asciinema-recorder
Record Claude Code sessions with asciinema. TRIGGERS - record session, asciinema record, capture terminal, demo recording.
Best use case
asciinema-recorder is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Record Claude Code sessions with asciinema. TRIGGERS - record session, asciinema record, capture terminal, demo recording.
Teams using asciinema-recorder should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/asciinema-recorder/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How asciinema-recorder Compares
| Feature / Agent | asciinema-recorder | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Record Claude Code sessions with asciinema. TRIGGERS - record session, asciinema record, capture terminal, demo recording.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# asciinema-recorder
Generate ready-to-copy commands for recording Claude Code sessions with asciinema. Dynamically creates filenames based on workspace and datetime.
> **Platform**: macOS, Linux (requires asciinema CLI)
---
## Why This Skill?
This skill generates ready-to-copy recording commands with:
- Dynamic workspace-based filename
- Datetime stamp for uniqueness
- Saves to project's tmp/ folder (gitignored)
---
## Requirements
| Component | Required | Installation |
| ----------------- | -------- | ------------------------ |
| **asciinema CLI** | Yes | `brew install asciinema` |
---
## Workflow Phases
### Phase 0: Preflight Check
**Purpose**: Verify asciinema is installed.
```bash
# Check asciinema CLI
which asciinema && asciinema --version
```
If asciinema is NOT installed, use AskUserQuestion:
- question: "asciinema not found. How would you like to proceed?"
header: "Setup"
multiSelect: false
options:
- label: "Install asciinema (Recommended)"
description: "Run: brew install asciinema (macOS) or apt install asciinema (Linux)"
- label: "Show manual instructions"
description: "Display installation commands for all platforms"
- label: "Cancel"
description: "Exit without recording"
Based on selection:
- **"Install asciinema"** → Run appropriate install command based on OS:
```bash
# macOS
brew install asciinema
# Linux (apt)
sudo apt install asciinema
# Linux (pip)
pip install asciinema
```
Then proceed to Phase 1.0.
- **"Show manual instructions"** → Display the commands above, then exit skill.
- **"Cancel"** → Exit skill without action.
---
### Phase 1.0: Recording Location
**Purpose**: Let user choose where to save the recording.
Use AskUserQuestion:
- question: "Where should the recording be saved?"
header: "Location"
multiSelect: false
options:
- label: "$PWD/tmp/ (Recommended)"
description: "Project tmp directory (gitignored)"
- label: "~/asciinema/"
description: "Global recordings directory"
- label: "Custom path"
description: "Specify your own directory"
Based on selection:
- **"$PWD/tmp/"** → Set `OUTPUT_DIR="$PWD/tmp"`
- **"~/asciinema/"** → Set `OUTPUT_DIR="$HOME/asciinema"` and create if missing: `mkdir -p ~/asciinema`
- **"Custom path"** → Use user's "Other" input as `OUTPUT_DIR`
---
### Phase 1.1: Recording Options
**Purpose**: Let user configure recording behavior.
Use AskUserQuestion:
- question: "Which recording options would you like?"
header: "Options"
multiSelect: true
options:
- label: "Add title/description"
description: "Include session title in recording metadata (-t flag)"
- label: "Disable idle time limit"
description: "Keep full pauses instead of 2s max (--idle-time-limit 0)"
- label: "Quiet mode"
description: "Suppress asciinema status messages (-q flag)"
Based on selections, build command flags:
- **"Add title"** → Continue to title selection question, add `-t "title"` flag
- **"Disable idle time limit"** → Add `--idle-time-limit 0` flag
- **"Quiet mode"** → Add `-q` flag
**If "Add title" was selected**, follow up with:
- question: "Enter a title for this recording:"
header: "Title"
multiSelect: false
options:
- label: "Use workspace name"
description: "Title: ${WORKSPACE}"
- label: "Use workspace + datetime"
description: "Title: ${WORKSPACE} ${DATETIME}"
- label: "Custom title"
description: "Enter your own title"
Based on title selection:
- **"Use workspace name"** → Set `TITLE="${WORKSPACE}"`
- **"Use workspace + datetime"** → Set `TITLE="${WORKSPACE} ${DATETIME}"`
- **"Custom title"** → Use user's "Other" input as `TITLE`
---
### Phase 1.2: Detect Context & Generate Command
**Purpose**: Generate a copy-paste ready recording command.
#### Step 1.2.1: Detect Workspace
Extract workspace name from `$PWD`:
```bash
/usr/bin/env bash << 'SKILL_SCRIPT_EOF'
WORKSPACE=$(basename "$PWD")
echo "Workspace: $WORKSPACE"
SKILL_SCRIPT_EOF
```
#### Step 1.2.2: Generate Datetime
```bash
/usr/bin/env bash << 'SKILL_SCRIPT_EOF_2'
DATETIME=$(date +%Y-%m-%d_%H-%M)
echo "Datetime: $DATETIME"
SKILL_SCRIPT_EOF_2
```
#### Step 1.2.3: Ensure Output Directory Exists
Create the output directory selected in Phase 1.0:
```bash
mkdir -p "${OUTPUT_DIR}"
```
#### Step 1.2.4: Construct Command
Build the recording command using:
- `OUTPUT_DIR` from Phase 1.0 (location selection)
- Flags from Phase 1.1 (options selection)
- `TITLE` if "Add title" was selected
```bash
# Base command
CMD="asciinema rec"
# Add flags from Phase 1.1 options
# (Claude builds this based on user selections)
# Final command format:
asciinema rec ${FLAGS} "${OUTPUT_DIR}/${WORKSPACE}_${DATETIME}.cast"
```
**Example outputs:**
```bash
# Default (no options selected):
asciinema rec /home/user/projects/my-app/tmp/my-app_2025-12-21_14-30.cast
# With title + quiet mode:
asciinema rec -t "my-app Demo" -q /home/user/projects/my-app/tmp/my-app_2025-12-21_14-30.cast
# With all options:
asciinema rec -t "my-app 2025-12-21 14:30" -q --idle-time-limit 0 ~/asciinema/my-app_2025-12-21_14-30.cast
