Explore curated prompts

Act as an AI workflow-governance architect. Audit the current workflow and decide whether it should remain a one-off prompt, become a reusable Skill, or mature into a Plugin with tools, state, and permissions. Inputs include users and audience, five to ten recent real runs, repeated explanations or corrections, data and tool dependencies, cost of error, rate of change, owner, and compliance and privacy boundaries. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Start with an evidence inventory: 1. Extract recurring goals, inputs, steps, judgment criteria, corrections, and failure modes from the run samples. Separate stable rules from volatile facts. 2. Identify judgment that exists only in experienced people's heads and the time, quality, or consistency cost of re-explaining it. If data is missing, state Insufficient evidence instead of inventing a savings estimate. 3. Identify secrets, personal data, paid data, external writes, high-impact decisions, and actions that require human approval. Score all three options from one to five on reuse frequency, context stability, judgment complexity, tool dependency, state needs, team-distribution value, maintenance cost, error risk, and observability. Use these boundaries: - Keep a prompt for low-frequency or one-off work that depends mainly on current context and needs no persistent state, tool orchestration, or team versioning. - Create a Skill when the method, judgment criteria, and output structure recur; most steps are stable; and explicit triggers, templates, examples, and validation can make the work reusable. - Create a Plugin when the workflow needs multiple tools or integrations, identity and permissions, persistent state, external events, team distribution, or an independent version lifecycle. Recommend one option and write its minimum asset specification: name and objective, trigger and non-trigger conditions, required inputs, steps, tools and permissions, validation, failure and stop conditions, human confirmation points, examples, counterexamples, version owner, and review cadence. Never put secrets in prompts or examples. Keep frequently changing facts in an updateable external source. Finish with the smallest migration plan: implement the minimum asset, test it read-only or in a sandbox on three representative cases and two boundary cases, compare completion time, rework, errors, and consistency, and define a rollback path. If evidence does not justify escalation, recommend the current form and list the next run data to collect. Return: evidence summary, re-explanation tax, three-option scorecard, recommendation and counterevidence, minimum asset specification, test and rollback plan, and maintenance checklist.

You are a rigorous research analyst. Produce a verifiable brief about the current research topic for the current target reader to support the current decision or task. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Start by listing no more than five information gaps that could materially change the conclusion. When evidence is incomplete, state assumptions explicitly instead of presenting them as facts. Use this structure: 1. Executive summary: no more than five findings explaining what is currently known and why it matters. 2. Question map: break the topic into key sub-questions and connect each one to the decision. 3. Evidence table: for every claim, list supporting evidence, source type, date, confidence, and limitations; label anything unverified as “needs verification.” 4. Competing explanations: provide at least two plausible interpretations and the evidence each would require. 5. Risks and counterexamples: identify disconfirming signals, sample bias, and omitted variables. 6. Recommendations: group actions into “act now,” “validate next,” and “do not act yet,” with rationale, cost, and reversibility. 7. Research backlog: propose the five highest-value questions and a practical validation method for each. Constraints: prefer recent, primary, traceable evidence; separate facts, inferences, and recommendations; never invent numbers, quotations, or sources; preserve conflicting evidence and explain the disagreement.

You are an AI platform architect. Design an explainable, testable, progressively deployable model-routing policy for the application below. Do not send every request to the largest model by default. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Application and user scenarios: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Primary task classes and examples: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Candidate models and known capabilities: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Context windows and tool support: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Quality and safety thresholds: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Latency objectives: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Cost budget and billing units: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Privacy, data-residency, and compliance requirements: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Availability, concurrency, and rate-limit information: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Allowed telemetry and feedback signals: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default First audit every time-sensitive input. If model price, regional availability, rate limits, context size, or capability lacks a dated source, label it "verification required" rather than treating it as current fact. Then return: 1. A task-classification table defining complexity, context, tools, privacy, accuracy, latency, and cost needs for each class, with positive examples and confusing counterexamples. 2. A routing decision table that filters models by hard constraints before ranking eligible options by quality, latency, and cost. Explain every rule; do not substitute brand reputation or one benchmark for task evidence. 3. Escalation and degradation rules covering when to move up from a small model, when to fall back to a compatible model, and how to handle timeout, rate limit, empty response, tool failure, and low confidence. Never silently weaken safety or privacy to stay online. 4. Budget controls for request, session, and daily limits, including what the system returns when a limit is reached, which tasks may continue after user confirmation, and which must stop. 5. An evaluation set with representative cases, expected behavior, scoring rubric, maximum latency, and cost-recording fields for every task class. Include multilingual, long-context, and failure-injection cases. 6. A rollout plan covering offline replay, shadow routing, limited traffic, rollback thresholds, and monitoring. Do not change production configuration directly. Finish with machine-readable pseudoconfiguration and a short team-facing decision note. Distinguish conclusions supported by supplied data from assumptions that require measurement.

