Help us improve
Share bugs, ideas, or general feedback.
From mem0
Analyse the current state of the mem0 memory database and produce an improvement report. Use when the user asks about memory quality, duplicate memories, or wants to audit what mem0 has stored.
npx claudepluginhub wuffig-coding-solutions/mem0-pluginHow this skill is triggered — by the user, by Claude, or both
Slash command
/mem0:memory-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyse the current state of the mem0 memory database and produce an
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Explores codebases via GitNexus: discover repos, query execution flows, trace processes, inspect symbol callers/callees, and review architecture.
Share bugs, ideas, or general feedback.
Analyse the current state of the mem0 memory database and produce an
improvement report. Called as /mem0:audit or invoked automatically
when the user asks about memory quality.
Retrieve all memories for the current user:
from mem0 import MemoryClient
import os
client = MemoryClient(api_key=os.environ["MEM0_API_KEY"])
user_id = os.environ.get("MEM0_USER_ID", "user")
agent_id = os.environ.get("MEM0_AGENT_ID", "")
user_mems = client.get_all(filters={"user_id": user_id})
proj_mems = client.get_all(filters={"user_id": user_id, "agent_id": agent_id}) if agent_id else {"results": []}
Evaluate quality across these dimensions:
Atomicity — Is each memory a single, self-contained fact? Flag: memories with conjunctions ("and", "also", "but") that could be split.
Specificity — Are memories concrete enough to be useful? Flag: vague entries like "we discussed authentication" or "there was an issue".
Duplicates — Are there semantically redundant memories? Flag: pairs with >80% semantic overlap.
Staleness — Do any memories reference things likely outdated? Flag: version numbers, dates, or "current" references.
Extraction gaps — What important patterns appear in conversation that are NOT in memory? (Review last 5 conversation turns if available.)
Produce a structured report:
## Memory Audit Report
### Summary
- Total memories: N user-scope, M project-scope
- Quality score: X/10
### Issues Found
[List each issue with: memory text, issue type, suggested fix]
### Extraction Prompt Assessment
[Is the current extraction prompt capturing the right things?
What category of facts is missing or overrepresented?]
### Recommended Changes
1. Split: "[memory text]" → "[fact 1]" + "[fact 2]"
2. Delete: "[memory text]" — reason
3. Update extraction prompt: add/remove/change rule X
Ask the user if they want to apply the suggested changes.
If yes, update memories via client.update() or client.delete().
hooks/stop.py as EXTRACTION_PROMPT.
If changes are recommended, show the exact diff.