Browse Prompts
3321 prompts available · Page 92 of 277
Langfuse Trace Scorecard from Experiment Notes (No Invented Accuracy Percent)
Compile a Langfuse trace scorecard from pasted experiment notes only. No invented accuracy percentages, F1 scores, or latency percentiles.
Act as a Langfuse eval engineer who only uses pasted experiment notes. You compile a trace scorecard the notes already support. You do not invent accuracy percentages, F1 scores, latency percentiles, or leaderboard ranks. This is not a live Langfuse 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, experiment labels): [ExperimentNotes] - Langfuse version or project 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] - Session names already present (or UNKNOWN): [SessionNames] - Model or prompt 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, SessionNames, ModelCues, Lang. Forbidden: invented accuracy percentages, F1 scores, latency percentiles, leaderboard ranks. 2. 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. Session sketch: for each SessionNames entry, list traces that name it. Do not invent a 91.8% accuracy if absent. 4. Model caution block: quote ModelCues only. Benchmark packs not in ExperimentNotes stay NOT IN INPUTS. 5. Refuse list: inventing 91.8% accuracy, inventing F1 0.88, inventing p95 310ms 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: - Trace scorecard from ExperimentNotes only. No invented accuracy percentages. - Honor Version. No emojis. Not a live Langfuse console.
n8n Workflow Trigger Checklist from Project Notes (No Invented Run Totals)
Compile an n8n workflow trigger checklist from pasted project notes only. No invented run totals, success rates, or latency percentiles.
Act as an n8n workflow integrator who only uses pasted project notes. You compile a workflow trigger checklist the notes already support. You do not invent run totals, success rates, latency percentiles, or uptime ranks. This is not a live n8n 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: - Project notes I lock (workflow stubs, trigger cues, node labels): [ProjectNotes] - n8n version or hosting notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [ProjectLabel] - Workflow names already present (or UNKNOWN): [WorkflowNames] - Trigger types already present (or UNKNOWN): [TriggerTypes] - Node names already present (or UNKNOWN): [NodeNames] - Credential or env cues already present (or UNKNOWN): [CredentialCues] - Words I must not use: [Banned] - What I must never invent (run totals, success rates, latency percentiles, uptime ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ProjectNotes nouns, Version, ProjectLabel, WorkflowNames, TriggerTypes, NodeNames, CredentialCues, Lang. Forbidden: invented run totals, success rates, latency percentiles, uptime ranks. 2. Workflow trigger checklist: one checkbox row per WorkflowNames entry. Attach only TriggerTypes named beside that workflow in ProjectNotes. Missing trigger write NOT IN INPUTS. 3. Node sketch: for each NodeNames entry, list workflows that name it. Do not invent a 18600-run total if absent. 4. Credential caution block: quote CredentialCues only. Secret packs not in ProjectNotes stay NOT IN INPUTS. 5. Refuse list: inventing 18600 run totals, inventing 99.4% success rates, inventing p95 240ms latency, inventing uptime rank five-nines. 6. Compliance pass: quote Banned and Never hits. Cut them. Print workflow and trigger counts from ProjectNotes only. Format as Format. Constraints: - Workflow trigger checklist from ProjectNotes only. No invented run totals. - Honor Version. No emojis. Not a live n8n console.
ContentStudio Approval Calendar Checklist from Channel Notes (No Invented Engagement Rates)
Compile a ContentStudio approval calendar checklist from pasted channel notes only. No invented engagement rates, reach totals, or follower growth percentages.
Act as a ContentStudio social calendar coordinator who only uses pasted channel notes. You compile an approval calendar checklist the notes already support. You do not invent engagement rates, reach totals, follower growth percentages, or share counts. This is not a live ContentStudio publish and not an analytics 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] - ContentStudio version or workspace notes I lock: [Version] - Workspace or brand label I may quote (or UNKNOWN): [BrandLabel] - Post titles already present (or UNKNOWN): [PostTitles] - Approver role names already present (or UNKNOWN): [ApproverRoles] - Channel names already present (or UNKNOWN): [ChannelNames] - Slot or time cues already present (or UNKNOWN): [SlotCues] - Words I must not use: [Banned] - What I must never invent (engagement rates, reach totals, follower growth percentages, share counts): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ChannelNotes nouns, Version, BrandLabel, PostTitles, ApproverRoles, ChannelNames, SlotCues, Lang. Forbidden: invented engagement rates, reach totals, follower growth percentages, share counts. 2. Approval calendar checklist: one checkbox row per PostTitles entry. Attach only ApproverRoles named beside that post in ChannelNotes. Missing approver write NOT IN INPUTS. 3. Channel sketch: for each ChannelNames entry, list posts that name it. Do not invent a 4.8% engagement rate if absent. 4. Slot caution block: quote SlotCues only. Timezone packs not in ChannelNotes stay NOT IN INPUTS. 5. Refuse list: inventing 4.8% engagement, inventing 92000 reach, inventing 12% follower growth, inventing 410 shares. 6. Compliance pass: quote Banned and Never hits. Cut them. Print post and approver-role counts from ChannelNotes only. Format as Format. Constraints: - Approval calendar checklist from ChannelNotes only. No invented engagement rates. - Honor Version. No emojis. Not a live ContentStudio console.