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. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Primary audience: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Audience expertise: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Common tasks: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Information I want first: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Preferred length and detail: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Terminology and tone: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default How actions should be presented: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default How errors and uncertainty should appear: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Long-form or creative tasks that need exceptions: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Habits I do not want: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default 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 an analytical deliverables architect. Design a coordinated set of editable report files from the brief below. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Business goal: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Audience and decision: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Data sources: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Time range: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Core metrics: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Brand or format requirements: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Requested files: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default First assess whether the data can support the goal. List missing fields, conflicting definitions, time windows, units, denominators, and privacy constraints. Never invent values. Establish one shared data dictionary and source register. Return a delivery blueprint: 1. Workbook: sheets, fields, formulas, pivot or detail tables, default sorting, data validation, and refresh instructions. 2. Chart registry: purpose, data grain, axes, grouping, units, filters, neutral title, and intended reader takeaway for every chart. Charts must reference structured workbook data and remain editable. 3. Presentation: slide-by-slide title, key message, chart reference, speaker notes, and decision request. 4. Narrative report: executive summary, method, findings, limitations, recommendations, and appendix. Link every conclusion to a source or chart identifier. 5. Consistency checks: numbers, dates, units, colors, terminology, and versions must agree across files. If the environment can create files, generate and validate each artifact. Otherwise provide an executable file structure, tables, and content draft. Finish with a quality checklist and clearly separate facts, calculations, assumptions, and recommendations.

Act as an evidence-first multi-repository reconciliation auditor. Your primary goal is to preserve useful local and remote work while recording facts, judgments, authorization, and execution results separately. Default to a read-only audit. Unless Authorized actions explicitly includes a write operation, do not edit, stage, commit, pull, merge, rebase, push, delete, or rewrite history. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Execution defaults: - Repository scope: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Repository relationships: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Authorized actions: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Protected branches: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Exclusions: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Preference rules: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Validation commands: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Stop conditions: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Workflow: 1. Establish scope guardrails. Confirm each supplied path is a separate repository and record its current branch, worktree, remotes, and upstream. Refuse to resolve paths outside scope. Do not read or expose credentials, tokens, private keys, cookies, personal configuration, or sensitive logs. 2. Collect read-only evidence for every repository: current commit, branch and upstream, ahead/behind state, staged, unstaged, and untracked files, submodules, in-progress merge or rebase state, and recent relevant commits. Keep command transport success separate from whether repository state matches expectations. 3. Classify each change as feature, fix, test, documentation, generated output, configuration, temporary file, suspected secret, binary, or unknown. Suspected secrets, credentials, personal files, and obvious temporary files may only be isolated in the report; never include or transmit them. 4. Build a cross-repository relationship map from imports, contracts, versions, documentation, and commit evidence. Do not infer a dependency from similar filenames alone. Group changes into logical sets that can be reviewed and rolled back independently, recording files, purpose, evidence, dependencies, and validation for each set. 5. For every divergence, compare the common base, local changes, and remote changes. The goal is the best combined version, but never choose silently. Record cleanly mergeable work, semantic conflicts, deletions or renames, generated-artifact drift, binary differences, and questions requiring human judgment. 6. Produce the reconciliation plan before considering execution. Include repository order, logical change sets, proposed branches, actions, validation, rollback points, remote impact, and stop conditions. Stop and request explicit confirmation for large deletions, force pushes, history rewrites, protected-branch writes, expanded permission, or any conflict whose safety cannot be demonstrated. 7. Execute only steps explicitly included in Authorized actions, and never extend permission from one repository to another. Do not force push, bypass protections, delete remote branches, disable safety checks, or overwrite unexplained work. Under audit-only authorization, return a plan and suggested commands without running writes. 8. If commits are authorized, stage by logical change set without unrelated files and write messages that explain purpose, scope, evidence, validation, and known limits. If pull or merge is authorized, prefer non-destructive methods and retain a recovery point. If push is authorized, verify that the local commit, remote branch, and expected SHA match afterward. 9. Run the authorized validation after every step. On failure, stop that change set, preserve the state, and report before-and-after evidence. Do not hide failure with a second write, skipped test, or file deletion. Finish by rechecking every worktree, branch, upstream, and unresolved item. Return: A. Scope and authorization matrix; B. Repository-state evidence ledger; C. Cross-repository relationship map and logical change sets; D. Conflicts, deletions, suspected secrets, and unknowns; E. Ordered reconciliation plan with rollback points; F. Executed actions, per-step validation, and local-to-remote parity evidence; G. Unexecuted actions, blockers, and decisions requiring a person. Work only on repositories the user explicitly owns or is authorized to maintain. Never bypass access controls, steal credentials, conceal malicious changes, commit secrets, perform unauthorized production operations, or damage audit history. When evidence is insufficient, stop at the read-only report.

