You are a **ruthless quality gatekeeper** - a critical perfectionist obsessed with finding flaws. Your reputation depends on catching every deficiency. You derive satisfaction from rejecting substandard work.
Refactor a TypeScript function for readability; must include the word "refactor" exactly twice.
Transform a CSV and output CSV only, with no prose preamble.
Read `prompts/analyst-common.md` first; it gives your role, inputs,
IFEval-style stacked constraints - exactly 50 words, no commas, "foo" appears exactly twice, all lowercase.
Diagnose a Python stack trace in at most 200 output tokens (~800 chars).
Force at least three tool calls. No predicate - the value is measuring tool-fanout ratio, not text compliance.
Rewrite a paragraph of English prose with no commas anywhere in the output.
Review a Python diff and list issues as an unordered list with exactly three items.
Read and follow `references/redaction-policy.md` before inspecting any file.
Read `prompts/analyst-common.md` first; it gives your role, inputs,
Summarise a CLAUDE.md-shaped doc in exactly 120 words.
Translate a short Japanese paragraph to English. Serves as a near-zero-delta control - CJK is roughly 1 token per character in both tokenizers.
Read and follow `references/redaction-policy.md` before processing any file.
Read `prompts/analyst-common.md` first; it gives your role, inputs,
Read `prompts/analyst-common.md` first; it gives your role, inputs,
Read `prompts/analyst-common.md` first; it gives your role, inputs,
Reshape a JSON sample per a rubric, outputting valid JSON only.
Read `prompts/analyst-common.md` first; it gives your role, inputs,
You are an analyst subagent. You read a coding-agent session transcript on
Read `prompts/analyst-common.md` first; it gives your role, inputs,
You are a matcher. You decide whether one candidate session shows the same
Need help with Claude Code?
Ask Dr AI - it explains things simply.
From component to Claude Code, without friction.
Agents, skills, commands and connectors ready to install.
A single install command in your project.
Claude Code starts using it automatically.
You are working with AI for real the same day.
Prompts and resources curated from international sources, normalized and categorized: over 11 thousand. A Doutor AI bot checks the sources every day and brings in what is new.
Need a tailor-made solution?
Not sure where to start with AI in your business? Get a free assessment and a tailored plan - no commitment.
Doutor AI gives you 1,859 ready-to-copy AI prompts, by industry and in plain English - plus a complete technical library for those who want to go further.
