About coding-prefs
A user-scoped coding-preferences skill that keeps `/memory/coding-prefs.md` aligned with an individual user's feedback. It specifies when to read preferences and how to append or replace rules so they can guide future conversations.
Key features
- 01Read preferences before coding decisions
- 02Capture feedback for future work
- 03Store each rule as a single line
- 04Append without overwriting existing entries
- 05Replace contradicted preferences
Use cases
- 01Applying a user's preferred test framework
- 02Following preferred style and documentation choices
- 03Keeping commit-message preferences consistent
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ langchain-ai/ deepagents --skill coding-prefsAfter installing, type/coding-prefsin Claude Code to confirm it loaded.
Details
From the project READMECoding Preferences Skill
Use this skill to keep /memory/coding-prefs.md in sync with how this
specific user wants you to work. This file is user-scoped, so each user
has their own copy — anything you write here only affects future
conversations with the same user.
When to Read
- Before picking a code style, test framework, or commit message format
- Before deciding whether to add comments, type hints, or docstrings
- Before refactoring beyond what was asked
When to Write
Append a new entry whenever the user gives feedback that should apply to future work:
- "Don't add docstrings unless I ask" → save it
- "I prefer pytest over unittest" → save it
- "Stop summarizing what you did at the end" → save it
Each entry should be one line: the rule, then a brief reason if the user gave one.
How to Write
Read the file first (it may not exist yet), then append. Don't overwrite — preferences accumulate over time. If a new preference contradicts an existing one, replace the old line and note the change.