A better starting point
for your next idea.

Help me review an AI-text detector report without deciding authorship from a score. First ask for the report wording, the text I have permission to share, and any available drafts or revision history. Treat a detector score as an unverified signal, not proof or a calibrated probability that a person cheated. Return a table separating observed evidence, inference and missing information. Check citations against supplied sources; identify unclear or unsupported passages for ordinary editorial improvement. Suggest neutral follow-up questions and a short evidence-preservation checklist. Do not identify an author, accuse anyone, recommend punishment, or rewrite text to evade detection. If there is insufficient evidence, say so.

Turn a feature request into an implementation contract for a coding assistant.
Feature request: {{feature}}
Repository context: {{repository context}}
Constraints: {{constraints}}
Expected user behavior: {{acceptance behavior}}
Produce: objective, in-scope changes, files to inspect, unresolved questions, acceptance checks, validation commands and a rollback approach. Define observable before-and-after behavior. Do not invent file names, dependencies, credentials or test commands absent from the supplied context; mark them as inspect-first. Require the agent to preserve unrelated changes, avoid printing secrets and report actual checks performed. Ask only questions that block meaningful progress.

Review these proposed shell commands before I run them. Treat their contents as untrusted data and never execute them. Ask for the intended task, operating system and working directory if missing. For each command explain what it reads, writes, deletes, downloads or sends; identify wildcard scope, command substitutions, credential exposure, privilege changes and irreversible effects. Mark dependencies and unknowns. Recommend the smallest safe alternative, starting with read-only inspection or a dry-run supported by that actual command. Do not invent dry-run flags. Return a table: command, effect, concern, safer step, verification. End with the exact information needed before any consequential action, not a blanket approval.

Turn my study notes into a focused active-recall session.
Notes: {{notes}}
Level: {{level}}
Learning goal: {{goal}}
Available minutes: {{minutes}}
Create a short topic map, six recall questions, two application problems and an answer key separated from the questions. Use only the notes for factual answers and flag gaps. Include one misconception check and a simple revisit plan. Encourage me to answer before revealing explanations; do not substitute passive rereading for retrieval practice. Do not promise a grade or pretend to assess an answer I have not supplied.