From markus
Extract noteworthy items from the current conversation into memory files. Use when a cron notification prompts periodic reflection, or when a decision, preference, or important context is observed.
npx claudepluginhub swen128/markus --plugin markusThis skill uses the workspace's default tool permissions.
These rules are non-negotiable. Violating any of them is a bug.
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.
Performs token-optimized structural code search using tree-sitter AST parsing to discover symbols, outline files, and unfold code without reading full files.
These rules are non-negotiable. Violating any of them is a bug.
.md files allowed in memory/ are YYYY-MM-DD.md. NEVER create topic-based files like memory/feedback_tooling.md or memory/user_role.md.---.- [file.md](memory/file.md) -- description. Use plain - <observation> lines.memory/YYYY-MM-DD.md)Each entry uses an ## HH:MM time header followed by bullet observations:
## 14:30
- User prefers Bun over Node for the test runner
- Team decided on tabs over spaces
MEMORY.md)Append significant items under a ## YYYY-MM-DD date header in the workspace root (not inside memory/):
## 2026-03-20
- User prefers Bun over Node for the test runner
memory/YYYY-MM-DD.md to avoid duplicates.memory/YYYY-MM-DD.md (create the file and memory/ directory if needed) using the daily log format above.MEMORY.md using the long-term memory format above.Be selective — persist only genuinely useful information, not routine operations. One line per item.