Set up session replay for visual debugging. An agent skill from nexus-labs-automation/mobile-observability.

MITAuto-check passedDevelopment

Install Session Replay

skills CLI
$ npx skills add nexus-labs-automation/mobile-observability --skill session-replay -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nexus-labs-automation/mobile-observability session-replay --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nexus-labs-automation/mobile-observability.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/session-replay .claude/skills/session-replay && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
session-replay
GitHub stars
116
Token cost
~362 tokens
SKILL.md length
116 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Set up session replay for visual debugging. An agent skill from nexus-labs-automation/mobile-observability.

  • Implementing screen recording
  • SKILL.md covers When to Use, Privacy Requirements (Must Do), Performance Budget and Capture Strategies, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Replay features

What it does

Session Replay is an agent skill from nexus-labs-automation/mobile-observability. Set up session replay for visual debugging. Use when implementing screen recording, replay features, or visual debugging tools.

Its SKILL.md is about 360 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging. The repository describes itself as: Claude Code plugin for mobile app observability: crash reporting, performance monitoring, and instrumentation for iOS, Android, and React Native. The licence is MIT.

When your agent uses it

  • Implementing screen recording
  • Replay features
  • Visual debugging tools

Example prompts

  • “/session-replay”

What it can do on your machine

Read from SKILL.md and the folder at commit 488c97f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Session Replay loads about 362 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 116 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~362

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nexus-labs-automation/mobile-observability at commit 488c97f, republished under its MIT licence (© nexus-labs-automation). 116 words, ~362 tokens.

Download SKILL.mdSave it as .claude/skills/session-replay/SKILL.md (or your agent's skills folder).
name
session-replay
description
Set up session replay for visual debugging. Use when implementing screen recording, replay features, or visual debugging tools.
triggers
record user sessions, replay user actions, screen recording, see what user did, set up session replay, visual debugging
priority
3

Session Replay

Capture visual recordings of user sessions for debugging.

When to Use

  • Reproducing hard-to-debug issues
  • Understanding user confusion
  • QA and support investigations

Privacy Requirements (Must Do)

Mask by default:

  • All text input fields
  • Passwords and sensitive data
  • User-generated content
  • Financial information
  • User photos/documents

Performance Budget

ResourceLimit
CPU<5% additional
Memory<20MB additional
NetworkBatch on WiFi
BatteryPause when low

Capture Strategies

StrategyFidelityOverhead
Screenshots (1-2 fps)LowerLower
View hierarchy recordingHigherModerate
Hybrid (screenshots + events)BestModerate

Best Practice

Don't record everything. Target:

  • Error sessions only (rolling buffer)
  • Key user journeys
  • 1-10% sampling for general insights

Implementation

See references/session-replay.md for:

  • Platform-specific setup
  • Privacy masking patterns
  • Vendor configurations (Sentry, Datadog, New Relic)

© nexus-labs-automation, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/session-replay of nexus-labs-automation/mobile-observability.

Open the folder on GitHubat commit 488c97f

Compare with similar skills

Session Replay next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Session Replay compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Session Replay this skillnexus-labs-automation/mobile-observability116—~362Automated safety check: PassMIT
Aosp Infrastructureaospbooks/aosp-internal-book139—~485Automated safety check: PassApache-2.0
Native Data FetchingCherryHQ/cherry-studio-app4k6 repos~2.9kAutomated safety check: NotesMIT
React DevTools Profile Analyzerkeybase/client9.3k—~978Automated safety check: PassBSD-3-Clause
Jazz UI Developmentgarden-co/classic-jazz2.5k—~1.7kAutomated safety check: PassMIT
Smt E2E Dataflow DebuggingGoogleCloudPlatform/DataflowTemplates1.3k—~1.8kAutomated safety check: PassApache-2.0

Similar skills

  • Aosp Infrastructure

    aospbooks/aosp-internal-book

    AOSP Part XIII — Infrastructure. An agent skill from aospbooks/aosp-internal-book.

    139 GitHub stars~485 tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Native Data Fetching

    CherryHQ/cherry-studio-app

    A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

    4k GitHub starsUsed in 6 repos~2.9k tokens
    DevelopmentAuto-check: notes
  • Parses a React DevTools Profiler JSON export with Python scripts to find re-render storms, commit fan-out and why a component rendered, without opening the DevTools UI.

