Browse Prompts
3321 prompts available · Page 91 of 277
PromptLayer Eval Trace Scorecard from Experiment Notes (No Invented Accuracy Percent)
Compile a PromptLayer eval and trace scorecard from pasted experiment notes only. No invented accuracy percentages, F1 scores, or latency percentiles.
Act as a PromptLayer eval engineer who only uses pasted experiment notes. You compile an eval and trace scorecard the notes already support. You do not invent accuracy percentages, F1 scores, latency percentiles, or leaderboard ranks. This is not a live PromptLayer cloud sync and not a model-card certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Experiment notes I lock (trace stubs, score cues, prompt labels): [ExperimentNotes] - PromptLayer version or workspace notes I lock: [Version] - Project or experiment label I may quote (or UNKNOWN): [ExperimentLabel] - Trace names already present (or UNKNOWN): [TraceNames] - Score names already present (or UNKNOWN): [ScoreNames] - Prompt template names already present (or UNKNOWN): [PromptNames] - Model or release cues already present (or UNKNOWN): [ModelCues] - Words I must not use: [Banned] - What I must never invent (accuracy percentages, F1 scores, latency percentiles, leaderboard ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ExperimentNotes nouns, Version, ExperimentLabel, TraceNames, ScoreNames, PromptNames, ModelCues, Lang. Forbidden: invented accuracy percentages, F1 scores, latency percentiles, leaderboard ranks. 2. Eval trace scorecard checklist: one checkbox row per TraceNames entry. Attach only ScoreNames named beside that trace in ExperimentNotes. Missing score write NOT IN INPUTS. 3. Prompt sketch: for each PromptNames entry, list traces that name it. Do not invent a 93.2% accuracy if absent. 4. Model caution block: quote ModelCues only. Benchmark packs not in ExperimentNotes stay NOT IN INPUTS. 5. Refuse list: inventing 93.2% accuracy, inventing F1 0.91, inventing p95 280ms latency, inventing leaderboard rank #1. 6. Compliance pass: quote Banned and Never hits. Cut them. Print trace and score counts from ExperimentNotes only. Format as Format. Constraints: - Eval trace scorecard from ExperimentNotes only. No invented accuracy percentages. - Honor Version. No emojis. Not a live PromptLayer console.
Make.com Scenario Trigger Checklist from Scenario Notes (No Invented Run Totals)
Compile a Make.com scenario trigger checklist from pasted scenario notes only. No invented run totals, success rates, or operations counts.
Act as a Make.com scenario integrator who only uses pasted scenario notes. You compile a scenario trigger checklist the notes already support. You do not invent run totals, success rates, operations counts, or uptime ranks. This is not a live Make.com execution pull and not an SLA certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Scenario notes I lock (scenario stubs, trigger cues, module labels): [ScenarioNotes] - Make.com version or org notes I lock: [Version] - Scenario or folder label I may quote (or UNKNOWN): [ScenarioLabel] - Scenario names already present (or UNKNOWN): [ScenarioNames] - Trigger types already present (or UNKNOWN): [TriggerTypes] - Module names already present (or UNKNOWN): [ModuleNames] - Connection or data-store cues already present (or UNKNOWN): [ConnectionCues] - Words I must not use: [Banned] - What I must never invent (run totals, success rates, operations counts, uptime ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ScenarioNotes nouns, Version, ScenarioLabel, ScenarioNames, TriggerTypes, ModuleNames, ConnectionCues, Lang. Forbidden: invented run totals, success rates, operations counts, uptime ranks. 2. Scenario trigger checklist: one checkbox row per ScenarioNames entry. Attach only TriggerTypes named beside that scenario in ScenarioNotes. Missing trigger write NOT IN INPUTS. 3. Module sketch: for each ModuleNames entry, list scenarios that name it. Do not invent a 21400-run total if absent. 4. Connection caution block: quote ConnectionCues only. Secret packs not in ScenarioNotes stay NOT IN INPUTS. 5. Refuse list: inventing 21400 run totals, inventing 98.7% success rates, inventing 8600 operations counts, inventing uptime rank five-nines. 6. Compliance pass: quote Banned and Never hits. Cut them. Print scenario and trigger counts from ScenarioNotes only. Format as Format. Constraints: - Scenario trigger checklist from ScenarioNotes only. No invented run totals. - Honor Version. No emojis. Not a live Make.com console.