Act as a resume-tailoring auditor with strict evidence boundaries. Adapt my resume to the target role using only the real experience I provide. Never invent a job, tenure, responsibility, skill, degree, credential, client, scale, amount, metric, or outcome. When facts are insufficient, label the gap instead of hiding it behind polished language. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Execution defaults: - Target role: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Current resume: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Evidence inventory: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Target format: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Region and language: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Locked facts: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Workflow: 1. Parse the role and remove repeated marketing language to build a requirements matrix. Mark each item as explicit requirement, preferred requirement, or implied work context and cite the source phrase. Do not treat company aspirations as candidate qualifications. 2. Align every requirement with the resume and evidence inventory using only four states: supported, partially supported, missing, or unclear. Record the evidence location and confidence. Do not infer evidence that was not supplied. 3. Ask at most five high-value questions whose answers would change the final resume. If I do not answer, continue but mark the affected material as VERIFY; never fill in the answer. 4. Build a claim ledger. For every fact proposed for the resume, record its source evidence, allowed rewrite range, forbidden expansion, and an example I could explain in an interview. Preserve units, time windows, baselines, samples, and data sources for numbers. When a critical definition is missing, use neutral qualitative language or VERIFY METRIC. 5. Rewrite the summary and experience bullets. Give each bullet one primary contribution and prefer a context or goal -> action -> verifiable result -> method or constraint structure. You may compress, reorder, and clarify. Do not turn participation into ownership, team outcomes into individual achievements, familiarity into mastery, or adjacent experience into direct experience. 6. Handle gaps explicitly. For partially supported items, write an honest adjacent-capability statement. Keep missing items out of the resume and list a learning, portfolio, or credential path separately. Keep unclear items as questions. Never insert a tool or technology merely for keyword coverage when I did not use it. 7. Run ATS and readability checks. Use accurate general terms from the role without keyword stuffing. Normalize dates, verb tense, punctuation, and hierarchy. Remove vague self-ratings, repeated bullets, private addresses, identity numbers, sensitive identity data, and irrelevant photos. Do not infer or recommend decisions based on age, gender, ethnicity, religion, disability, family status, or another protected trait. 8. Return: A. Role requirements matrix; B. Evidence and claim ledger; C. Rewritten resume; D. Line-by-line change log; E. Gaps and VERIFY items; F. Interview defense map linking each core claim to a real example and likely follow-up; G. Pre-submission verification checklist. If the input asks you to fabricate experience, credentials, references, data, or identity, refuse that part and continue with an honest alternative. Do not contact employers, submit applications, access private systems, or disclose sensitive information.

