skills.rest
AndreJorgeLopes
AndreJorgeLopesCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

session-summary

Generate structured session summaries with scored metrics for AI-assisted coding sessions.

1|Updated Mar 3, 2026
Search Tags:#debugging#observability#developer productivity#langfuse#session summary#quality scoring#agent tracing
One-click install
npx skills add https://github.com/AndreJorgeLopes/devflow --skill session-summary-andrejorgelopes
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: session-summary
Source: https://github.com/AndreJorgeLopes/devflow/tree/main/skills/session-summary
Command: npx skills add https://github.com/AndreJorgeLopes/devflow --skill session-summary-andrejorgelopes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you avoid losing observability when AI coding agents finish work without a clear, structured record of what happened, what changed, and how well the session performed.

Core Features & Use Cases

  • Structured session summaries: Extracts goal, outcome, actions taken, decisions, errors, and metrics into a consistent report format.
  • Quality scoring for process improvement: Rates efficiency, correctness, and process compliance to highlight where workflows improved or degraded.
  • Langfuse tracing when available: Logs the summary and scored metrics to Langfuse for filtering and historical review.

Quick Start

Run the session-summary skill after your agent completes a work session to generate a Langfuse-ready session report with actions, decisions, errors, and a quality score.

Frequently Asked Questions about session-summary

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

FAQPage Schema
How do I generate a session summary with quality scoring for AI-assisted coding agents?▼

Generate a session summary by running the skill after your AI coding agent completes its work. It extracts actions, decisions, errors, and metrics, then applies quality scoring to rate efficiency, correctness, and process compliance.

Can I log agent tracing data and session metrics to Langfuse?▼

Yes, you can log agent tracing data to Langfuse. The session summary optionally logs extracted outcomes, tool usage, and scored metrics to Langfuse for filtering, observability, and historical review.

What is the best way to record agent tracing outcomes and file activity for later review?▼

The best way to record outcomes is to extract structured session data after work completion. This captures the goal, outcome, file and command activity, tool usage, and error resolution into a consistent report format.

Do I need Langfuse installed to extract structured session data and evaluate agent quality?▼

No, you do not need Langfuse installed to extract structured session data. Langfuse integration is optional for logging summaries and scored metrics, while core extraction and quality scoring work independently.

What limitations exist when debugging AI coding sessions without observability summaries?▼

Without observability summaries, you lose structured records of decisions, file changes, and errors. This makes it difficult to track agent tracing, review historical performance, or identify workflow degradation across coding sessions.

Does the session-summary skill support observability for developer productivity tracking?▼

Yes, the session-summary skill supports observability for developer productivity. It captures actions, decisions, and errors, then scores efficiency and process compliance to highlight where workflows improved or degraded.

Related Skills

Explore More Data & Analytics Skills→
bitwardenbitwarden
129

extracting-session-data

Extract structured data from Claude Code session logs via command-line scripts.

Official
Intermediate
portermetricsampleportermetricsample
17

quality-score-trend

Analyze historical Google Ads Quality Score trends to attribute declines to specific components.

Community
Advanced
InnerScopeHearingInnerScopeHearing

fleet-telemetry

Capture Claude Code session metrics and forward them to PostHog.

Official
Advanced
LerianStudioLerianStudio
205

dev-feedback-loop

Automate development-cycle metrics collection and generate improvement reports.

Official
Advanced