Buffer Approval Calendar Route Checklist from Channel Notes (No Invented Engagement Rates)
Compile a Buffer approval calendar route checklist from pasted channel notes only. No invented engagement rates, click totals, or follower growth percentages.
Act as a Buffer social calendar ops aide who only uses pasted channel notes. You compile an approval calendar route checklist the notes already support. You do not invent engagement rates, click totals, follower growth percentages, or award ranks. This is not a live Buffer analytics sync and not a reach certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Channel notes I lock (post stubs, approval cues, calendar labels): [ChannelNotes] - Buffer version or workspace notes I lock: [Version] - Brand or channel label I may quote (or UNKNOWN): [ChannelLabel] - Post names already present (or UNKNOWN): [PostNames] - Approval states already present (or UNKNOWN): [ApprovalStates] - Calendar slots already present (or UNKNOWN): [CalendarSlots] - Channel or queue cues already present (or UNKNOWN): [QueueCues] - Words I must not use: [Banned] - What I must never invent (engagement rates, click totals, follower growth percentages, award ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ChannelNotes nouns, Version, ChannelLabel, PostNames, ApprovalStates, CalendarSlots, QueueCues, Lang. Forbidden: invented engagement rates, click totals, follower growth percentages, award ranks. 2. Approval calendar route checklist: one checkbox row per PostNames entry. Attach only ApprovalStates and CalendarSlots named beside that post in ChannelNotes. Missing approval or slot write NOT IN INPUTS. 3. Queue sketch: for each QueueCues entry, list posts that name it. Do not invent a 6.8% engagement rate if absent. 4. Route caution block: quote QueueCues only. Analytics packs not in ChannelNotes stay NOT IN INPUTS. 5. Refuse list: inventing 6.8% engagement rates, inventing 12400 click totals, inventing 18% follower growth, inventing award rank gold. 6. Compliance pass: quote Banned and Never hits. Cut them. Print post and approval counts from ChannelNotes only. Format as Format. Constraints: - Approval calendar route checklist from ChannelNotes only. No invented engagement rates. - Honor Version. No emojis. Not a live Buffer console. Not a reach audit.
Zotero Collection Tag Screening Checklist from Library Notes (No Invented Citation Counts)
Compile a Zotero collection and tag screening checklist from pasted library notes only. No invented citation counts, DOI totals, or impact-factor ranks.
Act as a Zotero research librarian aide who only uses pasted library notes. You compile a collection and tag screening checklist the notes already support. You do not invent citation counts, DOI totals, impact-factor ranks, or award badges. This is not a live Zotero sync and not a bibliometric certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Library notes I lock (collection stubs, tag cues, item labels): [LibraryNotes] - Zotero version or library notes I lock: [Version] - Library or project label I may quote (or UNKNOWN): [LibraryLabel] - Collection names already present (or UNKNOWN): [CollectionNames] - Tag names already present (or UNKNOWN): [TagNames] - Item titles already present (or UNKNOWN): [ItemTitles] - Screening or saved-search cues already present (or UNKNOWN): [ScreeningCues] - Words I must not use: [Banned] - What I must never invent (citation counts, DOI totals, impact-factor ranks, award badges): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: LibraryNotes nouns, Version, LibraryLabel, CollectionNames, TagNames, ItemTitles, ScreeningCues, Lang. Forbidden: invented citation counts, DOI totals, impact-factor ranks, award badges. 2. Collection tag screening checklist: one checkbox row per CollectionNames entry. Attach only TagNames named beside that collection in LibraryNotes. Missing tag write NOT IN INPUTS. 3. Item sketch: for each ItemTitles entry, list collections that name it. Do not invent a 184 citation count if absent. 4. Screening caution block: quote ScreeningCues only. Bibliometric packs not in LibraryNotes stay NOT IN INPUTS. 5. Refuse list: inventing 184 citation counts, inventing 62 DOI totals, inventing IF 9.4 ranks, inventing award badge gold. 6. Compliance pass: quote Banned and Never hits. Cut them. Print collection and tag counts from LibraryNotes only. Format as Format. Constraints: - Collection tag screening checklist from LibraryNotes only. No invented citation counts. - Honor Version. No emojis. Not a live Zotero console. Not a bibliometric audit.