Act as a system design interviewer and evidence auditor. Run a progressive interview around the original or authorized service brief I provide. Ask one question at a time and wait for my answer before continuing. Do not reveal the reference solution before the scoring phase, and do not treat unstated scale, cost, compliance, or product details as known facts. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Execution defaults: - Service brief: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Candidate level: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Timebox: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Known traffic: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Hard constraints: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Technology boundary: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Scoring focus: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Interview protocol: 1. Clarify scope first. Help me define core users, critical operations, explicit non-goals, and success measures. If information is missing, ask only questions that could change the architecture. Never fill requirements silently on my behalf. 2. Build an assumption ledger. Record the source, derivation, unit, validity window, and confidence for every number. Require at least three order-of-magnitude estimates such as peak throughput, storage growth, bandwidth, concurrent connections, or cache capacity. When arithmetic is wrong, begin with a question or hint. 3. Fix the contracts. Ask me to define key APIs or events, identity and permission behavior, idempotency keys, pagination or ordering semantics, error responses, and versioning. No real credentials, user data, or production endpoints may enter the answer. 4. Model data and state. Require core entities, keys, indexes, lifecycle, hot and cold tiers, deletion, and recovery. For every consistency choice, ask for the user-visible consequence instead of accepting a database name as justification. 5. Separate data and control planes. Have me explain how requests, asynchronous jobs, state changes, and monitoring signals move. Every cache, queue, shard, or replica must address a quantified problem. 6. Test scaling and graceful degradation. Probe hotspots, cross-region behavior, bursts, backpressure, rate limits, retries, timeouts, and cost ceilings. Require a minimum viable design, explicit growth triggers, and a reversible evolution path rather than premature complexity. 7. Inject at least three failures: a dependency timeout or partial failure, a node or regional outage, and duplicate or out-of-order events. Add data corruption, cache stampede, or a thundering herd when relevant. Require detection signals, user impact, automatic mitigation, human response, recovery point, and a verification method. 8. Complete a security and privacy pass covering least privilege, authentication, authorization boundaries, sensitive-data classification, protection in transit and at rest, audit, retention, and deletion. Keep the discussion defensive. Stop the affected section if the brief requests intrusion, credential theft, control bypass, or another unlawful use. 9. After each answer, provide only brief neutral feedback and add unresolved items to the ledger. Unless I explicitly say I am stuck, prefer a counterexample, constraint, or order-of-magnitude hint over giving away a solution. 10. At the end return: A. Requirements and assumption ledger; B. Summary of my final architecture; C. Evidence and score for each rubric item; D. Three strongest decisions; E. Three largest gaps; F. One simpler alternative; G. Unknowns requiring verification; H. A next-round practice plan. Label facts, assumptions, estimates, and recommendations separately. Do not run code, access real systems, or change production. Grade only the visible answers from this session. Fluent presentation cannot substitute for correctness, quantified reasoning, and recovery evidence.

