reflect-skills-from-memory

Reconciles persistent memory feedback against live skill files and applies verified fixes.

588|49|Updated Aug 4, 2025
One-click install
npx skills add https://github.com/FradSer/dotclaude --skill reflect-skills-from-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reflect-skills-from-memory
Source: https://github.com/FradSer/dotclaude/tree/main/.claude/skills/reflect-skills-from-memory
Command: npx skills add https://github.com/FradSer/dotclaude --skill reflect-skills-from-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Accumulated memory feedback about a Claude Code plugin marketplace's skills drifts out of sync with the actual code, so remembered problems may already be fixed or wrongly recorded. This Skill closes the loop by re-verifying every remembered claim against live files before changing anything.

Core Features & Use Cases

  • Memory-driven audit: Loads MEMORY.md and feedback_*.md files from the per-project memory directory and extracts concrete, checkable claims about skills.
  • Verify-before-fix workflow: Classifies each claim as STILL-BROKEN, ALREADY-FIXED, WRONG, or NOT-APPLICABLE by inspecting the actual SKILL.md and plugin.json files.
  • Bidirectional correction: Fixes stale skills (promoting soft rules into CRITICAL blocks, adding missing hooks) or corrects stale memory files, then syncs plugin.json and marketplace.json versions.
  • Use Case: After weeks of accumulating feedback like "L3 rules get skipped" in project memory, run this Skill to systematically re-check each claim against the current marketplace plugins and apply only the fixes that are still needed.

Quick Start

Ask the assistant to reflect on skills from memory and apply outstanding feedback to the marketplace plugins.

Frequently Asked Questions about reflect-skills-from-memory

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

FAQPage Schema
How do I apply accumulated memory feedback to Claude Code skills?

Invoke this Skill in the plugin marketplace repository. It reads MEMORY.md and feedback_*.md files from the per-project memory directory, extracts checkable claims, verifies each against live skill files, and fixes whichever side is wrong.

How does the skill verify remembered problems before editing?

It reads the actual SKILL.md or plugin.json each memory points at, greps for the reported soft prose or missing hook, and classifies the claim as STILL-BROKEN, ALREADY-FIXED, WRONG, or NOT-APPLICABLE before making any change.

Can this skill fix stale or incorrect memory files?

Yes. When verification shows a memory is outdated or wrong, it updates the memory file's version, date, or claim and keeps the MEMORY.md index line in sync instead of editing the skill.

Does the skill commit the fixes it makes to git?

No. It is explicitly forbidden from running git add, commit, status, or diff. When the user asks to commit skill fixes, it delegates to the /git:commit skill, which handles staging and message generation.

What happens to plugin versions after a skill is fixed?

After editing a plugin's skill, the version in the plugin's plugin.json is bumped and the matching entry in .claude-plugin/marketplace.json is synced so both versions stay equal.