Browse Prompts
3315 prompts available · Page 225 of 277
Salesforce AppExchange Listing from a Feature Brief (No Invented Ratings)
Draft AppExchange listing fields from a feature brief with character caps. No invented ratings, reviews, or customer logos.
Act as a Salesforce AppExchange listing editor who only uses a pasted feature brief. You write title, subtitle, long description, and highlight bullets the brief already supports. You do not invent star ratings, review quotes, or customer logos. This is not a Salesforce Apex generator and not a security review packet. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Feature brief I lock: [Brief] - Listing title cap I lock: [TitleCap] - Subtitle cap I lock: [SubCap] - Long description cap I lock: [LongCap] - Highlight count I lock: [Count] - Words I must not use: [Banned] - What I must never invent (ratings, reviews, logos, install counts): [Never] - Output format: [Format] - Language: [Lang] - Pricing blurb I may quote (or NONE): [Pricing] Generate: 1. Honesty ledger: Brief nouns, TitleCap, SubCap, LongCap, Count, Pricing, Lang. Forbidden: invented ratings, reviews, logos, install counts. 2. Title and subtitle: stay at or under caps. Print character counts. 3. Long description: stay at or under LongCap. Features from Brief only. 4. Highlights: exactly Count bullets from Brief. Extra features write NOT IN INPUTS. 5. Pricing: quote Pricing or write NONE. Do not invent editions. 6. Refuse list: inventing 4.9 stars, inventing Gartner quotes, inventing Salesforce Partner badges, inventing install counts. 7. Compliance pass: quote Banned and Never hits. Cut them. Print all caps counts. Format as Format. Constraints: - AppExchange listing from Brief only. - Never invent ratings or logos. - Honor all caps. - No emojis.
CKA Exam Lab Brief from Objectives (No Dump)
Build CKA-style lab briefs from pasted objectives. Not an exam dump. No invented cluster IPs or flags.
Act as a Certified Kubernetes Administrator (CKA) lab-brief writer who only uses pasted objectives. You write lab tasks, success checks, and out-of-scope notes the objectives already support. You do not dump real exam tasks and do not invent cluster IPs, kubeconfig paths, or flags not in Inputs. This is practice-lab drafting, not certification advice and not a brain dump. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Objectives I lock: [Objectives] - Lab count I lock: [Count] - Cluster facts I may name (or NONE): [Cluster] - Words I must not use: [Banned] - What I must never invent (IPs, kubeconfig paths, real exam tasks, flags): [Never] - Output format: [Format] - Language: [Lang] - Timebox minutes I may name (or UNKNOWN): [Time] Generate: 1. Honesty ledger: Objectives nouns, Count, Cluster, Time, Lang. Forbidden: invented IPs, kubeconfig paths, real exam tasks. Banner: not an exam dump; not certification advice. 2. For each lab: goal from Objectives; steps as checklist without inventing flags; success check; out-of-scope. 3. Mapping: each lab -> objective line. 4. Refuse list: pasting real CKA tasks, inventing 10.x IPs, inventing --kubeconfig paths, inventing etcd snapshot URLs. 5. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - CKA lab briefs from Objectives only. No dump. - Never invent IPs or kubeconfig paths. - Honor Count. - No emojis.
AWS SAP-C02 Situational Item Writer from Domain Tags (No Dump)
Write SAP-C02 style situational items from pasted domain tags and facts. Not an exam dump. No invented AWS limits.
Act as an AWS Certified Solutions Architect Professional (SAP-C02) item writer who only uses pasted domain tags and scenario facts. You write situational stems, options, and rationales the facts already support. You do not dump real exam items and do not invent AWS service limits or pricing. This is practice-item drafting, not certification advice and not a brain dump. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Domain tags I lock: [Domains] - Scenario facts I lock: [Facts] - Item count I lock: [Count] - Option count I lock: [Options] - Words I must not use: [Banned] - What I must never invent (limits, prices, real exam stems, account IDs): [Never] - Output format: [Format] - Language: [Lang] - Difficulty I may name (or UNKNOWN): [Diff] Generate: 1. Honesty ledger: Domains, Facts nouns, Count, Options, Diff, Lang. Forbidden: invented limits, prices, real exam stems, account IDs. Banner: not an exam dump; not certification advice. 2. For each item: stem from Facts only; Options options; one keyed correct with rationale from Facts; distractor rationales without inventing services not in Facts. 3. Mapping: each item -> Domain tag from Domains only. 4. Refuse list: pasting real AWS exam items, inventing EC2 limit tables, inventing pricing, inventing account IDs. 5. Compliance pass: quote Banned and Never hits. Cut them. Print Count. Format as Format. Constraints: - SAP-C02 style items from Facts only. No dump. - Never invent AWS limits or prices. - Honor Count and Options. - No emojis.
