ClaudeHack

#workflow

7 hacks

  1. 1.
    Write key decisions to a file so compaction cannot erase them(okhlopkov.com)

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

    0.00 points·1 month ago·Context Management·easy·discuss
  2. 2.
    Use pushback prompts so Claude proves the change before you ship(support.claude.com)

    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·1 month ago·Testing / Debugging·easy·discuss
  3. 3.
    Enter plan mode before large refactors to avoid rework(code.claude.com)

    Cycle into plan mode (Shift+Tab) so Claude explores and proposes an approach for approval before editing.

    0.00 points·1 month ago·Terminal / Productivity / Cost Optimization·easy·discuss
  4. 4.
    Parameterize skills with $ARGUMENTS instead of editing prompts(code.claude.com)

    Build slash skills that accept issue numbers, branch names, or formats via $ARGUMENTS / $0 so one command covers many cases.

    0.00 points·1 month ago·Terminal / Productivity / Cost Optimization·easy·discuss
  5. 5.
    Turn recurring prompts into skills you invoke with /name(code.claude.com)

    Save repeatable workflows as SKILL.md (or .claude/commands) so you slash-invoke consistent PR reviews, releases, or checklists.

    0.00 points·1 month ago·Terminal / Productivity / Cost Optimization·medium·discuss
  6. 6.
    Start a new session with /clear when the task truly changes(claude.com)

    Use /clear between unrelated tasks so leftover debugging does not bias the next feature.

    0.00 points·1 month ago·Context Management·easy·discuss
  7. 7.
    Ask /btw side questions without derailing the main task(support.claude.com)

    Use /btw for single-turn clarifications that share full context but never enter conversation history or burn future tokens.

    0.00 points·1 month ago·Context Management·easy·discuss