wfc-retro

Analyze WFC telemetry data to identify performance trends and bottlenecks.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/sam-fakhreddine/wfc --skill wfc-retro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wfc-retro
Source: https://github.com/sam-fakhreddine/wfc/tree/main/wfc/skills/wfc-retro
Command: npx skills add https://github.com/sam-fakhreddine/wfc --skill wfc-retro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the analysis of WFC telemetry data to identify workflow bottlenecks, performance trends, and areas for continuous improvement, transforming raw data into actionable insights for team retrospectives.

Core Features & Use Cases

  • Telemetry Analysis: Aggregates and analyzes WFC telemetry logs (wfc-*.WNN.jsonl).
  • Bottleneck Detection: Identifies slow or failing tasks and common failure modes.
  • Performance Trends: Analyzes patterns in agent performance, review quality, and task completion times.
  • Values Alignment: Tracks adherence to TEAMCHARTER values using Say:Do ratios and specific value impact.
  • Recommendation Generation: Provides concrete, actionable recommendations for workflow optimization.
  • Use Case: After a sprint, use this Skill to generate a comprehensive retrospective report that highlights what went well, what didn't, and provides data-backed suggestions for the next sprint.

Quick Start

Run a retrospective analysis for the last 7 days using the /wfc-retro command.

Frequently Asked Questions about wfc-retro

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

FAQPage Schema
How do I automate retrospective analysis on team telemetry data?

AI-powered retrospective analysis automates the review of WFC telemetry data to identify performance trends and workflow bottlenecks. It aggregates logs and analyzes task completion times to generate actionable recommendations for continuous improvement.

How do I track team values alignment using Say:Do ratios?

Say:Do ratios track adherence to TEAMCHARTER values by comparing commitments against completed tasks. Specific Python scripts compute these ratios and generate values alignment charts, revealing gaps between stated intentions and actual workflow outcomes.

What is the best way to detect workflow bottlenecks in agent performance?

Workflow bottlenecks are detected by analyzing telemetry logs for slow or failing tasks and common failure modes. This retrospective approach evaluates review quality and agent performance patterns to pinpoint areas requiring optimization.

Can I generate retrospective reports from WFC telemetry logs?

Yes, retrospective reports are generated by aggregating WFC telemetry logs like wfc-*.WNN.jsonl files. The analysis produces data-backed suggestions highlighting what went well and what failed, providing concrete recommendations for the next sprint.

Do I need Python scripts to analyze task completion times and review quality?

Python scripts are required to compute Say:Do ratios and generate values alignment charts from telemetry data. These scripts process aggregated WFC logs to analyze review quality, task completion times, and agent performance trends.

Why does my telemetry retrospective analysis fail to identify failure modes?

Telemetry retrospective analysis fails to identify failure modes if WFC logs are not properly aggregated. Ensure wfc-*.WNN.jsonl files are correctly collected so the AI analysis can accurately evaluate performance trends and common failure patterns.