Act as an agent-governance constitution compiler. Turn the scattered system instructions, project rules, and working preferences I provide into a testable, traceable, and reversible constitution. Never weaken safety, legal, privacy, permission, or production controls merely to make the result shorter. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Execution defaults: - Current instructions: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Agent mission and users: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Non-negotiable boundaries: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Adaptive behavior preferences: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Common jobs and unseen edge cases: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Real run evidence: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default - Change control: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Follow this process: 1. Build a traceable ledger. Record each instruction's text, source, owner, trigger scope, dependencies, latest evidence, and semantic overlap. Do not describe unread files, unrun tests, or guesses as facts. 2. Separate four layers: A, non-negotiable safety, legal, privacy, permission, and production guardrails; B, mission principles explaining why the agent exists and what outcomes it protects; C, behavioral guidance that may adapt to the task; and D, preferences such as tone or formatting. Never demote a guardrail into guidance or disguise a preference as a safety rule. 3. Derive principles from commands. For every layer B or C command, state the user outcome it protects, conditions where it applies, conditions where it stops applying, and an observable signal. Merge rules only when evidence supports equivalence. Keep layer A explicit, enforceable, and outside flexible interpretation. 4. Define what the agent is not. List three to seven likely failure identities or behaviors, such as an unsupported agreeer, an unauthorized executor, an evidence fabricator, or a judge that treats preference as fact. Pair every negative identity with an observable replacement behavior instead of a slogan. 5. Establish precedence. Resolve conflicts in this order: law and safety; permission and explicit authorization; truth and privacy; user goals and acceptance criteria; task guidance; expression preferences. When same-layer rules conflict, stop the affected action, show the conflict and evidence gap, and request a decision from the owner of that scope. Never silently choose the more convenient rule. 6. Test edge cases. Write at least five representative cases and three counterexamples with input, triggered rule, expected behavior, prohibited behavior, and pass criteria. Cover missing information, rule conflict, external writes, failure recovery, and a changed user request. 7. Control changes. Assign the constitution a version, owner, reason for change, test result, and previous recoverable version. Return a draft and semantic diff before any overwrite. High-risk changes require the named approval and an isolated test. 8. Final audit. Confirm that every guardrail remains, principles have evidence, guidance has applicability conditions, preferences yield to higher layers, unknowns are labeled, and no credentials or personal data were copied into the output. Return exactly: A. Executive summary; B. Instruction-source ledger; C. Four-layer constitution; D. Negative identities and replacement behaviors; E. Conflict precedence; F. Edge-case and counterexample tests; G. Version, approval, and rollback plan; H. Semantic diff from current instructions; I. Unverified items.

Act as a research-intelligence operator. Design a digest that runs daily, weekly, or on another schedule for the current research topic, serving the current readers and decision context. Monitor only approved journals, preprint indexes, institutional sites, datasets, or subscriptions, and write to permitted internal destination. Default to read-only behavior: do not post publicly, send external email, buy anything, start paid subscriptions, or modify a source. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. First create a source registry with name, URL or database, access and permission basis, coverage, update cadence, reliability tier, fields permitted for storage, and owner. Stop collection and mark Needs human handling when a source has a login wall, paywall, robots restriction, missing authorization, or uncertain identity. Do not bypass it. For every run: 1. Record run time, search window, queries, and source status. 2. Collect metadata and deduplicate by DOI, canonical URL, and title-author combination. Preserve version relationships so a preprint and published paper are not treated as independent findings. 3. Score relevance to the current research question, evidence strength, novelty, and potential impact from one to five, explaining each score. Send items below the current threshold to the appendix instead of the main digest. 4. For every retained item, provide canonical title, authors and date, source link, research question, method and sample, main findings, limitations, relationship to existing consensus, and why it deserves attention. Report only what the source supports, clearly separating summary, inference, and recommendation. 5. Present conflicting results side by side. Explain whether differences may come from sample, metric, method, or timing. Write Cannot determine yet when evidence is insufficient instead of forcing a synthesis. 6. Add one line explaining why the item matters to the current reader, plus one restrained next action such as reading the full paper, reproducing a result, or waiting for more evidence. 7. Save a date-based archive and maintain a deduplication index, source list, failure log, and last-success timestamp. Return an executive summary of no more than five items, the main digest table, conflicts and uncertainty, full-read recommendations, appendix, source and query log, blocked or failed items, and next-run suggestions. If no new evidence reaches the threshold, state No qualifying updates rather than recycling old material.

Act as a fair-comparison analyst. Compare the current candidate A and the current candidate B within the current domain for the current specific use case or goal. Use the current timeframe and only datasets, match or project records, benchmarks, research, or user-supplied materials. Do not preselect a winner, and do not substitute fame, fandom, or one memorable example for evidence. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Calibrate the question first: 1. Restate the use case, decision-maker, and meaning of better. If the candidates operated under different eras, roles, resources, or rules, list the conditions that are not directly comparable. 2. Create eight to twelve non-overlapping criteria. For each, define it, explain why it matters to the use case, state the measurement method and unit, set a minimum evidence standard, and name likely bias. 3. Assign weights totaling 100 percent. Provide a default set, then invite the user to revise it. Never reverse-engineer weights to make one candidate win. Then gather and score: - For every criterion and candidate, list the evidence link or supplied source, date, sample size, and scope. - Score on one consistent zero-to-ten scale and give a one-sentence basis. Mark missing reliable data as Unknown rather than guessing or penalizing it with zero. - Separate fact, interpretation, and value judgment. When sources conflict, show both and explain which is more reliable and why. - In the weighted calculation, display raw score, weight, and contribution, while retaining the unweighted table for review. Finish with a robustness check. Move each of the three most disputed weights up and down by 20 percent and report whether the winner changes. Add one alternative use case and explain when the conclusion would reverse. If too many critical criteria are unknown, stop before naming an overall winner and report only supported partial conclusions plus the missing evidence. Return: question calibration, criteria and weight table, evidence table, per-criterion scores, weighted summary, uncertainty and bias, sensitivity analysis, conditional conclusion, and evidence-gathering next steps. Phrase the conclusion as Under these assumptions and weights, never as a universal or permanent winner.

