apply-improvements

Apply prioritized improvement proposals to plugin files with surgical edits.

15|6|Updated May 7, 2026
One-click install
npx skills add https://github.com/MinhThang1009/dotclaude --skill apply-improvements
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: apply-improvements
Source: https://github.com/MinhThang1009/dotclaude/tree/main/plugins/subagent-system/skills/apply-improvements
Command: npx skills add https://github.com/MinhThang1009/dotclaude --skill apply-improvements

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill should be used when the user asks to apply improvement proposals ('apply improvements', 'ap dung improvement proposals') from .claude/improvement-proposals.md (written by pipeline-retrospective) to the plugin files.

Core Features & Use Cases

  • Parse and read improvement proposals from the project root at .claude/improvement-proposals.md.
  • Locate target plugin files based on paths specified in proposals, using the CLAUDE_PLUGIN_ROOT environment variable if available.
  • Automatically apply HIGH and MEDIUM priority proposals, while presenting LOW priority items to the user for confirmation before applying.
  • Ensure changes are surgical: read target files, apply precise edits to descriptions or steps, verify by re-reading, and log what changed.
  • Do not apply changes that delete functionality, alter agent body behavior, or modify more than three files at once; otherwise escalate for manual review.

Quick Start

Run the apply-improvements skill to automatically apply HIGH and MEDIUM priority proposals from .claude/improvement-proposals.md to your plugin files.

Frequently Asked Questions about apply-improvements

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

FAQPage Schema
How do I automatically apply improvement proposals to plugin files?

To automatically apply improvement proposals to plugin files, use a skill that parses proposals from your project workspace and applies surgical code edits to target plugin paths. It enforces priority levels and performs safety checks before modifying files.

What are the safety limits for applying automated code edits to plugins?

Automated code edits to plugins have strict safety limits: the process prevents destructive updates, refuses to alter agent body behavior, and blocks changes that modify more than three files at once. It flags complex items for manual review instead of applying them.

How does priority-based automation handle LOW priority improvement proposals?

Priority-based automation automatically applies HIGH and MEDIUM priority proposals, but pauses and presents LOW priority items to the user for confirmation before applying any changes. This ensures risky edits receive manual approval.

Do I need a specific environment variable to locate target plugin files for workflow automation?

Yes, workflow automation uses the CLAUDE_PLUGIN_ROOT environment variable to locate target plugin files if available. Proposals specify file paths, and the system reads and edits these files precisely within the project workspace.

How are surgical code edits verified after applying changes to plugin files?

Surgical code edits are verified by re-reading target files immediately after applying precise modifications. The system then logs what changed to ensure descriptions or steps were updated correctly without breaking existing functionality.