/xxd-strip-ai-meta

Remove C2PA Content Credentials, AI provenance, OpenAI/gpt-image metadata, prompts, EXIF/XMP/IPTC/comment/software metadata from image files or directories. Use when users ask to strip "made with AI", C2PA, Content Credentials, image metadata, EXIF, AI labels, OpenAI provenance, or batch-clean many PNG/JPEG/WebP/TIFF images while replacing originals and preserving pixel quality as much as possible.

AI, LLMs & Agents

Pencilplaybook

stevembarclay/pencilplaybook

PencilPlaybook is the UI Skills / Taste-Skill for Pencil.dev + Claude Code — a design playbook that gives Claude real perceptual psychology and senior-level guardrails so it stops producing averaged-out AI slop.

AI, LLMs & Agents

Agent Forge

AlekseiUL/agentforge-openclaw

Создание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.

AI, LLMs & Agents

Math Modeling Skill

anticipate218/math-modeling-skill

数学建模竞赛全流程助手：审题选题、模型选型与求解、结果检验（误差/灵敏度/稳健性）、论文写作与提交自检，覆盖国赛 CUMCM、研赛华为杯、美赛 MCM/ICM。当用户准备建模竞赛、写建模论文、问赛题思路、写摘要、做灵敏度分析、选模型、检查论文格式或提交前自检时使用——即使没说"数学建模"三字也应使用。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.