A smaller prompt library designed for responsible reuse.

Act as a senior SEO strategist, content architect, and subject-matter editor. Create a complete, evidence-led SEO content brief for the following page.

INPUTS
- Primary topic or query: [TARGET KEYWORD]
- Audience and level of knowledge: [AUDIENCE]
- Country, language, or market: [MARKET]
- Business objective and desired conversion: [BUSINESS GOAL]
- Product, service, or website context: [ADD CONTEXT]
- Existing pages that may overlap: [PASTE URLS OR TITLES]
- First-party evidence available: [CUSTOMER QUESTIONS, DATA, EXPERT NOTES]
- Verified SERP or competitor observations: [PASTE MANUAL RESEARCH OR WRITE NONE]

PHASE 1 — DIAGNOSIS
1. Restate the search problem in plain language.
2. Separate the likely primary intent, secondary intents, reader stage, and decision the visitor is trying to make.
3. Identify what must be manually validated in the live search results. Never pretend to have current SERP, ranking, traffic, or keyword-volume data.
4. Assess whether this should be a guide, comparison, landing page, glossary, tool, template, or another format. Explain the choice.
5. Define the page’s unique information gain: the original experience, data, framework, examples, tool, or point of view needed to make it better than a generic summary.

PHASE 2 — CONTENT SPECIFICATION
Return:
- Three accurate title-tag options with different angles
- A recommended H1 and concise meta description
- A one-sentence editorial promise
- A detailed H2/H3 outline in the order a reader needs it
- The purpose of every major section
- Questions each section must answer
- Entities, concepts, definitions, and comparisons to cover naturally
- Evidence required: first-party experience, expert input, examples, screenshots, data, sources, or demonstrations
- Claims that require verification or citation
- Recommended tables, checklists, diagrams, calculators, templates, or interactive elements
- What to exclude to avoid scope drift and keyword cannibalization

PHASE 3 — SITE INTEGRATION
Create an internal-link plan with:
- Relevant pages that should link to this page
- Pages this article should link to
- Natural anchor concepts
- Reader reason for each link
- Potential overlap, merge, redirect, or refresh decisions

PHASE 4 — TRUST AND CONVERSION
Define:
- Author expertise or review evidence the page should display
- Transparency notes and limitations
- A primary and secondary call to action matched to search intent
- Objections or anxieties to address before the CTA
- Accessibility and mobile-reading requirements

PHASE 5 — ACCEPTANCE CRITERIA
Finish with:
- A prioritized production checklist
- A fact-check checklist
- An originality and helpfulness checklist
- Five ways this page could fail
- The analytics events and Search Console signals to review after publication
- A 30/60/90-day refresh plan

Do not draft the full article. Do not invent live data. Clearly label every assumption, research gap, and item requiring human verification.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Act as a senior SEO strategist and information architect. Build a semantic topical map for [CORE TOPIC] for [AUDIENCE]. The site offers [SITE OFFER]. Existing relevant pages: [EXISTING PAGES]. First-party expertise or evidence we can contribute: [FIRST-PARTY EXPERTISE].

Start by defining the central reader problem, the decisions readers need to make, and the important entities, processes, attributes, alternatives, and risks connected to the topic. Group the coverage into a small number of coherent clusters. For every proposed page, provide its unique purpose, primary intent, audience stage, recommended format, essential questions, original evidence required, parent page, child pages, and natural internal-link relationships.

Identify pages that would overlap, compete, or add little value. Recommend which ideas to merge, exclude, or treat as sections instead of separate URLs. Finish with a prioritized publishing sequence that establishes a useful core before expanding the cluster. Do not invent keyword volume, ranking difficulty, trends, or live search results.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Create an original-evidence content plan for [TOPIC] aimed at [AUDIENCE] and supporting [BUSINESS GOAL]. Available experience: [AVAILABLE EXPERIENCE]. Available data, examples, screenshots, interviews, or tests: [DATA OR EXAMPLES].

Separate what we know directly from what requires research. Propose five content assets that use our evidence to answer a meaningful reader question better than a generic summary could. For each asset, define the unique claim or lesson, the evidence needed, the practical deliverable for the reader, the best page format, the fact-checking requirements, and the internal pages that should support it.

Include a plan for obtaining missing first-party evidence through small tests, interviews, demonstrations, or analysis. Reject ideas that rely mainly on rewriting existing articles. Finish with a quality rubric covering originality, accuracy, completeness, transparency, usefulness, and maintenance.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Design a reusable prompt system for [RECURRING TASK], used by [USERS]. Typical inputs: [INPUTS]. Required output: [OUTPUT REQUIREMENTS]. Known failures: [KNOWN FAILURES].

Define the task contract: objective, user, source hierarchy, mandatory inputs, optional inputs, missing-information behavior, operating steps, decision rules, boundaries, output schema, examples, and acceptance criteria. Create the master prompt with clearly named variables and instructions that remain portable across ChatGPT, Claude, and Gemini.

Then create a five-case evaluation set covering normal use, incomplete input, conflicting evidence, an edge case, and an unsafe or out-of-scope request. Provide a scoring rubric, version label, change log template, owner, review trigger, and rollback rule. Do not optimize for one polished demonstration.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Design a governed prompt library for [TEAM] covering [USE CASES] across [TOOLS]. Risk levels: [RISK LEVELS]. Current prompts or storage: [CURRENT PROMPTS].

Define the record schema for each prompt: identifier, title, owner, purpose, intended users, model compatibility, required inputs, prompt text, examples, evaluation cases, limitations, approved data classes, status, version, last review, and change history. Propose roles and permissions for authors, reviewers, users, and administrators.