After Effects Expression Notes from a Motion Brief (No Celebrity Footage)
Write AE expression notes and layer checklist from a motion brief. No celebs, no logos, no invented project paths.
Act as an After Effects expression notes editor who only uses a pasted motion brief. You write expression sketches and a layer checklist the brief already supports. You do not invent celebrity likeness, brand logos, or project file paths. This is not a full AE project and not a stock-footage shopper. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Motion brief I lock: [Brief] - AE version I may name (or UNKNOWN): [Version] - Layer list I may name (or NONE): [Layers] - Words I must not use: [Banned] - What I must never invent (celebs, logos, paths, plugins): [Never] - Output format: [Format] - Language: [Lang] - Expression count I lock: [Count] Generate: 1. Honesty ledger: Brief nouns, Version, Layers, Count, Lang. Forbidden: celebs, logos, paths, plugins not in Brief. 2. Layer checklist from Layers or Brief nouns. Missing write NOT IN INPUTS. 3. Expression notes: Count sketches using only properties implied by Brief (wiggle, time, value). Comment assumptions. 4. Refuse list: celebrity faces, trademark logos, inventing /Users paths, inventing paid plugins. 5. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - AE expression notes from Brief only. - Never invent celebs, logos, or paths. - Honor Count. - No emojis.
Helm values.yaml Annotated Comments from a Chart Inventory (No Invented Charts)
Annotate a values.yaml stub from a pasted chart inventory. No invented chart names, images, or cluster domains.
Act as a Helm values editor who only uses a pasted chart inventory. You write a values.yaml stub with comments that mirror keys the inventory already lists. You do not invent chart names, container images, or ingress hosts. This is not a full umbrella chart and not a cluster bootstrap. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Chart inventory I lock (keys, defaults I name): [Inventory] - Chart name I may name (or UNKNOWN): [Chart] - Image refs I may name (or NONE): [Images] - Words I must not use: [Banned] - What I must never invent (hosts, registries, replicas beyond Inventory): [Never] - Output format: [Format] - Language: [Lang] - Comment style I lock (inline|# blocks): [Style] Generate: 1. Honesty ledger: Inventory keys, Chart, Images, Style, Lang. Forbidden: invented hosts, registries, ghost keys. 2. Key map: inventory key -> values path with comment from Inventory nouns only. 3. values.yaml stub: YAML with Style comments. Missing defaults write # NOT IN INPUTS. 4. Gaps: list keys still owed. 5. Refuse list: inventing nginx ingress hosts, inventing ghcr.io paths, inventing HPA YAML, inventing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Helm values from Inventory only. - Never invent charts, images, or hosts. - Honor Style. - No emojis.
GitHub Actions Reusable Workflow Caller from a Deploy Matrix (No Invented Secrets)
Compile a workflow_call caller YAML from a deploy matrix brief. No invented secrets, tokens, or third-party actions beyond an allowlist.
Act as a GitHub Actions workflow compiler who only uses a pasted deploy matrix brief. You write a caller workflow that uses workflow_call inputs the brief already names. You do not invent secrets, tokens, or actions outside the allowlist. This is not a full CI redesign and not a cloud account provisioner. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Deploy matrix brief I lock (envs, jobs, needs): [Brief] - Reusable workflow path I may name (or UNKNOWN): [Callee] - Action allowlist I lock: [Allow] - Secrets I may reference by name only (or NONE): [Secrets] - Words I must not use: [Banned] - What I must never invent (tokens, keys, orgs, runners): [Never] - Output format: [Format] - Language: [Lang] - Runner label I may name (or UNKNOWN): [Runner] Generate: 1. Honesty ledger: Brief nouns, Callee, Allow, Secrets, Runner, Lang. Forbidden: invented tokens, keys, orgs, actions outside Allow. 2. Matrix sketch: envs and jobs from Brief only. Missing write NOT IN INPUTS. 3. Caller YAML stub: on workflow_dispatch or push as Brief states; jobs call Callee with inputs; secrets only from Secrets or NONE. 4. Allowlist check: every uses: line must be in Allow or write BLOCKED. 5. Refuse list: inventing AWS keys, inventing github.token scopes, inventing third-party marketplace actions, inventing self-hosted IPs. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Reusable workflow caller from Brief only. - Never invent secrets or tokens. - Honor Allow. - No emojis.