    9.3k GitHub stars~978 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Jazz UI Development

    garden-co/classic-jazz

    A skill your agent uses when building, debugging, or optimizing Jazz applications.

    2.5k GitHub stars~1.7k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Smt E2E Dataflow Debugging

    GoogleCloudPlatform/DataflowTemplates

    Debugs logical errors and data discrepancies in Dataflow templates by launching jobs via Terraform and comparing source (e.g.

    1.3k GitHub stars~1.8k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • MCP Debugger

    debugmcp/mcp-debugger

    A skill your agent uses when investigating a bug, failing test, or unexpected runtime behavior and the mcp-debugger MCP server is available — drives real step-through debuggers (breakpoints, stack…

    174 GitHub stars~4.2k tokensUpdated today
    DevelopmentAuto-check passed

More from nexus-labs-automation/mobile-observability

All 8 skills in this repo
  • Crash Instrumentation

    nexus-labs-automation/mobile-observability

    Set up crash instrumentation with actionable context. An agent skill from nexus-labs-automation/mobile-observability.

    116 GitHub stars~744 tokensUpdated 1 mo ago
    Auto-check passed
  • Instrumentation Planning

    nexus-labs-automation/mobile-observability

    Plan what to measure in mobile apps. An agent skill from nexus-labs-automation/mobile-observability.

    116 GitHub stars~517 tokensUpdated 1 mo ago
    Auto-check passed
  • Network Tracing

    nexus-labs-automation/mobile-observability

    Instrument API requests with spans and distributed tracing. An agent skill from nexus-labs-automation/mobile-observability.

    116 GitHub stars~672 tokensUpdated 1 mo ago
    Auto-check passed
  • Symbolication Setup

    nexus-labs-automation/mobile-observability

    Configure crash symbolication for readable stack traces. An agent skill from nexus-labs-automation/mobile-observability.

    116 GitHub stars~996 tokensUpdated 1 mo ago
    Auto-check passed
  • Interaction Latency

    nexus-labs-automation/mobile-observability

    Measure time from user tap to action completion. An agent skill from nexus-labs-automation/mobile-observability.

    116 GitHub stars~358 tokensUpdated 1 mo ago
    Auto-check passed
  • Navigation Latency

    nexus-labs-automation/mobile-observability

    Measure time from navigation tap to screen fully loaded and interactive.

    116 GitHub stars~395 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Session Replay

What does Session Replay do?

Set up session replay for visual debugging. An agent skill from nexus-labs-automation/mobile-observability. Session Replay is an agent skill from nexus-labs-automation/mobile-observability. Set up session replay for visual debugging.

When should I use Session Replay?

Session Replay fits situations like: implementing screen recording; replay features; visual debugging tools.

How do I install Session Replay in Claude Code?

Run `npx skills add nexus-labs-automation/mobile-observability --skill session-replay -a claude-code`. Or copy the skill folder (skills/session-replay in nexus-labs-automation/mobile-observability) into .claude/skills/session-replay in your project. Claude Code loads it when a task matches its description.

How do I install Session Replay in Codex?

Run `npx skills add nexus-labs-automation/mobile-observability --skill session-replay -a codex`. Or copy the skill folder (skills/session-replay in nexus-labs-automation/mobile-observability) into .agents/skills/session-replay in your project. Codex loads it when a task matches its description.

Can I use Session Replay in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nexus-labs-automation/mobile-observability --skill session-replay -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/session-replay, .gemini/skills/session-replay, .github/skills/session-replay and .opencode/skills/session-replay in your project.

What does Session Replay need to run?

SKILL.md names no scripts, command-line tools or credentials: Session Replay is instructions for the agent only.

Does Session Replay access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Session Replay safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Session Replay use?

Session Replay is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Session Replay use?

About 362 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Session Replay?

Skills that share tags, products or a category with Session Replay: Aosp Infrastructure (aospbooks/aosp-internal-book, 139 stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), React DevTools Profile Analyzer (keybase/client, 9.3k stars) and Jazz UI Development (garden-co/classic-jazz, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Session Replay?

nexus-labs-automation (a GitHub organization) maintains it in nexus-labs-automation/mobile-observability, which has 116 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 23, 2026.

Source: nexus-labs-automation/mobile-observability on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.