asciinema-recorder
Record Claude Code sessions with asciinema. TRIGGERS - record session, asciinema record, capture terminal, demo recording.
What this skill does
# 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)
> **Self-Evolving Skill**: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
## When to Use This Skill
Use this skill when:
- Starting a new terminal recording session
- Creating demos or documentation recordings
- Capturing Claude Code sessions for review or sharing
- Generating workspace-specific recording filenames
---
## 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 tRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.