```
---
### Phase 2: User Guidance
**Purpose**: Explain the recording workflow step-by-step.
Present these instructions:
```markdown
## Recording Instructions
1. **Exit Claude Code** - Type `exit` or press `Ctrl+D`
2. **Copy the command** shown above
3. **Paste and run** in your terminal (starts a recorded shell)
4. **Run `claude`** to start Claude Code inside the recording
5. Work normally - everything is captured
6. **Exit Claude Code** - Type `exit` or press `Ctrl+D`
7. **Exit the recording shell** - Type `exit` or press `Ctrl+D` again
Your recording will be saved to:
`$PWD/tmp/{workspace}_{datetime}.cast`
```
---
### Phase 3: Additional Info
**Purpose**: Provide helpful tips for after recording.
```markdown
## Tips
- **Environment variable**: `ASCIINEMA_REC=1` is set during recording
- **Playback**: Use `asciinema-player` skill or `asciinema play file.cast`
- **Upload (optional)**: `asciinema upload file.cast` (requires account)
- **Markers**: Add `asciinema marker` during recording for navigation points
```
---
## TodoWrite Task Templates
### Template: Record Claude Code Session
```
1. [Preflight] Check asciinema CLI installed
2. [Preflight] Offer installation if missing
3. [Context] Detect current workspace from $PWD
4. [Context] Generate datetime slug
5. [Context] Ensure tmp/ directory exists
6. [Command] Construct full recording command
7. [Guidance] Display step-by-step instructions
8. [Guidance] Show additional tips (playback, upload)
9. Verify against Skill Quality Checklist
```
---
## Post-Change Checklist
After modifying this skill:
1. [ ] Command generation still uses `$PWD` (no hardcoded paths)
2. [ ] Guidance steps remain clear and platform-agnostic
3. [ ] TodoWrite template matches actual workflow
4. [ ] README.md entry remains accurate
5. [ ] Validate with quick_validate.py
---
## CLI Options Reference
| Option | Flag | Description |
| ------ | ---- | ----------------------------------- |
| Title | `-t` | Recording title (for asciinema.org) |
| Quiet | `-q` | Suppress status messages |
| Append | `-a` | Append to existing recording |
---
## Troubleshooting
### "Cannot record from within Claude Code"
**Cause**: asciinema must wrap the program, not be started from inside.
**Fix**: Exit Claude Code first, then run the generated command.
### "Recording file too large"
**Cause**: Long sessions produce large files.
**Fix**:
- Use `asciinema upload` to store online instead of locally
- Split long sessions into smaller recordings
### "Playback shows garbled output"
**Cause**: Terminal size mismatch.
**Fix**: Use `-r` flag during playback to resize terminal.
---
## Reference Documentation
- [asciinema rec Usage](https://docs.asciinema.org/manual/cli/usage/)
- [asciinema CLI Options](https://man.archlinux.org/man/extra/asciinema/asciinema-rec.1.en)
- [asciinema Markers](https://docs.asciinema.org/manual/cli/markers/)Related Skills
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
mcp-create-declarative-agent
Skill converted from mcp-create-declarative-agent.prompt.md
MCP Architecture Expert
Design and implement Model Context Protocol servers for standardized AI-to-data integration with resources, tools, prompts, and security best practices
mathem-shopping
Automatiserar att logga in på Mathem.se, söka och lägga till varor från en lista eller recept, hantera ersättningar enligt policy och reservera leveranstid, men lämnar varukorgen redo för manuell checkout.
math-modeling
本技能应在用户要求"数学建模"、"建模比赛"、"数模论文"、"数学建模竞赛"、"建模分析"、"建模求解"或提及数学建模相关任务时使用。适用于全国大学生数学建模竞赛(CUMCM)、美国大学生数学建模竞赛(MCM/ICM)等各类数学建模比赛。
matchms
Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.
managing-traefik
Manages Traefik reverse proxy for local development. Use when routing domains to local services, configuring CORS, checking service health, or debugging connectivity issues.
managing-skills
Install, find, update, and manage agent skills. Use when the user wants to add a new skill, search for skills that do something, check if skills are up to date, or update existing skills. Triggers on: install skill, add skill, get skill, find skill, search skill, update skill, check skills, list skills.
manage-agents
Create, modify, and manage Claude Code subagents with specialized expertise. Use when you need to "work with agents", "create an agent", "modify an agent", "set up a specialist", "I need an agent for [task]", or "agent to handle [domain]". Covers agent file format, YAML frontmatter, system prompts, tool restrictions, MCP integration, model selection, and testing.
maintainx-automation
Automate Maintainx tasks via Rube MCP (Composio). Always search tools first for current schemas.
mailsoftly-automation
Automate Mailsoftly tasks via Rube MCP (Composio). Always search tools first for current schemas.
mails-so-automation
Automate Mails So tasks via Rube MCP (Composio). Always search tools first for current schemas.