skills.rest
langware-labs
langware-labsOFFICIAL
Explore all skills by this author →
GitHub

workflow_learning

Analyze workflow trace JSONL files to update markdown memory and generate feedback.

5|1|Updated Mar 15, 2026
Search Tags:#automation#workflow#feedback#analysis#learning
One-click install
npx skills add https://github.com/langware-labs/flowpad --skill workflow-learning
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: workflow_learning
Source: https://github.com/langware-labs/flowpad/tree/main/flow_sdk/system_projects/flowpad_assistant/.claude/skills/workflow_learning
Command: npx skills add https://github.com/langware-labs/flowpad --skill workflow-learning

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps improve workflow efficiency by analyzing recent run data, updating persistent memory, and providing actionable feedback to avoid repeated issues.

Core Features & Use Cases

  • Analyze Workflow Runs: Reads workflow trace and analysis JSONL files to identify errors and patterns.
  • Update Memory: Synthesizes findings to improve the next execution’s guidance, capturing lessons and pitfalls.
  • Provide Feedback: Generates feedback based on recurring issues, assisting in workflow debugging and refinement.

Quick Start

Provide pathways to analyze recent run files, update memory documentation, and generate improvement suggestions for ongoing workflow optimization.

Frequently Asked Questions about workflow_learning

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

FAQPage Schema
How do I analyze workflow trace files to improve automation efficiency?▼

To analyze workflow trace files, you parse JSONL execution logs to identify recurring errors and patterns. This synthesis updates workflow memory and generates feedback to prevent repeated issues in future automation runs.

What is the best way to update workflow memory after an AI-assisted process execution?▼

The best way to update workflow memory is by synthesizing recent execution insights from analysis files into markdown-based logs. This captures lessons learned and modifies persistent memory to guide the next execution effectively.

Can I use JSONL execution logs for workflow debugging and refinement?▼

Yes, you can use JSONL execution logs for workflow debugging by analyzing trace files to identify errors. The process synthesizes these findings to generate feedback for refining and improving your automation workflows.

How does synthesizing workflow analysis files prevent recurring automation issues?▼

Synthesizing workflow analysis files prevents recurring automation issues by extracting patterns from trace data and updating persistent markdown memory. This ensures past pitfalls are captured to guide and optimize subsequent executions.

Do I need markdown memory files to generate feedback for workflow optimization?▼

Yes, you need markdown-based memory files to store synthesized insights from JSONL traces. Modifying these memory logs ensures that generated feedback is persistently captured for ongoing workflow optimization and debugging.

Related Skills

Explore More Product & Management Skills→
rysweetrysweet
1

session-replay

Analyze claude-trace JSONL files for session health, token usage, and error patterns.

Community
Intermediate
henrique-simoeshenrique-simoes
13

prototype-feedback

Process prototype feedback into thematically organized insights across iterations.

Community
Intermediate
kk580kkkk580kk
1

experimental-memory-status

Monitor in-house memory system health via process, database, and log queries.

Community
Intermediate
zhuanggenhuazhuanggenhua
19

planning-with-files

Manage task plans, findings, and progress logs in markdown files.

Community
Advanced