try-learn-skill

Evaluate completed feature artifacts to extract reusable procedures for learned skills.

1|Updated Apr 22, 2026

Search Tags:#workflow analysis #git diff #ledger #feature artifacts #learned skills #skill extraction

Ready to run

npx skills add https://github.com/AbsolutSystems/absolutpowers --skill try-learn-skill

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: try-learn-skill
Source: https://github.com/AbsolutSystems/absolutpowers/tree/main/claude/skills/try-learn-skill
Command: npx skills add https://github.com/AbsolutSystems/absolutpowers --skill try-learn-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps decide whether a finished feature contains a repeatable procedure worth turning into a learned skill, instead of capturing obvious one-off work that will not help next time.

Core Features & Use Cases

Candidate evaluation: Reviews planning, task artifacts, and git diffs to judge whether a workflow is truly reusable.
High-threshold filtering: Rejects generic implementation steps and only keeps non-obvious procedures with durable value.
Ledger-first learning: Records first sightings as candidates, promotes repeated patterns into learned skills, and avoids collisions with existing static skills.
Use case: After a feature is complete, use this Skill to determine whether the team discovered a reliable procedure for future projects or just completed normal engineering work.

Quick Start

Ask this Skill to review the completed feature artifacts and tell you whether there is a reusable procedure to learn.

Frequently Asked Questions about try-learn-skill

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

FAQPage Schema

How do I extract reusable skills from completed feature artifacts and git diffs?▼

Workflow analysis identifies reusable procedures by reviewing planning docs, task files, and git diffs from finished work. It applies high-threshold filtering to reject generic implementation steps, keeping only non-obvious procedures with durable value for future projects.

When should I turn completed engineering work into a learned skill?▼

Turn completed work into a learned skill when post-implementation analysis of artifacts reveals a non-obvious, repeatable procedure. If the feature only involved normal engineering work without durable patterns, it should not be promoted to a learned skill.

How do I track learned skills and avoid collisions with existing static skills?▼

Track learned skills via a ledger that records first sightings of patterns as candidates. Repeated patterns are promoted into learned skills only after passing collision checks against existing static skills and receiving explicit human approval.

What is the best way to filter generic implementation steps during skill extraction?▼

The best way to filter generic implementation steps is applying high-threshold criteria during workflow analysis. Reject obvious one-off work and retain only non-obvious procedures that demonstrate durable, repeatable value for future engineering projects.

Does promoting a reusable workflow into a learned skill require human approval?▼

Yes, promoting a reusable workflow into a learned skill requires human approval. The ledger-first learning process records candidates, checks for collisions with existing skills, and mandates explicit human approval before creating any new learned skill.