Two-tier memory system that makes Claude a workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. Use when resolving unknown names, terms, or acronyms, or when the user asks to "remember this", "who is X", "what does X mean", or when updating memory after a session.
From nudesk-osnpx claudepluginhub nudesk/nudesk-os-plugin --plugin nudesk-osThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Memory makes Claude your workplace collaborator — someone who speaks your internal language.
Transform shorthand into understanding:
User: "follow up with Sarah about the SOW"
-> Claude decodes
"Follow up with Sarah Chen (Acme Corp) about the
Statement of Work (rescheduled from last Tuesday)"
~/.claude/CLAUDE.md <- Hot cache (Working Memory section)
~/.claude/memory/
glossary.md <- Full decoder ring (everything)
people/ <- Complete profiles
projects/ <- Project details
context/ <- Company, teams, tools
CLAUDE.md (Hot Cache):
~/.claude/memory/glossary.md (Full Glossary):
~/.claude/memory/people/, projects/, context/:
User mentions an unknown name/term/acronym
1. Check ~/.claude/CLAUDE.md Working Memory section
-> Covers 90% of daily cases
2. If not found -> read ~/.claude/memory/glossary.md
-> Full glossary has everyone/everything
3. If still not found -> check ~/.claude/memory/people/ or projects/
-> Rich detail files
4. If still not found -> ask user
-> "What does X mean? I'll remember it."
When user says "remember this" or new context emerges:
Glossary items (acronyms, terms, shorthand):
~/.claude/memory/glossary.mdPeople:
~/.claude/memory/people/{name}.mdProjects:
~/.claude/memory/projects/{name}.mdPreferences: Add to CLAUDE.md Preferences section
When user asks "who is X" or "what does X mean":
~/.claude/memory/ for full detailPromote to CLAUDE.md when:
Demote to ~/.claude/memory/ only when:
This keeps CLAUDE.md fresh and relevant.
project-name.md, person-name.md)~/.claude/memory/ only