// Analyze pi/codex/claude session transcripts to discover patterns, skills, and model performance correlations. Mines usage history for automation opportunities and tracks model quality by time of day.
Create or revise RFCs and ADRs using Lawbot-Hub templates, strong in-repo examples, and concrete failure-mode examples. Use when drafting, reviewing, or tightening RFC/ADR documents, or when assessing RFC/ADR quality.
Generates TRMNL-compatible e-ink display images. Use when creating images for TRMNL devices, converting images to 1-bit format, or uploading content to e-ink displays. Triggers on "TRMNL", "e-ink", "e-paper", "terminal display".
Convert documents and files to useful Markdown using the installed markitdown and markit CLIs. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images, audio, ZIP archives, YouTube URLs, or EPubs to Markdown, when choosing between markit and markitdown for better extraction quality, when comparing PDF extraction results, or when OCR may be needed for scanned or image-heavy PDFs.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an AI coding agent's capabilities with specialized knowledge, workflows, or tool integrations.
Render inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly in the conversation. Use this skill whenever the user asks to visualize, diagram, chart, illustrate, or explain something visually, or when an explanation would genuinely benefit from a spatial or interactive diagram rather than text. Also triggers for flowcharts, architecture diagrams, data visualizations, interactive explainers, comparison layouts, UI mockups, and requests containing 'show me', 'draw', 'map out', 'visualize', or 'diagram'.
This skill should be used when creating commits or pull requests, enforcing a human-written PR structure, intent capture, and evidence in agentic workflows.
| name | session-analyzer |
| description | Analyze pi/codex/claude session transcripts to discover patterns, skills, and model performance correlations. Mines usage history for automation opportunities and tracks model quality by time of day. |
Two tools for session analysis:
Analyzes frustration signals across all sessions (pi, codex, claude) correlated with time of day and model.
# Run analysis (outputs to ./model-performance-analysis/)
~/code/research/pi-skills/session-analyzer/model-performance.js
# Custom output directory
~/code/research/pi-skills/session-analyzer/model-performance.js /path/to/output
Outputs:
report.md — full analysis with ASCII chartschart.html — interactive browser chartsdata.csv — raw data for external graphingmodel-stats.json — aggregated stats per modelKey metrics:
Extracts transcripts and optionally spawns subagents to find automation opportunities.
# Extract transcripts for current directory
~/code/research/pi-skills/session-analyzer/analyze.js
# Extract transcripts for specific directory
~/code/research/pi-skills/session-analyzer/analyze.js /path/to/project
# Extract + analyze with subagents
~/code/research/pi-skills/session-analyzer/analyze.js --analyze
# Custom output directory
~/code/research/pi-skills/session-analyzer/analyze.js --output ./my-analysis --analyze
~/.pi/agent/sessions/Without --analyze:
session-transcripts/
├── session-transcripts-000.txt
├── session-transcripts-001.txt
└── ...
With --analyze:
session-transcripts/
├── session-transcripts-000.txt
├── session-transcripts-000.summary.txt # Pattern analysis
├── session-transcripts-001.txt
├── session-transcripts-001.summary.txt
└── FINAL-SUMMARY.txt # Aggregated findings
Install dependencies (run once):
cd ~/code/research/pi-skills/session-analyzer
npm install
Source: ferologics/pi-skills Originally adapted from badlogic/pi-mono gist