Properties5
| Type | Article |
| Author | Luca Dellanna |
| Date | Feb 15, 2026 |
| URL | https://www.threads.com/@lucadellanna/post/DUvms2eibBi |
| Note created | Feb 15, 2026 |
Some tips for Claude Code that can be given straight to the tool to improve its performance.
1) Self-improvement injection
Create a
UserPromptSubmithook (global settings). Script echoes: If 8+ tool calls, append one optimization hint (reusable skill, memory pattern, or workflow fix). One sentence. Skip if exploratory.
2) Skills audit
Create a skill that lists all installed skills (project & global level) with their line counts. Then ask the user which to review for improvement opportunities (conciseness, clarity, overlapping scopes, token efficiency).
3) Claude audit
Create a skill that reads all
CLAUDE.mdfiles and checks for: redundant instructions, verbose phrasing, and content that could move to memory. Present findings and ask if the user wants to implement them.
4) Reflect
Create a skill that reviews the current conversation, analyzes tasks, errors, and user feedback, and extracts opportunities for learning, skill creation, and skill improvement; then, presents the findings to the user and asks what to implement or write to memory.
5) Conditional prompt linter
Create a
UserPromptSubmithook in global settings. The script counts words and, if >50, echoes a note asking Claude to check if the desired outcome is clear. The output gets appended to the prompt.
To start using them, simply copy/paste the one-paragraph prompts I provided above into Claude Code. No complex setup, no need to trust third-party tools that you don’t understand.