AugmentClaude

Recording Analyzer

Extract keywords and patterns from converted text recordings.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/analyze-terrylica/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Semantic analysis of converted recordings. TRIGGERS - analyze cast, keyword extraction, find patterns.

What this skill does

/asciinema-tools:analyze

Run semantic analysis on converted .txt recordings.

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.

Arguments

ArgumentDescription
filePath to .txt file
-d, --domainsDomains: trading,ml,dev,claude
-t, --typeType: curated, auto, full, density
--jsonOutput in JSON format
--mdSave as markdown report
--densityInclude density analysis
--jumpJump to peak section after analysis

Execution

Invoke the asciinema-analyzer skill with user-selected options.

Skip Logic

  • If file provided -> skip Phase 1 (file selection)
  • If -t provided -> skip Phase 2 (analysis type)
  • If -d provided -> skip Phase 3 (domain selection)
  • If --json/--md provided -> skip Phase 6 (report format)
  • If --jump provided -> auto-execute jump after analysis

Workflow

  1. Preflight: Check for .txt file
  2. Discovery: Find .txt files
  3. Selection: AskUserQuestion for file
  4. Type: AskUserQuestion for analysis type
  5. Domain: AskUserQuestion for domains (multi-select)
  6. Curated: Run ripgrep searches
  7. Auto: Run YAKE if selected
  8. Density: Calculate density windows if selected
  9. Format: AskUserQuestion for report format
  10. Next: AskUserQuestion for follow-up action

Examples

# Quick curated analysis for trading domain
/asciinema-tools:analyze session.txt -d trading -t curated

# Full analysis with density and JSON output
/asciinema-tools:analyze session.txt -t full --density --json

# Auto keyword discovery with markdown report
/asciinema-tools:analyze session.txt -t auto --md

Troubleshooting

IssueCauseSolution
ripgrep not foundNot installedbrew install ripgrep
YAKE not availablePython package missinguv pip install yake
No keywords foundWrong domain or sparse contentTry -t auto for discovery

Post-Execution Reflection

After this skill completes, check before closing:

  1. Did the command succeed? — If not, fix the instruction or error table that caused the failure.
  2. Did parameters or output change? — If the underlying tool's interface drifted, update Usage examples and Parameters table to match.
  3. Was a workaround needed? — If you had to improvise (different flags, extra steps), update this SKILL.md so the next invocation doesn't need the same workaround.

Only update if the issue is real and reproducible — not speculative.

Related skills