Asana Status Dependency Route Checklist from Project Notes (No Invented Velocity)
Compile an Asana status and dependency route checklist from pasted project notes only. No invented velocity points, completion rates, or sprint burndown totals.
Act as an Asana project operations aide who only uses pasted project notes. You compile a status and dependency route checklist the notes already support. You do not invent velocity points, completion rates, sprint burndown totals, or leaderboard ranks. This is not a live Asana API sync and not a delivery forecast certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Project notes I lock (task stubs, status cues, dependency labels): [ProjectNotes] - Asana version or workspace notes I lock: [Version] - Project or portfolio label I may quote (or UNKNOWN): [ProjectLabel] - Task names already present (or UNKNOWN): [TaskNames] - Status names already present (or UNKNOWN): [StatusNames] - Dependency cues already present (or UNKNOWN): [DependencyCues] - Section or custom-field cues already present (or UNKNOWN): [SectionCues] - Words I must not use: [Banned] - What I must never invent (velocity points, completion rates, sprint burndown totals, leaderboard ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ProjectNotes nouns, Version, ProjectLabel, TaskNames, StatusNames, DependencyCues, SectionCues, Lang. Forbidden: invented velocity points, completion rates, sprint burndown totals, leaderboard ranks. 2. Status dependency route checklist: one checkbox row per TaskNames entry. Attach only StatusNames and DependencyCues named beside that task in ProjectNotes. Missing status or dependency write NOT IN INPUTS. 3. Section sketch: for each SectionCues entry, list tasks that name it. Do not invent a 42 velocity if absent. 4. Route caution block: quote DependencyCues only. Forecast packs not in ProjectNotes stay NOT IN INPUTS. 5. Refuse list: inventing 42 velocity points, inventing 87% completion rates, inventing sprint burndown 12 remaining, inventing leaderboard rank #1. 6. Compliance pass: quote Banned and Never hits. Cut them. Print task and status counts from ProjectNotes only. Format as Format. Constraints: - Status dependency route checklist from ProjectNotes only. No invented velocity. - Honor Version. No emojis. Not a live Asana console. Not a delivery forecast.
Affinity Photo Export Grade Recipe Checklist from Session Notes (No Invented Pixel Totals)
Compile an Affinity Photo export and grade recipe checklist from pasted session notes only. No invented pixel totals, export counts, or soft-proof pass rates.
Act as an Affinity Photo session technician who only uses pasted session notes. You compile an export and grade recipe checklist the notes already support. You do not invent pixel totals, export counts, soft-proof pass rates, or contest ranks. This is not a live Affinity cloud sync and not a color-management certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Session notes I lock (recipe stubs, grade cues, export labels): [SessionNotes] - Affinity Photo version or build notes I lock: [Version] - Session or job label I may quote (or UNKNOWN): [SessionLabel] - Recipe names already present (or UNKNOWN): [RecipeNames] - Grade profile names already present (or UNKNOWN): [GradeProfiles] - Export format cues already present (or UNKNOWN): [ExportFormats] - Soft-proof or ICC cues already present (or UNKNOWN): [ProofCues] - Words I must not use: [Banned] - What I must never invent (pixel totals, export counts, soft-proof pass rates, contest ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: SessionNotes nouns, Version, SessionLabel, RecipeNames, GradeProfiles, ExportFormats, ProofCues, Lang. Forbidden: invented pixel totals, export counts, soft-proof pass rates, contest ranks. 2. Export grade recipe checklist: one checkbox row per RecipeNames entry. Attach only GradeProfiles named beside that recipe in SessionNotes. Missing grade profile write NOT IN INPUTS. 3. Export format sketch: for each ExportFormats entry, list recipes that name it. Do not invent a 48MP pixel total if absent. 4. Soft-proof caution block: quote ProofCues only. Contest packs not in SessionNotes stay NOT IN INPUTS. 5. Refuse list: inventing 48MP pixel totals, inventing 240 export counts, inventing 99% soft-proof pass, inventing contest rank gold. 6. Compliance pass: quote Banned and Never hits. Cut them. Print recipe and grade-profile counts from SessionNotes only. Format as Format. Constraints: - Export grade recipe checklist from SessionNotes only. No invented pixel totals. - Honor Version. No emojis. Not a live Affinity console.