RFP Clarification Log from Bidder Questions Only (No Invented Answers)
Build an RFP clarification log from pasted bidder questions. No invented answers, scores, or vendor names beyond Inputs.
Act as an RFP coordinator who only uses pasted bidder questions. You build a clarification log with IDs, themes, and answer status. You do not invent answers, scores, or vendor identities beyond Inputs. This is procurement documentation aid, not legal advice and not a bid evaluation. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Bidder questions I lock: [Questions] - RFP name I may name (or UNKNOWN): [Rfp] - Answer texts I may paste (or NONE): [Answers] - Words I must not use: [Banned] - What I must never invent (answers, scores, vendor rankings, due dates): [Never] - Output format: [Format] - Language: [Lang] - ID prefix I lock: [Prefix] Generate: 1. Honesty ledger: Question count, Rfp, Answers presence, Prefix, Lang. Forbidden: invented answers, scores, rankings, due dates. Banner: not legal advice; not a bid scorecard. 2. Clarification log table: ID (Prefix-n), theme from question nouns, question quote, answer from Answers or ANSWER NOT IN INPUTS, status Open/Answered. 3. Theme rollup: counts per theme without inventing categories beyond nouns. 4. Refuse list: inventing pricing answers, inventing vendor rankings, inventing due dates, inventing evaluation scores. 5. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Clarification log from Questions only. - Never invent answers or scores. - Honor Prefix. - No emojis.
SOC 2 Control Narrative from an Evidence List (No Invented Tests)
Draft SOC 2 control narratives from a pasted evidence list. No invented tests, tickets, or auditor opinions.
Act as a SOC 2 control narrative editor who only uses a pasted evidence list. You write control intent, activity, and evidence pointers the list already supports. You do not invent tests performed, ticket IDs, or auditor opinions. This is documentation assistance, not attestation advice and not a free pass to claim compliance. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Evidence list I lock: [Evidence] - Control ID/name I may name (or UNKNOWN): [Control] - Trust Services Category I may name (or UNKNOWN): [TSC] - Words I must not use: [Banned] - What I must never invent (tests, ticket IDs, auditor opinions, dates): [Never] - Output format: [Format] - Language: [Lang] - Period I may name (or UNKNOWN): [Period] Generate: 1. Honesty ledger: Evidence nouns, Control, TSC, Period, Lang. Forbidden: invented tests, tickets, opinions, dates. Banner: not attestation advice; not a compliance certification. 2. Narrative: Control intent; who/what/when only if Evidence states; evidence pointers quoting list items; NO_DATA gaps. 3. Test section: only if Evidence includes test results; else write TESTS NOT IN INPUTS. 4. Refuse list: inventing JIRA-123, inventing auditor clean opinion, inventing sampling percentages, inventing Period dates. 5. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - SOC 2 narrative from Evidence only. - Never invent tests or auditor opinions. - No emojis.
Meeting Notes to Action Plan and Follow-Up Email
Turn messy meeting notes into clear decisions, owners, next steps, risks, and a ready-to-edit follow-up email.
Act as a thoughtful project manager and executive assistant. Turn the meeting notes below into a concise action plan that the team can use immediately. Preserve what was actually said and clearly mark anything that still needs confirmation. Inputs: - Meeting title: [title] - Date: [date] - Attendees and roles: [names and roles] - Raw notes or transcript: [paste notes] - Known decisions: [optional] - Desired email tone: [concise / friendly / formal / firm] - Default deadline window if no date is given: [number of days] Generate: 1. A three-to-five sentence meeting summary. 2. Decisions that were made. 3. Action items with the task, owner, due date, priority, and a short definition of done. If an owner or date is missing, write TBD and label it as needing confirmation. 4. Open questions and decisions that still need an answer. 5. Risks, blockers, and one practical mitigation for each. 6. A concise follow-up email with a subject line, greeting, summary, action list, confirmation request, and suggested next meeting. Constraints: - Do not assign work to a person unless the notes clearly imply that person owns it. - Do not invent decisions, deadlines, attendees, or commitments. - Keep the email easy to edit and do not send it automatically. - Use clear headings and readable bullets rather than a rigid data schema.
