skills.rest
slbug
slbugCOMMUNITY
Explore all skills by this author →
GitHub

session-scan

Compute exploratory metrics from Claude session transcripts to triage and rank sessions.

7|Updated Mar 22, 2026
Search Tags:#analytics#claude#triage#session-analysis#ccrider#friction-score#plugin-opportunity
One-click install
npx skills add https://github.com/slbug/claude-ruby-grape-rails --skill session-scan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: session-scan
Source: https://github.com/slbug/claude-ruby-grape-rails/tree/main/.claude/skills/session-scan
Command: npx skills add https://github.com/slbug/claude-ruby-grape-rails --skill session-scan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill computes deterministic exploratory metrics from Claude session transcripts so contributors can triage, rank, and prioritize sessions for deeper review rather than relying on anecdotal signals or manual inspection.

Core Features & Use Cases

  • Provider-scoped discovery and filtering: discover recent sessions via ccrider when available and restrict analysis to a single provider or project to avoid mixed-provider bias.
  • Deterministic scoring via canonical script: uses references/compute-metrics.py to compute friction, fingerprint, plugin opportunity, tool profile, file hotspots, and session duration.
  • Scalable, safe orchestration: deduplicates against an append-only ledger, spawns one lightweight subagent per session to avoid fetching large transcripts in the main context, supports listing, rescan, and writing scan metadata for trends.
  • Use Case: run a scan to surface recent claude-code sessions with high friction scores and identify candidates for manual deep dive and verification.

Quick Start

Run /session-scan --since 7 days ago --provider claude-code to generate a triage table of recent sessions and append results to .claude/session-metrics/metrics.jsonl.

Frequently Asked Questions about session-scan

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

FAQPage Schema
How do I analyze Claude session transcripts to identify high-friction interactions?▼

To analyze Claude session transcripts for friction, you compute deterministic exploratory metrics using a canonical scoring script. This generates a triage table ranking sessions by friction score to prioritize transcripts for deeper manual review based on tool profiles and file hotspots.

What is the best way to triage and rank Claude Code sessions without loading large transcripts into the main context?▼

To triage and rank Claude Code sessions without loading large transcripts in the main context, spawn one lightweight subagent per session. This approach computes friction scores and plugin opportunities while keeping the main context clear of large transcript fetches.

Do I need the ccrider MCP to scan and filter recent Claude sessions by provider?▼

Access to the ccrider MCP is required for interactive discovery and provider-scoped filtering of recent sessions. If unavailable, you can manually provide transcript inputs to compute the friction and session metrics.

How do I track session analytics trends over time using an append-only ledger?▼

To track session analytics trends over time, compute metrics and append the results to an append-only JSONL ledger file. Deduplication against this ledger supports rescanning sessions while preserving historical scan metadata for longitudinal friction analysis.

What specific metrics does the session analysis compute for Claude transcripts?▼

Session analysis computes deterministic exploratory metrics including friction score, fingerprint, plugin opportunity, tool profile, file hotspots, and session duration. These metrics are calculated via a canonical Python script to surface sessions needing deeper review.

Can I limit a session scan to a single provider or project to avoid mixed-provider bias?▼

You can restrict session scans to a single provider or project to avoid mixed-provider bias. Provider-scoped discovery and filtering restrict the analysis to specific Claude Code transcripts, ensuring accurate triage and ranking results.

Related Skills

Explore More Software Engineering Skills→
oliver-kriskaoliver-kriska
517

find-sessions

Find and analyze Claude Code sessions via the ccrider MCP.

Community
Intermediate
wangrenzhu-olawangrenzhu-ola
2

gh-session-extract

Extract conversation skeletons or error signals from a session JSONL file.

Community
Intermediate
oliver-kriskaoliver-kriska
517

analyze-session

Analyze Claude Code sessions to identify workflow patterns and friction points.

Community
Advanced
alex-voloshin-devalex-voloshin-dev
2

feedback

Analyze Claude Code JSONL transcripts to categorize workflow failures and plugin anomalies.

Community
Advanced