From claudna
Use when you want to save, read, or organize persistent notes across Claude sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claudna:notesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Maintain persistent notes across Claude sessions.
Maintain persistent notes across Claude sessions.
Global notes: ~/.claude/notes/
Structure:
~/.claude/notes/
├── projects/ # Per-project learnings
│ ├── api-server.md
│ ├── data-pipeline.md
│ └── myproject.md
├── patterns/ # Reusable patterns discovered
│ ├── snowflake.md
│ ├── streamlit.md
│ └── python.md
└── decisions/ # Key decisions and rationale
└── YYYY-MM-DD-topic.md
When asked to take notes or after completing significant work:
Identify the category:
~/.claude/notes/projects/{project}.md~/.claude/notes/patterns/{topic}.md~/.claude/notes/decisions/{date}-{topic}.mdAppend to existing notes (don't overwrite):
## YYYY-MM-DD: Topic
### Context
What was the task/problem?
### Solution
What worked?
### Lessons
- Key takeaway 1
- Key takeaway 2
Reference notes when starting related work:
~/.claude/notes/projects/{project}.md before working on a projectSave a note: Read the current content with the Read tool, then use the Edit tool to append:
## 2024-01-15: Topic here
Content here...
Read project notes: Use the Read tool on ~/.claude/notes/projects/<project>.md
List all notes: Use the Glob tool with pattern **/*.md in ~/.claude/notes/
After completing a PR or significant task, Claude should ask:
"Should I add notes about this work to
~/.claude/notes/projects/{project}.md?"
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub claudfather/claudna --plugin claudna