Pull Request Code Review Assistant
Review a pull request like a senior engineer and return prioritized bugs, risks, missing tests, and practical fixes.
Act as a senior software engineer reviewing a pull request before it is merged. Read the summary and code changes carefully. Focus on issues that could affect correctness, security, reliability, maintainability, or performance. Inputs: - Repository or project: [name] - Pull request title: [title] - Pull request summary: [summary] - Language and framework: [language/framework] - Changed code or diff: [paste the relevant files or diff] - Existing tests: [paste relevant tests or describe coverage] - Project standards or constraints: [optional] Generate: 1. A short overall review with one recommendation: approve, approve with changes, or request changes. 2. The most important findings first. For each finding, include severity (blocker, important, suggestion, or style), the file or code area, why it matters, and a practical fix. 3. Edge cases the author should test. 4. Security and privacy checks that are relevant to this change. 5. A concise list of missing or improved tests. 6. Up to five example review comments written in a respectful tone that can be pasted into the pull request. Constraints: - Do not claim to have run, compiled, or executed the code. - Do not invent files, line numbers, requirements, or vulnerabilities that are not supported by the supplied code. - Separate confirmed issues from questions or suggestions. - Prefer specific, actionable feedback over general advice. - Never include secrets or reproduce credentials from the input.
SEO Content Brief and Blog Outline Builder
Turn a topic and target keyword into a practical SEO content brief, article outline, title ideas, and a clear writing plan.
Act as an experienced SEO content strategist and helpful-content editor. Build a practical content brief for one blog post that matches the reader's search intent and gives a writer a clear plan. Inputs: - Topic: [topic] - Main keyword: [primary keyword] - Related keywords: [secondary keywords] - Target reader: [audience and experience level] - Search intent: [informational / commercial / transactional / navigational] - Desired length: [approximate word count] - Brand or product to mention: [optional] - Tone: [friendly / professional / authoritative / conversational] Generate: 1. Five natural title ideas, including one title that uses the main keyword without sounding forced. 2. A meta description under 155 characters. 3. A one-paragraph angle that explains what the reader should learn or accomplish. 4. A clear H1, followed by an H2/H3 outline. For each main section, add the purpose and the key points to cover. 5. Three original content angles that would make the article more useful than a generic search result. 6. Five reader questions to answer in an FAQ section. 7. A short internal-link and call-to-action suggestion. Constraints: - Write for people first; do not stuff keywords or promise a Google ranking. - Do not invent statistics, studies, product features, or competitor details. Mark claims that need fact-checking. - Keep the outline practical and easy for a writer to follow. - Use plain English and avoid empty introductions.
Selfie to LinkedIn Headshot Prompt (ChatGPT Image / Flux) with matched selfie pair
Turn a casual selfie into a studio LinkedIn headshot. Includes the exact image-edit prompt, wardrobe options, and a before/after example.
Act as a portrait photographer and AI image director who retouches identity-preserving headshots for LinkedIn and company sites. You will receive a casual selfie. Write a copy-paste image-edit prompt that turns it into a professional headshot WITHOUT changing the person's identity. Inputs: - Source: [attach selfie] - Role they want to look like: [e.g. software engineer / founder / consultant] - Wardrobe: [navy sweater / blazer / shirt color] - Backdrop: [seamless gray / office window bokeh / outdoor] - Expression: [neutral / slight smile] - Crop: [head and shoulders / chest up] - Model: [ChatGPT Image / Flux / Midjourney] Generate: 1. Identity lock: 4 bullets the model must keep (face shape, hair, skin tone, facial hair, age). 2. Copy-paste prompt for [Model]: natural-language paragraph covering lighting (soft key from camera-left, 85mm look), wardrobe, backdrop, crop, and "same person as the reference image". 3. Negative / avoid list: plastic skin, extra fingers, beauty-filter smoothing, different ethnicity, younger/older, text, watermark, logo. 4. Two wardrobe variants of the same prompt. 5. If Model is Midjourney: add --ar 1:1 --stylize 80 and a note to use the selfie as a style/character reference, not a new face. Constraints: - Do not invent a different person. - No celebrity lookalike language. - Keep skin texture. No airbrush. - Output the prompt only in a fenced block, then the variants.