ai-learn
Learns from PR review feedback to suggest updates to project standards and LESSONS.md.
Install
mkdir -p .claude/skills/ai-learn && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9549" && unzip -o skill.zip -d .claude/skills/ai-learn && rm skill.zipInstalls to .claude/skills/ai-learn
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Extracts lessons from merged PR review feedback by analyzing what reviewers caught, identifying missed checks, and writing entries directly to LESSONS.md. Trigger for 'the AI keeps doing X wrong', 'learn from this PR', 'what patterns did reviewers catch', 'update our standards from feedback'. Not for in-session observation; use /ai-session-watch instead. Not for skill-level rewrites; use /ai-skill-improve instead.Key capabilities
- →Analyze PR feedback
- →Identify missed checks
- →Write lessons
- →Draft AGENTS.md proposals
How it works
Analyzes PR reviews to extract actionable patterns and updates project knowledge bases.
Inputs & outputs
When to use ai-learn
- →Analyzing PR feedback
- →Updating project coding standards
- →Learning from past mistakes
About ai-learn
Analyzes review feedback from PRs to extract patterns and lessons learned. It automates the process of updating project knowledge bases to improve future AI output quality.
Extracts lessons from merged PR review feedback by analyzing what reviewers caught, identifying missed checks, and writing entries directly to LESSONS.md. Trigger for 'the AI keeps doing X wrong', 'learn from this PR', 'what patterns did reviewers catch', 'update our standards from feedback'. Not fo
When not to use it
- →In-session observation
- →Skill-level rewrites
Limitations
- →Only write lessons for repeatable patterns
- →Never edit AGENTS.md directly
How it compares
Automates the feedback loop to improve AI output quality over time.
Compared to similar skills
ai-learn side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ai-learn (this skill) | 0 | 2mo | No flags | Intermediate |
| deepwiki-rs | 25 | 9mo | Review | Intermediate |
| python-code-style | 9 | 6mo | Review | Intermediate |
| code-review-excellence | 19 | 5mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by arcasilesgroup
View all by arcasilesgroup →You might also like
deepwiki-rs
sopaco
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.
python-code-style
wshobson
Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.
code-review-excellence
wshobson
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
code-walk-thru
pchalasani
Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.
cookbook-audit
anthropics
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
schema-markup
davila7
When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.