/chainRuns multiple prompts in sequence, feeding each one's output into the next.
Category: Power Commands
Before / After
Do A then B then C.
/chain Step 1: research X. Step 2: outline a blog post from the research. Step 3: write the intro. Step 4: critique it.
What changes in Claude's response
Claude runs each step explicitly and shows you the intermediate output before continuing. You can stop, restart, or modify between steps. It's the closest thing Claude has to a workflow tool — no extra software needed.
When NOT to use /chain
Skip /chain for tightly-coupled tasks where the steps don't have meaningful intermediate outputs. Just ask the whole question at once.
Codes that stack with /chain
/chain is one of 120 tested prompt prefixes. The full cheat sheet has before/after examples, warnings, combos, and 10 workflow playbooks.
See the full cheat sheet — from $5More Power Commands codes
/godmodeThe most thorough, longest, most detailed response Claude can give. Use sparingly.
/autopromptYou give Claude a rough idea, it builds the perfect prompt to get the best output.
MEGAPROMPTGenerates a long, detailed prompt for exactly what you want — usually 500+ words.
/systemWrites a custom system prompt you can drop into any LLM, not just Claude.
PERSONAMakes Claude respond as a specific expert. The specificity is everything.