autoskill

Analyzes coding sessions to extract durable preferences and proposes edits to Skill files.

2|Updated Feb 14, 2026
One-click install
npx skills add https://github.com/Gamaroff/agent-skills --skill autoskill-gamaroff
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: autoskill
Source: https://github.com/Gamaroff/agent-skills/tree/main/skills/autoskill
Command: npx skills add https://github.com/Gamaroff/agent-skills --skill autoskill-gamaroff

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Feedback given during a coding session is usually lost once the session ends, forcing users to repeat the same corrections. This Skill captures durable preferences from corrections and approvals and codifies them into the Skill files that were active, so the agent improves across sessions. ## Core Features & Use Cases - Signal Detection: Scans sessions for corrections, repeated patterns, and approvals while filtering out one-off or ambiguous feedback. - Quality Filtering: Applies a four-question test to ensure only new, actionable, project-specific information is captured. - Reviewed Proposals: Maps signals to the relevant SKILL.md files and presents HIGH/MEDIUM confidence edits for explicit approval before applying. - Use Case: After a session where you corrected the agent twice to use cn() instead of clsx(), ask it to learn from the session and it will propose a minimal, reversible edit to the appropriate Skill file. ## Quick Start Ask the agent to learn from this session and update the skills based on the corrections you gave.

Frequently Asked Questions about autoskill

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

FAQPage Schema
How do I make an AI coding agent remember my preferences?▼

Trigger autoskill after a session by asking it to learn from the session or remember a pattern. It detects your corrections, filters for durable preferences, and proposes edits to the relevant Skill files for your approval.

What kinds of feedback get saved as skill updates?▼

Corrections stated as general rules, feedback repeated two or more times, and project-specific conventions like custom utility locations or team preferences. One-off, ambiguous, or contradictory signals are ignored or clarified first.

Does autoskill edit skill files automatically?▼

No. It always presents a summary of HIGH and MEDIUM confidence proposals and waits for explicit approval before editing any file. Changes are minimal, additive, and committed with a chore(autoskill) message when git is available.

What is the difference between autoskill and observe-work?▼

autoskill is an explicit, on-demand pass that proposes edits to skills active in the current session. observe-work runs continuously and writes observations to a durable log for later review; the two are complements.

When should I not use session-based skill learning?▼

Avoid it for one-off, context-specific corrections or when feedback is ambiguous or contradictory. General best practices and standard framework conventions are also excluded since they apply to any project.