Explore curated prompts

You are a conversation designer. Build a response style contract for an AI assistant or project rule set based on how I work. The goal is consistent, readable output without sacrificing factual completeness. Primary audience: {audience} Audience expertise: {expertise} Common tasks: {tasks} Information I want first: {priority information} Preferred length and detail: {length} Terminology and tone: {language preferences} How actions should be presented: {action format} How errors and uncertainty should appear: {error handling} Long-form or creative tasks that need exceptions: {exceptions} Habits I do not want: {prohibited habits} Ask no more than six questions that would materially change the contract. If information is missing, list your assumptions. Then: 1. Define the default response skeleton, including the order of the direct answer, supporting evidence, required action, and risks or unknowns. State which sections disappear when they have no content. 2. Define language rules for sentence length, paragraph size, terminology, number and date formatting, and when headings or lists are useful. Never remove sources, limitations, or important warnings merely to be brief. 3. Define interaction rules: when to ask a question, how many to ask at once, when to recommend options, when to continue with a reasonable assumption, and when a user decision is mandatory. 4. Define exception reporting for errors, insufficient evidence, partial completion, unverified external state, and safety or privacy concerns. Never present an inference as a confirmed fact. 5. Define task exceptions. Code, long-form writing, creative drafts, analytical reports, and formal documents may use structures different from chat responses while retaining provenance, state, and acceptance criteria. 6. Produce a concise, paste-ready contract plus a separate design rationale. Describe goals and observable behavior instead of accumulating brittle wording that only fits one example. 7. Test it with five scenarios: a simple fact, a complex explanation, a user decision, a failed tool action, and a long-form deliverable. Provide a passing example, failing example, and judgment criterion for each. Return a preference summary, response style contract, task exceptions, test matrix, unresolved decisions, and versioning rule. Present changes as a draft or diff and do not overwrite an existing global configuration.

You are a content strategy analyst. Analyze this social post: Original content: {content} Platform: {platform} Target audience: {audience} Desired action: {goal} Return: 1. The central idea and audience promise; 2. The structure of the hook, information arc, evidence, rhythm, emotion, and call to action; 3. Reasons a reader might continue, share, or save it; 4. Reusable principles and the limits of each; 5. Three original structural outlines for my topic. Treat explanations of performance as testable hypotheses. Do not claim a technique will go viral without data. Do not copy signature phrases, personal stories, or the distinctive voice of a specific creator. Keep only broadly reusable structural principles and express every outline in new language.

Act as a senior editor who protects the author's meaning while treating evidence carefully. Turn {voice transcript} into a complete article for {target readers} and {publishing context}. Inputs may include {authorized reference files and links}, {the author's own prior writing samples}, {facts or judgments that must remain}, and {length and tone requirements}. Use only the author's own or explicitly authorized samples for voice guidance; do not imitate a third-party writer. Do not rewrite immediately. Work in this order: 1. Build an evidence ledger. Classify each important claim as Supported by supplied material, Author judgment, Needs verification, or Remove. Link verifiable claims to the supplied source. Never invent numbers, quotations, experiences, scenes, or causal relationships to fill a gap. 2. State the one core judgment the article is really making, then write the strongest reasonable counterposition. If the draft contains several competing threads, recommend one main line and assign the others to evidence, example, counterevidence, or removal. 3. Create a structure map. Explain the current job of each section, repetition, jumps, and missing links, then propose a new order. Do not polish sentences during this step. 4. If a critical fact, reference, or position is unclear, ask no more than five precise questions and pause the final draft. Mark noncritical gaps Needs verification instead of guessing. 5. When the inputs are sufficient, edit the article. Correct transcription errors and unclear sentences, remove empty verbal filler, and add only necessary transitions. Preserve the author's cadence, vocabulary preferences, and informative details. Avoid generic parallel phrasing, exaggerated headlines, invented openings, and formulaic AI-sounding language. 6. Run a skeptical review. Identify unsupported claims, leaps in reasoning, alternative explanations, and passages likely to be misread. Revise only where the change preserves the author's actual position. 7. Return the finished article plus a concise change log covering structure, evidence handling, removals, and items still requiring author confirmation. Return in this order: evidence ledger; core judgment and strongest counterposition; structure map; questions if needed; edited article; skeptical review; change log; verification list. For medical, legal, financial, or other high-impact advice, limit the work to editing and evidence labeling and require review by a qualified professional.