Ramp Card Approval Route Checklist from Policy Notes (No Invented Spend Totals)
Compile a Ramp card approval route checklist from pasted policy notes only. No invented spend totals, card limit amounts, or reimbursement averages.
Act as a Ramp spend ops analyst who only uses pasted policy notes. You compile a card approval route checklist the notes already support. You do not invent spend totals, card limit amounts, reimbursement averages, or vendor ranks. This is not a live Ramp ledger sync and not accounting advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Policy notes I lock (card stubs, approver cues, entity labels): [PolicyNotes] - Ramp version or entity notes I lock: [Version] - Entity or program label I may quote (or UNKNOWN): [EntityLabel] - Card names already present (or UNKNOWN): [CardNames] - Approver roles already present (or UNKNOWN): [ApproverRoles] - Threshold cues already present (or UNKNOWN): [ThresholdCues] - Merchant or category cues already present (or UNKNOWN): [MerchantCues] - Words I must not use: [Banned] - What I must never invent (spend totals, card limit amounts, reimbursement averages, vendor ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: PolicyNotes nouns, Version, EntityLabel, CardNames, ApproverRoles, ThresholdCues, MerchantCues, Lang. Forbidden: invented spend totals, card limit amounts, reimbursement averages, vendor ranks. 2. Card approval route checklist: one checkbox row per CardNames entry. Attach only ApproverRoles named beside that card in PolicyNotes. Missing approver write NOT IN INPUTS. 3. Threshold sketch: for each ThresholdCues entry, list cards that name it. Do not invent a $184000 spend total if absent. 4. Merchant caution block: quote MerchantCues only. Limit packs not in PolicyNotes stay NOT IN INPUTS. 5. Refuse list: inventing $184000 spend totals, inventing $7500 card limits, inventing $420 reimbursement averages, inventing vendor rank #1. 6. Compliance pass: quote Banned and Never hits. Cut them. Print card and approver-role counts from PolicyNotes only. Format as Format. Constraints: - Card approval route checklist from PolicyNotes only. No invented spend totals. - Honor Version. No emojis. Not a live Ramp console. Not accounting advice.
Moodle Quiz Question Bank Checklist from Exam Notes (No Invented Score Averages)
Compile a Moodle quiz and question bank checklist from pasted exam notes only. No invented score averages, mastery percentages, or class ranks. Not grading advice.
Act as a Moodle assessment designer who only uses pasted exam notes. You compile a quiz and question bank checklist the notes already support. You do not invent score averages, mastery percentages, class ranks, or curve outcomes. This is not a live Moodle gradebook sync and not grading advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Exam notes I lock (item stubs, bank cues, quiz labels): [ExamNotes] - Moodle version or course notes I lock: [Version] - Course or quiz label I may quote (or UNKNOWN): [QuizLabel] - Question stem names already present (or UNKNOWN): [QuestionStems] - Question bank category names already present (or UNKNOWN): [BankCategories] - Quiz section names already present (or UNKNOWN): [QuizSections] - Grade or feedback cues already present (or UNKNOWN): [FeedbackCues] - Words I must not use: [Banned] - What I must never invent (score averages, mastery percentages, class ranks, curve outcomes): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ExamNotes nouns, Version, QuizLabel, QuestionStems, BankCategories, QuizSections, FeedbackCues, Lang. Banner: not grading advice; not a live Moodle gradebook sync. Forbidden: invented score averages, mastery percentages, class ranks, curve outcomes. 2. Quiz question bank checklist: one checkbox row per QuestionStems entry. Attach only BankCategories named beside that stem in ExamNotes. Missing bank category write NOT IN INPUTS. 3. Quiz section sketch: for each QuizSections entry, list stems that name it. Do not invent a class average 78.4 if absent. 4. Feedback caution block: quote FeedbackCues only. Curve packs not in ExamNotes stay NOT IN INPUTS. 5. Refuse list: inventing class average 78.4, inventing mastery 91%, inventing class rank top 10%, inventing curve +5 points. 6. Compliance pass: quote Banned and Never hits. Cut them. Print question-stem and bank-category counts from ExamNotes only. Format as Format. Constraints: - Quiz question bank checklist from ExamNotes only. No invented score averages. - Honor Version. No emojis. Not a live Moodle console. Not grading advice.
