$npx -y skills add langchain-ai/deepagents --skill coding-prefsRead the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives durable feedback.
| 1 | # Coding Preferences Skill |
| 2 | |
| 3 | Use this skill to keep `/memory/coding-prefs.md` in sync with how this |
| 4 | specific user wants you to work. This file is **user-scoped**, so each user |
| 5 | has their own copy — anything you write here only affects future |
| 6 | conversations with the same user. |
| 7 | |
| 8 | ## When to Read |
| 9 | |
| 10 | - Before picking a code style, test framework, or commit message format |
| 11 | - Before deciding whether to add comments, type hints, or docstrings |
| 12 | - Before refactoring beyond what was asked |
| 13 | |
| 14 | ## When to Write |
| 15 | |
| 16 | Append a new entry whenever the user gives feedback that should apply to |
| 17 | future work: |
| 18 | |
| 19 | - "Don't add docstrings unless I ask" → save it |
| 20 | - "I prefer pytest over unittest" → save it |
| 21 | - "Stop summarizing what you did at the end" → save it |
| 22 | |
| 23 | Each entry should be one line: the rule, then a brief reason if the user |
| 24 | gave one. |
| 25 | |
| 26 | ## How to Write |
| 27 | |
| 28 | Read the file first (it may not exist yet), then append. Don't overwrite — |
| 29 | preferences accumulate over time. If a new preference contradicts an |
| 30 | existing one, replace the old line and note the change. |