Some tips for [[Claude Code]] that can be given straight to the tool to improve its performance. ## 1) Self-improvement injection > Create a `UserPromptSubmit` hook (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.md` files 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 `UserPromptSubmit` hook 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.