Create submission, test, approval, publication, monitoring, update, deprecation, and incident workflows. Include naming rules, duplicate detection, search tags, adoption metrics, failure reporting, and a 30-day pilot plan. Keep controls proportional to risk and avoid unnecessary bureaucracy.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Create an evaluation suite for this prompt: [PROMPT]. Task: [TASK]. Definition of a good output: [GOOD OUTPUT]. Known failure modes: [FAILURE MODES]. Models or versions to compare: [MODELS].

Design at least twelve test cases covering typical inputs, missing context, noisy input, conflicting sources, boundary conditions, adversarial phrasing, format pressure, and out-of-scope requests. For each case, provide the input, expected behavior, prohibited behavior, critical assertions, and severity if it fails.

Build a scoring rubric for correctness, evidence use, instruction adherence, completeness, usefulness, uncertainty handling, safety, format, latency, and cost where available. Define pass thresholds, reviewer instructions, comparison rules, regression triggers, and how to document a prompt or model update.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Synthesize [SOURCES] to answer [RESEARCH QUESTION] for decision [DECISION]. Create a source table with type, date, relevance, and limitations. Then summarize converging findings, disagreements, plausible explanations, evidence gaps, and practical implications. Distinguish direct evidence from inference. Do not invent citations or details not present in the sources. State what the evidence can support, what it cannot support, and the next evidence worth collecting.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Evaluate [SOURCE MATERIAL] as evidence for [CLAIM] in [USE CASE]. Assess authorship, expertise, publication context, methodology, sample, transparency, incentives, recency, relevance, and corroboration. Separate issues that reduce credibility from issues that merely limit applicability. Quote only short necessary fragments. Return a confidence assessment with reasons, what can safely be cited, what needs qualification, and stronger source types to seek.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Compare [OPTIONS] for [DECISION CONTEXT] using [CRITERIA] and evidence [EVIDENCE]. Define every criterion before scoring. For each option provide supported strengths, limitations, costs, risks, dependencies, and unknowns. Use the same evidence standard across options. Show how the recommendation changes when criterion weights or key assumptions change. If the evidence is insufficient, recommend a test rather than a false winner.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Act as an n8n solution architect. Design a production-minded workflow for [PROCESS] using [APPS AND APIS]. Input data: [INPUT DATA]. Allowed actions: [ALLOWED ACTIONS]. Risk level and approval requirements: [RISK LEVEL].

Return a node-by-node blueprint covering trigger, authentication, validation, normalization, deterministic routing, AI operation, prompt and context, structured output, confidence or validation checks, human approval, downstream action, persistence, notification, and completion. For every node, specify inputs, outputs, error path, retry behavior, idempotency need, and sensitive-data considerations.

Separate decisions that should be deterministic from judgments appropriate for AI. Add timeouts, rate-limit handling, cost controls, logging, test data, rollback, and a staged launch plan. Do not invent API fields or n8n node capabilities; mark documentation checks explicitly.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Act as a defensive AI application security reviewer. Create a prompt-injection threat model for [AI APPLICATION]. Input sources: [INPUT SOURCES]. Data and secrets the system can access: [DATA AND SECRETS]. Connected tools and possible actions: [TOOLS AND ACTIONS]. User roles and permissions: [USER ROLES].

Draw the trust boundaries from each input source through retrieval, memory, model calls, output handling, tools, and final destinations. For every boundary, identify who controls the content, what the model can see, what action could follow, and the worst credible impact if untrusted text changes model behavior.

Create a risk register covering direct and indirect prompt injection, retrieved-content manipulation, memory contamination, tool-result injection, excessive permissions, cross-user data exposure, unsafe output rendering, unauthorized actions, and weak approval paths. For each risk, state prerequisites, affected asset, existing control, control gap, likelihood, impact, detection signal, owner, and defensive test.

Recommend layered controls: data minimization, source labeling, isolation, input screening, structured contracts, least-privilege tools, server-side authorization, parameter validation, output sanitization, human approval, monitoring, rate limits, incident response, and regression tests. Do not provide attack payloads or instructions for bypassing safeguards. State clearly which controls must be implemented outside the prompt.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.

Act as a pragmatic senior software reviewer. Review [CODE] for [GOAL] in [STACK] under [CONSTRAINTS]. Check correctness, security, performance, accessibility where relevant, maintainability, and tests. Prioritize findings by severity. For every finding quote only the smallest necessary fragment, explain the concrete impact, and propose a minimal fix. Separate confirmed issues from questions and preferences. Finish with missing tests and a concise ship/no-ship recommendation.

REVIEWED EXECUTION PROTOCOL
1. Begin by restating the objective, intended audience, supplied evidence, constraints, and missing information.
2. Ask no more than three high-impact clarification questions when missing context would materially change the result. Otherwise continue with clearly labeled assumptions.
3. Work from the supplied facts. Do not invent research, statistics, quotations, customer evidence, rankings, citations, capabilities, or results.
4. Make the reasoning auditable: distinguish evidence, interpretation, recommendation, risk, and open question.
5. Produce a decision-ready deliverable, not generic advice. Prioritize the most valuable actions and explain the trade-offs.
6. Finish with:
   - Assumptions to validate
   - Risks and failure modes
   - Recommended next actions
   - Quality-control checklist

QUALITY STANDARD
The result must be specific enough for an experienced professional to use, concise enough to review, and honest about uncertainty. Reject vague filler, repeated ideas, unsupported superlatives, and fabricated facts.