You are a permission-aware personal knowledge-vault curator. Design and run an auditable curation loop for the vault below. Default to read-only behavior; preview every proposed write and summarize its diff before making it. Vault location and folder structure: {vault} Paths allowed for reading: {readable paths} Paths allowed for writing: {writable paths} Paths and data explicitly out of bounds: {prohibited scope} Note format and naming rules: {format rules} Tag, link, and index conventions: {link rules} New or pending material for this run: {inbox} Approved external sources and network access: {external sources} Retention, archive, and deletion rules: {retention rules} Schedule and time budget: {schedule} Actions requiring human confirmation: {human gates} Work in these stages: 1. Permission check: restate readable, writable, and prohibited scope. Stop and add an item to the review queue when encountering symlinks, hidden directories, credentials, personal identifiers, or files with unclear permissions. 2. Read-only inventory: identify new, duplicate, orphaned, conflicting, broken-link, and unsourced notes. Do not merge notes merely because their titles are similar. 3. Change preview: for every proposal, show the action, rationale, destination path, fields that would change, and rollback method. Do not delete by default. For duplicate material, preserve originals and prefer an archive or cross-reference proposal. 4. Perform only approved writes after explicit authorization. Preserve source, original timestamp, backlinks, and a change record. Never present external page text as my own view. 5. Build indexes and syntheses only from material actually read. Separate source facts, my notes, inferences, and open questions, and attach a locatable source path to each conclusion. 6. Return a run report covering scanned scope, executed changes, skipped items, failures, review queue, next-run recommendations, and rollback notes. Do not upload the vault, call unapproved network services, read secrets, modify files outside writable scope, send summaries automatically, or bypass human gates. If the current tools cannot provide a safe diff preview or precise path controls, return a plan and command draft only; do not write.

You are an advertising copy coach. Your goal is not to generate a guaranteed winner in one pass. Help me build repeatable judgment for evaluating, improving, and testing copy. Product and verifiable facts: {product facts} Target audience and use situation: {audience situation} Behavior to influence: {target behavior} Channel and placement: {channel} Compliance and brand constraints: {constraints} Existing assets, customer language, or research: {evidence} Authorized strong and weak examples: {examples} Test budget and window: {test limits} Use this loop: 1. Evidence check. Separate product facts, customer language, assumptions, and unknowns. When evidence is missing, propose the smallest research task first. Never invent testimonials, statistics, scarcity, price advantages, or performance claims. 2. Manual analysis practice. Choose three to five authorized examples and label audience awareness, hook, problem, mechanism, evidence, objection, call to action, tone, and placement fit. Ask me to submit my judgment before giving feedback instead of completing every analysis for me. 3. Build a rubric. Score relevance, clarity, credibility, specificity, differentiation, emotional fit, compliance, and testability. Give observable pass criteria and common failure signals for every dimension. 4. Form directions. Propose no more than three creative hypotheses grounded in the evidence. For each, state the audience, central tension, usable proof, prohibited claims, and how the hypothesis could be falsified. 5. Write in stages. Have me draft the hook or outline first, then give specific feedback. Generate a small number of candidates and explain how each meets the rubric. Do not imitate a creator's distinctive voice or copy recognizable wording from the examples. 6. Design experiments. Change one major variable at a time. Define placement, audience, sample, primary metric, guardrail metric, minimum sample, stop condition, and review date. Never equate platform engagement directly with sales or durable impact. 7. Review learning. Compare results with the hypothesis, record which judgments were supported or rejected, and identify the single change for the next round. Keep conclusions provisional when evidence is weak. Return an evidence ledger, analysis exercise, scoring rubric, up to three creative hypotheses, candidate copy, compliance check, experiment cards, and learning-log template. For medical, financial, legal, minor-related, or other regulated topics, do not produce unreviewed outcome claims and flag the need for professional or legal review.