learn-from-feedback — for Claude Code learn-from-feedback, duklog, community, for Claude Code, ide skills, feedback learning, code improvement, knowledge base updating, coding standards automation, domain knowledge management, Claude Code

v1.0.0
GitHub

このスキルについて

Ideal for Code Review Agents seeking to enhance code quality through iterative learning and feedback incorporation. The learn-from-feedback skill helps developers improve code quality by learning from user feedback, self-observation, and updating the project's knowledge base. This skill benefits developers by preventing recurring issues and improving overall coding standards.

機能

Identify feedback sources using PR comments and self-observation
Classify learning into coding standards, domain knowledge, testing practices, and workflow/process
Apply fixes to code issues and update the knowledge base
Summarize learnings and report updates to the knowledge base

# Core Topics

for Claude Code feedback learning code improvement knowledge base updating coding standards automation domain knowledge management
rubberduck203 rubberduck203
[3]
[0]
Updated: 3/13/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
20
Canonical Locale
en
Detected Body Locale
en

Ideal for Code Review Agents seeking to enhance code quality through iterative learning and feedback incorporation. The learn-from-feedback skill helps developers improve code quality by learning from user feedback, self-observation, and updating the project's knowledge base. This skill benefits developers by preventing recurring issues and improving overall coding standards.

このスキルを使用する理由

Empowers agents to update project knowledge bases by classifying learnings into coding standards, domain knowledge, testing practices, and workflow/process improvements, utilizing files like `.claude/skills/coding-standards/SKILL.md` and `.claude/rules/domain.md`.

おすすめ

Ideal for Code Review Agents seeking to enhance code quality through iterative learning and feedback incorporation.

↓ 実現可能なユースケース for learn-from-feedback

Automating the update of coding standards based on user feedback and self-observation
Generating concise knowledge base entries for domain-specific patterns and testing practices
Debugging recurring issues by applying learnings from feedback to code fixes and workflow adjustments

! セキュリティと制限

  • Requires access to project feedback channels like PR comments and code review findings
  • Needs ability to parse and classify feedback into specific knowledge base categories
  • Should be used conservatively, only saving verified and stable patterns

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is learn-from-feedback?

Ideal for Code Review Agents seeking to enhance code quality through iterative learning and feedback incorporation. The learn-from-feedback skill helps developers improve code quality by learning from user feedback, self-observation, and updating the project's knowledge base. This skill benefits developers by preventing recurring issues and improving overall coding standards.

How do I install learn-from-feedback?

Run the command: npx killer-skills add rubberduck203/duklog/learn-from-feedback. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for learn-from-feedback?

Key use cases include: Automating the update of coding standards based on user feedback and self-observation, Generating concise knowledge base entries for domain-specific patterns and testing practices, Debugging recurring issues by applying learnings from feedback to code fixes and workflow adjustments.

Which IDEs are compatible with learn-from-feedback?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for learn-from-feedback?

Requires access to project feedback channels like PR comments and code review findings. Needs ability to parse and classify feedback into specific knowledge base categories. Should be used conservatively, only saving verified and stable patterns.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add rubberduck203/duklog/learn-from-feedback. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use learn-from-feedback immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Imported Repository Instructions

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

Supporting Evidence

learn-from-feedback

Install learn-from-feedback, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly
Imported Repository Instructions
The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.
Supporting Evidence

Learn from Feedback

When receiving feedback (PR comments, user corrections, code review findings) or observing patterns yourself during implementation, update the project's knowledge base so the same issues don't recur.

Process

  1. Identify the source:
    • User feedback: read PR comments (gh pr view $ARGUMENTS --comments) or parse the correction from context
    • Self-observation: findings from the reflect skill, or patterns noticed during implementation
  2. Classify the learning:
    • Coding standard → update .claude/skills/coding-standards/SKILL.md
    • Domain knowledge → update .claude/rules/domain.md
    • Testing practice → update .claude/rules/testing.md
    • Workflow/process → update CLAUDE.md (Git Workflow section) or relevant skill
    • Project-specific pattern → update auto memory (MEMORY.md)
    • Missed refactoring → add to the "When Touching a File" checklist in .claude/rules/testing.md (test helpers) or .claude/skills/coding-standards/SKILL.md (code patterns) so the pattern fires proactively next time
  3. Apply the fix: If the feedback points to a code issue, fix it
  4. Update the knowledge base: Write the learning to the appropriate file so it persists
  5. Summarize: Report what was learned and where it was saved

Rules

  • Be conservative: only save verified, stable patterns — not one-off corrections
  • Keep entries concise: one bullet point per learning
  • Don't duplicate: check if the learning already exists before adding
  • If unsure where a learning belongs, prefer auto memory (lowest commitment)

関連スキル

Looking for an alternative to learn-from-feedback or another community skill for your workflow? Explore these related open-source skills.

すべて表示

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

カスタマイズ可能なウィジェットプラグインをprompts.chatのフィードシステム用に生成する

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

React フレームワーク

★ 138.4k
⑂ 0
ブラウザ

pr-review

Logo of pytorch
pytorch

Pythonにおけるテンソルと動的ニューラルネットワーク（強力なGPUアクセラレーション）

★ 98.6k
⑂ 0
開発者