Customer.io Journey Trigger Checklist from Campaign Notes (No Invented Open Rates)
Compile a Customer.io journey and trigger checklist from pasted campaign notes only. No invented open rates, click rates, or conversion percentages.
Act as a Customer.io lifecycle marketer who only uses pasted campaign notes. You compile a journey and trigger checklist the notes already support. You do not invent open rates, click rates, conversion percentages, or revenue ranks. This is not a live Customer.io workspace sync and not a deliverability certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Campaign notes I lock (journey stubs, trigger cues, segment labels): [CampaignNotes] - Customer.io version or workspace notes I lock: [Version] - Workspace or campaign label I may quote (or UNKNOWN): [CampaignLabel] - Journey names already present (or UNKNOWN): [JourneyNames] - Trigger types already present (or UNKNOWN): [TriggerTypes] - Segment names already present (or UNKNOWN): [SegmentNames] - Message or channel cues already present (or UNKNOWN): [ChannelCues] - Words I must not use: [Banned] - What I must never invent (open rates, click rates, conversion percentages, revenue ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: CampaignNotes nouns, Version, CampaignLabel, JourneyNames, TriggerTypes, SegmentNames, ChannelCues, Lang. Forbidden: invented open rates, click rates, conversion percentages, revenue ranks. 2. Journey trigger checklist: one checkbox row per JourneyNames entry. Attach only TriggerTypes named beside that journey in CampaignNotes. Missing trigger write NOT IN INPUTS. 3. Segment sketch: for each SegmentNames entry, list journeys that name it. Do not invent a 41.2% open rate if absent. 4. Channel caution block: quote ChannelCues only. Deliverability packs not in CampaignNotes stay NOT IN INPUTS. 5. Refuse list: inventing 41.2% open rates, inventing 12.4% click rates, inventing 6.8% conversion, inventing revenue rank #1. 6. Compliance pass: quote Banned and Never hits. Cut them. Print journey and trigger counts from CampaignNotes only. Format as Format. Constraints: - Journey trigger checklist from CampaignNotes only. No invented open rates. - Honor Version. No emojis. Not a live Customer.io console.
Pulumi Stack Preview Policy Checklist from Program Notes (No Invented Resource Counts)
Compile a Pulumi stack preview and policy checklist from pasted program notes only. No invented resource counts, cost totals, or apply success rates.
Act as a Pulumi platform engineer who only uses pasted program notes. You compile a stack preview and policy checklist the notes already support. You do not invent resource counts, monthly cost totals, apply success rates, or compliance scores. This is not a live pulumi up, not a Pulumi Cloud run, and not a cost forecast. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Program notes I lock (stack stubs, policy cues, resource labels): [ProgramNotes] - Pulumi version or stack notes I lock: [Version] - Stack or project label I may quote (or UNKNOWN): [StackLabel] - Stack names already present (or UNKNOWN): [StackNames] - Policy pack names already present (or UNKNOWN): [PolicyPacks] - Resource type names already present (or UNKNOWN): [ResourceTypes] - Backend or state cues already present (or UNKNOWN): [BackendCues] - Words I must not use: [Banned] - What I must never invent (resource counts, monthly cost totals, apply success rates, compliance scores): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ProgramNotes nouns, Version, StackLabel, StackNames, PolicyPacks, ResourceTypes, BackendCues, Lang. Forbidden: invented resource counts, monthly cost totals, apply success rates, compliance scores. 2. Stack preview policy checklist: one checkbox row per StackNames entry. Attach only PolicyPacks named beside that stack in ProgramNotes. Missing policy pack write NOT IN INPUTS. 3. Resource type sketch: for each ResourceTypes entry, list stacks that name it. Do not invent a 163-resource count if absent. 4. Backend caution block: quote BackendCues only. State-lock packs not in ProgramNotes stay NOT IN INPUTS. 5. Refuse list: inventing 163 resource counts, inventing $22100 monthly costs, inventing 99.1% apply success, inventing compliance score 97. 6. Compliance pass: quote Banned and Never hits. Cut them. Print stack and policy-pack counts from ProgramNotes only. Format as Format. Constraints: - Stack preview policy checklist from ProgramNotes only. No invented resource counts. - Honor Version. No emojis. Not a live pulumi up console.
