ClaudeHack

Latest Hacks

64 hacks, newest first

  1. 1.

    Ask Claude to log architecture decisions and TODOs into a repo file that can be re-read after /compact.

    0.00 points·13 hours ago·Context Management·easy·discuss
  2. 2.

    Enable /voice and hold Space to speak complex requirements into the prompt instead of typing walls of text.

    0.00 points·13 hours ago·Terminal / Productivity / Cost Optimization·easy·discuss
  3. 3.

    Connect the Claude in Chrome extension so Claude can open your app, click through flows, read console errors, and iterate until the UI actually works.

    0.00 points·13 hours ago·Testing / Debugging·intermediate·discuss
  4. 4.

    Create a skill that forces a red→green verification loop so Claude cannot claim done without running the suite.

    0.00 points·13 hours ago·Testing / Debugging·medium·discuss
  5. 5.

    Add the words "use a workflow" to a prompt and Claude writes a JavaScript orchestration script that runs subagents in the background, keeping only the final answer in your context.

    0.00 points·13 hours ago·MCP / Agents·intermediate·discuss
  6. 6.

    When Claude repeats a project gotcha, end your prompt with an instruction to write a CLAUDE.md rule so it never happens again.

    0.00 points·13 hours ago·Claude Code / CLAUDE.md·easy·discuss
  7. 7.

    Use /effort (low→max) or CLAUDE_CODE_EFFORT_LEVEL so simple edits stay cheap and hard debugging gets deeper reasoning without paying max on every prompt.

    0.00 points·13 hours ago·Terminal / Productivity / Cost Optimization·easy·discuss
  8. 8.

    Inspect `/usage` (alias `/cost`) for per-skill, subagent, and MCP breakdowns, then cut the expensive outliers.

    0.00 points·13 hours ago·Usage & Limits·easy·discuss
  9. 9.

    Spelling out do-this-then-that is now the common failure mode. Describe the goal, the constraints and how Claude knows it is done, then leave the method alone.

    0.00 points·13 hours ago·Claude Code / CLAUDE.md·easy·discuss
  10. 10.

    Install the GitHub app and mention @claude in review comments so corrections become durable CLAUDE.md rules for every future session.

    0.00 points·13 hours ago·Git & GitHub / Pull Requests·intermediate·discuss
  11. 11.

    Keep the root CLAUDE.md short and drop domain-specific CLAUDE.md files under paths like src/db/ so Claude loads them only when it works in that area.

    0.00 points·13 hours ago·Claude Code / CLAUDE.md·easy·discuss
  12. 12.

    Spin up a subagent for codebase search or verification so only the conclusion returns to your main context.

    0.00 points·13 hours ago·MCP / Agents·medium·discuss
  13. 13.

    Proactively run `/compact` with focus instructions so summaries keep the work that matters instead of stale debugging.

    0.00 points·13 hours ago·Context Management·easy·discuss
  14. 14.

    Schedule an early Claude Code run so your usage window resets around lunch instead of mid-afternoon.

    2.00 points·13 hours ago·Usage & Limits·easy·2 comments
  15. 15.

    Every installed skill spends context just being listed, before you invoke anything. Sort the list by cost, then set the ones you never use to name-only.

    0.00 points·13 hours ago·Context Management·easy·discuss
  16. 16.

    Write the plan in one session, then open a fresh Claude with no context and ask it to review the plan like a staff engineer.

    0.00 points·13 hours ago·Claude Code / CLAUDE.md·easy·discuss
  17. 17.

    Use bundled /loop and /schedule skills for recurring health checks, log watches, or periodic repo tasks without external cron wiring.

    0.00 points·13 hours ago·Scheduled Tasks / Automation·intermediate·discuss
  18. 18.

    Turn on `/sandbox` so OS-level filesystem and network boundaries replace many per-command Bash prompts.

    0.00 points·13 hours ago·Terminal / Productivity / Cost Optimization·medium·discuss
  19. 19.

    End implementation prompts with /simplify so parallel agents review reuse, efficiency, quality, and CLAUDE.md compliance in one sweep.

    0.00 points·13 hours ago·Testing / Debugging·easy·discuss
  20. 20.

    Use /init to generate a starter CLAUDE.md, then delete anything inaccurate or obvious before committing.

    0.00 points·13 hours ago·Claude Code / CLAUDE.md·easy·discuss
  21. 21.

    Double-Esc /rewind back to after useful file reads, then re-prompt with what you learned—without the failed approach still in context.

    0.00 points·13 hours ago·Context Management·easy·discuss
  22. 22.

    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.

    0.00 points·13 hours ago·Terminal / Productivity / Cost Optimization·easy·discuss
  23. 23.

    Put a single `@AGENTS.md` import in CLAUDE.md so Claude Code and other agent tools share the same project instructions without symlink confusion.

    0.00 points·13 hours ago·Claude Code / CLAUDE.md·easy·discuss
  24. 24.

    Force verification with prompts like “prove this works” and “grill me before the PR” so Claude has to validate instead of declaring done.

    0.00 points·13 hours ago·Testing / Debugging·easy·discuss