session-analysis

Analyze cross-session Claude Code digests and propose SKILL.md diffs.

Updated Mar 28, 2026
One-click install
npx skills add https://github.com/skaile-ai/ai-assets --skill session-analysis-skaile-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-analysis
Source: https://github.com/skaile-ai/ai-assets/tree/main/skaile-development/skills/session-analysis
Command: npx skills add https://github.com/skaile-ai/ai-assets --skill session-analysis-skaile-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cross-session analysis of Claude Code session data for the skaile-dev monorepo. It reads a pre-computed digest (≤10KB) from the Python pipeline, triages improvement opportunities, reads implicated SKILL.md files, and proposes concrete diffs to reduce token waste and improve workflow adherence. Run after ./run.sh in _scripts/session-analysis/.

Core Features & Use Cases

  • Cross-session triage of token waste across multiple sessions.
  • Proposes concrete SKILL.md diffs to improve workflow adherence.
  • Reads and references implicated SKILL.md files to drive targeted improvements.

Quick Start

Run the digest pipeline to generate analyses, then run this skill to triage improvements and propose SKILL.md diffs.

Frequently Asked Questions about session-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze Claude Code session data to find token waste?

Cross-session analysis triages token waste by reading a pre-computed digest from the Python pipeline across multiple Claude Code sessions. It validates the digest, reads implicated SKILL.md files, and proposes concrete diffs to reduce token usage.

What's the best way to reduce token usage in SKILL.md files?

To reduce token usage in SKILL.md files, analyze session data to triage improvement opportunities, then propose targeted edits to the implicated files. This skill generates concrete diffs without applying changes automatically.

Do I need to run a script before analyzing cross-session token usage?

Yes, you must run ./run.sh in _scripts/session-analysis/ to generate the pre-computed digest before starting cross-session analysis. The skill reads this digest to identify token-waste opportunities and propose SKILL.md improvements.

Can I automatically apply SKILL.md diffs generated from session analysis?

No, the session analysis proposes concrete SKILL.md diffs to reduce token waste but does not apply changes automatically. You receive targeted improvement proposals to review and implement manually across your sessions.

How does cross-session triage improve workflow adherence?

Cross-session triage improves workflow adherence by analyzing token-waste patterns across multiple sessions and proposing concrete SKILL.md diffs. It reads implicated files to drive targeted optimizations for better token efficiency.