mcpField
A
analyze

analyze

github.com/terrylicaData & databases294 installsUpdated 1d ago
Repository

About analyze

analyze is a skill for semantic analysis of converted `.txt` recordings. It supports domain-specific and automatic analysis, with options for density analysis and JSON or Markdown reports.

Key features

  1. 01Analyzes converted `.txt` recordings
  2. 02Supports trading, ml, dev, and claude domains
  3. 03Offers curated, auto, full, and density types
  4. 04Outputs JSON or Markdown reports
  5. 05Can analyze density and jump to peak sections

Use cases

  1. 01Analyze recordings in the trading domain
  2. 02Discover keywords automatically
  3. 03Generate a JSON or Markdown analysis report

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/terrylica/cc-skills --skill analyze

After installing, type/analyzein Claude Code to confirm it loaded.

Bundled filesreferences/evolution-log.md

Details

From the project README

/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.

Comments

Markdown supported