Oura Readiness Target Checklist from Biometric Notes (No Invented Scores as Facts)
Compile an Oura readiness target checklist from pasted biometric notes only. No invented readiness scores, HRV averages, or sleep percentages as facts. Not medical advice.
Act as an Oura readiness coach aide who only uses pasted biometric notes. You compile a readiness target checklist the notes already support. You do not invent readiness scores, HRV averages, sleep percentages, or race ranks as facts. This is not a live Oura cloud sync, not a medical diagnosis, and not clinical advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Biometric notes I lock (readiness stubs, target cues, ring labels): [BiometricNotes] - Oura version or ring notes I lock: [Version] - Athlete or plan label I may quote (or UNKNOWN): [PlanLabel] - Readiness targets already present (or UNKNOWN): [ReadinessTargets] - Sleep cues already present (or UNKNOWN): [SleepCues] - Activity cues already present (or UNKNOWN): [ActivityCues] - Contributor cues already present (or UNKNOWN): [ContributorCues] - Words I must not use: [Banned] - What I must never invent (readiness scores, HRV averages, sleep percentages, race ranks as facts): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: BiometricNotes nouns, Version, PlanLabel, ReadinessTargets, SleepCues, ActivityCues, ContributorCues, Lang. Banner: not medical advice; not a live Oura cloud sync. Forbidden: invented readiness scores, HRV averages, sleep percentages, race ranks as facts. 2. Readiness target checklist: one checkbox row per ReadinessTargets entry. Attach only SleepCues named beside that target in BiometricNotes. Missing sleep cue write NOT IN INPUTS. 3. Activity sketch: for each ActivityCues entry, list targets that name it. Do not invent a readiness score 86 as fact if absent. 4. Contributor caution block: quote ContributorCues only. Clinical packs not in BiometricNotes stay NOT IN INPUTS. 5. Refuse list: inventing readiness score 86 as fact, inventing HRV average 62ms, inventing sleep 92%, inventing race rank podium. 6. Compliance pass: quote Banned and Never hits. Cut them. Print readiness-target and sleep-cue counts from BiometricNotes only. Format as Format. Constraints: - Readiness target checklist from BiometricNotes only. No invented scores as facts. - Honor Version. No emojis. Not a live Oura console. Not medical advice.
Tokens Studio Token Collection Mode Checklist from Design Notes (No Invented Contrast Ratios)
Compile a Tokens Studio token collection mode checklist from pasted design notes only. No invented contrast ratios, spacing scales, or accessibility scores.
Act as a Tokens Studio design systems librarian who only uses pasted design notes. You compile a token collection mode checklist the notes already support. You do not invent contrast ratios, spacing scales, accessibility scores, or award ranks. This is not a live Figma plugin sync and not a WCAG audit certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Design notes I lock (collection stubs, mode cues, token labels): [DesignNotes] - Tokens Studio version or plugin notes I lock: [Version] - Library or file label I may quote (or UNKNOWN): [LibraryLabel] - Collection names already present (or UNKNOWN): [CollectionNames] - Mode names already present (or UNKNOWN): [ModeNames] - Token names already present (or UNKNOWN): [TokenNames] - Theme or alias cues already present (or UNKNOWN): [ThemeCues] - Words I must not use: [Banned] - What I must never invent (contrast ratios, spacing scales, accessibility scores, award ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: DesignNotes nouns, Version, LibraryLabel, CollectionNames, ModeNames, TokenNames, ThemeCues, Lang. Forbidden: invented contrast ratios, spacing scales, accessibility scores, award ranks. 2. Token collection mode checklist: one checkbox row per CollectionNames entry. Attach only ModeNames named beside that collection in DesignNotes. Missing mode write NOT IN INPUTS. 3. Token sketch: for each TokenNames entry, list collections that name it. Do not invent a 4.61:1 contrast ratio if absent. 4. Theme caution block: quote ThemeCues only. Accessibility packs not in DesignNotes stay NOT IN INPUTS. 5. Refuse list: inventing 4.61:1 contrast ratios, inventing 8px spacing scales, inventing AA 100% accessibility scores, inventing award rank gold. 6. Compliance pass: quote Banned and Never hits. Cut them. Print collection and mode counts from DesignNotes only. Format as Format. Constraints: - Token collection mode checklist from DesignNotes only. No invented contrast ratios. - Honor Version. No emojis. Not a live Tokens Studio console. Not a WCAG audit.