episode-complete

Complete learning episodes by scoring outcomes, extracting patterns, and updating heuristics.

11|Updated Nov 5, 2025

Search Tags:#heuristics #learning #patterns #memory #episode #complete

Ready to run

npx skills add https://github.com/d-o-hub/rust-self-learning-memory --skill episode-complete

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: episode-complete
Source: https://github.com/d-o-hub/rust-self-learning-memory/tree/main/.claude/skills/episode-complete
Command: npx skills add https://github.com/d-o-hub/rust-self-learning-memory --skill episode-complete

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill completes and scores a learning episode, extracts patterns, and updates heuristics to improve future tasks.

Core Features & Use Cases

Outcome scoring: verdict, time, tokens, and artifacts recorded.
Reflection & learning: what worked, what to improve, key learnings.
Pattern extraction: tool sequences, decision points, and error patterns.

Quick Start

Call complete_episode with the episode_id and a constructed TaskOutcome; allow system to derive patterns and heuristics.

Frequently Asked Questions about episode-complete

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

FAQPage Schema

How do I extract patterns and learnings from completed tasks?▼

Pattern extraction captures tool sequences, decision points, and error patterns from task episodes. After completing a task, the episode-complete Skill scores outcomes (verdict, time, tokens, artifacts) and generates reflections that identify what worked and what to improve, then stores these patterns for future retrieval and heuristic updates.

What data does outcome scoring capture in learning episodes?▼

Outcome scoring records verdict, execution time in milliseconds, token usage, generated artifacts, and errors encountered. This outcome data feeds into reward scoring and reflection generation, which extract actionable patterns to refine future task performance.

How do I update heuristics based on episode completion?▼

When you call complete_episode with a constructed TaskOutcome, the Skill derives patterns from tool sequences and decision points, computes a RewardScore, generates reflections on successes and gaps, then updates persistent storage and indices. This feeds learned heuristics back into the system.

Can episode-complete work with any task type or workflow?▼

Episode-complete applies during post-task closure across learning episodes regardless of task type. It requires a constructed TaskOutcome with outcome data; the Skill then handles pattern extraction, reflection, and heuristic updates automatically without dependencies on specific frameworks or components.

What's the difference between reflection and pattern extraction in episode completion?▼

Reflection documents what worked and what to improve—high-level learnings from the episode. Pattern extraction identifies reusable structures: tool sequences (how tools were chained), decision points (where choices mattered), and error patterns (failure modes). Both update persistent storage for future tasks.