Page 2 of 3
Add a deterministic PreToolUse hook that rejects destructive shell patterns before Claude can run them.
Create a skill that forces a red→green verification loop so Claude cannot claim done without running the suite.
Run claude remote-control on your machine, then connect from the Claude mobile app to approve builds, poke CI failures, and keep coding with full local tools.
Use /clear between unrelated tasks so leftover debugging does not bias the next feature.
Add a top-level cache_control ephemeral flag so growing conversation prefixes reuse cached tokens and cut API cost and latency.
Add a Notification hook that plays a short sound when Claude is idle or waiting on permission so you can multitask without staring at the terminal.
Turn off MCP servers unrelated to the current project—their tool schemas still consume context at session start.
Enable /voice and hold Space to speak complex requirements into the prompt instead of typing walls of text.
Build slash skills that accept issue numbers, branch names, or formats via $ARGUMENTS / $0 so one command covers many cases.
Run /context to break down token consumers—CLAUDE.md, MCP tools, conversation—and prune the expensive ones.
Use bundled /loop and /schedule skills for recurring health checks, log watches, or periodic repo tasks without external cron wiring.
Add the GitHub MCP server so Claude can cross-reference issues, PRs, and repo state without leaving the session.
Define custom subagents with `isolation: worktree` so delegated edits happen on a temporary branch checkout.
Use /config to set Explanatory or Learning output style so Claude explains the why behind changes — not just the diff.
Mark deploy/ship/destructive skills so only an explicit /command runs them—Claude cannot auto-trigger them mid-session.
Use /permissions to allowlist read-only and trusted commands so you stop mindlessly clicking Approve.
Run prettier/ruff/gofmt automatically after Edit/Write tools so Claude never leaves unformatted files.
Put domain-specific instructions in path-scoped `.claude/rules/` so they load only when Claude touches matching files.
Use `claude --print --output-format json` in GitHub Actions to automate reviews or summaries without an interactive TTY.
Inspect `/usage` (alias `/cost`) for per-skill, subagent, and MCP breakdowns, then cut the expensive outliers.
Ask Claude to log architecture decisions and TODOs into a repo file that can be re-read after /compact.
Turn on `/sandbox` so OS-level filesystem and network boundaries replace many per-command Bash prompts.
Use the bundled /doctor skill to find duplicate local memory, unused MCP/plugins, and slow hooks eating budget.
Run `/batch` on large mechanical migrations so Claude decomposes work and spawns per-unit worktree agents with PRs.