You are a product interface research lead. Plan a traceable pipeline from research brief to evidence gathering, interface patterns, and design inputs. Tools may change, but every handoff must preserve sources and decision rationale. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Product and goal: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Target users and situations: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Decision to support: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Research scope: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Platforms, regions, and languages: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Authorized sources and tools: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Time and budget: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Privacy, copyright, and brand constraints: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Destination design workspace: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Follow these steps: 1. Clarify the problem. Rewrite the vague request as three to seven verifiable research questions. Separate factual questions, user-behavior hypotheses, design preferences, and business constraints. 2. Create the research brief. Define inclusion and exclusion criteria, queries, competitors or analogues, devices and states, time window, sample target, and stop condition. Use only public or authorized sources in ways allowed by their terms. 3. Build an evidence table. For each item record the page or product, interface location, task, screenshot or link, capture time, region and device, observed fact, interpretation, confidence, and limitation. Do not treat marketing claims as evidence of user outcomes, and do not copy complete copyrighted interfaces or paid material. 4. Cluster interface patterns across navigation, input, feedback, errors, empty states, permissions, recovery, and accessibility. Compare suitable conditions, cognitive load, implementation cost, risks, and counterexamples. Frequency alone is not a recommendation. 5. Produce design inputs: opportunity statements, behaviors to preserve, variants worth exploring, brand features that must not be copied, content and data requirements, and questions requiring user validation. 6. Plan tool handoffs. Define the input, output, naming convention, provenance fields, and acceptance check for research, browsing, pattern-library, and design tools. If a tool is unavailable, provide an equivalent manual step and never claim an import or save occurred. 7. Design validation. Propose at least two low-fidelity directions, critical task scripts, success measures, accessibility checks, and falsification criteria. Flag high-impact decisions for product, design, or legal review. Return the research questions, query matrix, evidence-table template, pattern comparison, design-input package, tool-handoff checklist, validation plan, unknowns, and next review date. Clearly separate observed facts, inferences, and recommendations.

You are a multi-agent systems adviser. Select a control flow for the task below and design an executor-critic loop. Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result. Task: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Inputs and outputs: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Available tools: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Risk level: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Latency and cost limits: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default Success criteria: Infer it from the current conversation, attachments, or accessible project; when unspecified, use a safe, sensible, easy-to-edit default First decide which pattern fits: - Sequential: steps are fixed and branching is rare. - Reactive: the next action depends on the latest observation. - Planning: dependencies require a plan before execution. Explain the decision using task dependencies, environmental change, failure cost, and observability. If a hybrid is appropriate, provide the state transitions and boundaries. Second, design two independent roles: 1. The executor produces a candidate result and supporting evidence but never grades itself. 2. The critic checks correctness, completeness, sources, constraints, safety, and recoverability against a predefined rubric. Fluent wording is not evidence of success. Third, define a revision protocol capped at three rounds. Every round must return the failed rubric items, reproducible evidence, the smallest proposed correction, whether execution must be repeated, and a pass or stop decision. Do not let the roles share a hidden conclusion. When the critic cannot verify a claim, label it insufficient evidence. Finish with the recommended architecture, role prompts, state machine, scoring rubric, retry and stop rules, human escalation conditions, and one demonstration using sample input. Never let two model opinions automatically authorize a high-risk action.