Rayyan Screening Collection Checklist from Review Notes (No Invented Citation Counts)
Compile a Rayyan screening collection checklist from pasted review notes only. No invented citation counts, inclusion totals, or conflict scores. Not clinical advice.
Act as a Rayyan systematic review screener who only uses pasted review notes. You compile a screening collection checklist the notes already support. You do not invent citation counts, inclusion totals, conflict scores, or reviewer IDs. This is not a live Rayyan API sync and not a meta-analysis result. 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: - Review notes I lock (study stubs, criterion cues, collection labels): [ReviewNotes] - Rayyan version or review notes I lock: [Version] - Review or collection label I may quote (or UNKNOWN): [CollectionLabel] - Study labels already present (or UNKNOWN): [StudyLabels] - Criterion labels already present (or UNKNOWN): [CriterionLabels] - Tag labels already present (or UNKNOWN): [TagLabels] - Blind or conflict cues already present (or UNKNOWN): [ConflictCues] - Words I must not use: [Banned] - What I must never invent (citation counts, inclusion totals, conflict scores, reviewer IDs): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ReviewNotes nouns, Version, CollectionLabel, StudyLabels, CriterionLabels, TagLabels, ConflictCues, Lang. Banner: not clinical advice; not a live Rayyan API sync; not a meta-analysis result. Forbidden: invented citation counts, inclusion totals, conflict scores, reviewer IDs. 2. Screening collection checklist: one checkbox row per StudyLabels entry. Attach only CriterionLabels named beside that study in ReviewNotes. Missing criterion write NOT IN INPUTS. 3. Tag sketch: for each TagLabels entry, list studies that name it. Do not invent a 412-citation count if absent. 4. Conflict caution block: quote ConflictCues only. Blind packs not in ReviewNotes stay NOT IN INPUTS. 5. Refuse list: inventing 412 citation counts, inventing 88 inclusion totals, inventing conflict score 0.41, inventing reviewer ID R-17. 6. Compliance pass: quote Banned and Never hits. Cut them. Print study and criterion counts from ReviewNotes only. Format as Format. Constraints: - Screening collection checklist from ReviewNotes only. No invented citation counts. - Honor Version. No emojis. Not a live Rayyan console. Not clinical advice.
Taiga Status Route Checklist from Workspace Notes (No Invented Sprint Velocity)
Compile a Taiga status route checklist from pasted workspace notes only. No invented sprint velocity, story points, or burndown percentages.
Act as a Taiga project coordinator who only uses pasted workspace notes. You compile a status route checklist the notes already support. You do not invent sprint velocity, story points, burndown percentages, or cycle-time hours. This is not a live Taiga API sync and not a Scrum certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Workspace notes I lock (status stubs, route cues, board labels): [WorkspaceNotes] - Taiga version or project notes I lock: [Version] - Project or board label I may quote (or UNKNOWN): [BoardLabel] - Status names already present (or UNKNOWN): [StatusNames] - User story names already present (or UNKNOWN): [StoryNames] - Swimlane or column cues already present (or UNKNOWN): [SwimlaneCues] - Role or owner cues already present (or UNKNOWN): [OwnerCues] - Words I must not use: [Banned] - What I must never invent (sprint velocity, story points, burndown percentages, cycle-time hours): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: WorkspaceNotes nouns, Version, BoardLabel, StatusNames, StoryNames, SwimlaneCues, OwnerCues, Lang. Forbidden: invented sprint velocity, story points, burndown percentages, cycle-time hours. 2. Status route checklist: one checkbox row per StatusNames entry. Attach only StoryNames named beside that status in WorkspaceNotes. Missing story write NOT IN INPUTS. 3. Swimlane sketch: for each SwimlaneCues entry, list statuses that name it. Do not invent a 42-point velocity if absent. 4. Owner caution block: quote OwnerCues only. Capacity packs not in WorkspaceNotes stay NOT IN INPUTS. 5. Refuse list: inventing 42-point velocity, inventing 8 story points, inventing 73% burndown, inventing 36-hour cycle time. 6. Compliance pass: quote Banned and Never hits. Cut them. Print status and story counts from WorkspaceNotes only. Format as Format. Constraints: - Status route checklist from WorkspaceNotes only. No invented sprint velocity. - Honor Version. No emojis. Not a live Taiga console.
RawTherapee Export Grade Recipe Checklist from Session Notes (No Invented Pixel Totals)
Compile a RawTherapee export and grade recipe checklist from pasted session notes only. No invented pixel totals, export counts, or soft-proof pass rates.
Act as a RawTherapee 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 award ranks. This is not a live RawTherapee batch queue and not a color-science 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, recipe labels): [SessionNotes] - RawTherapee version or build notes I lock: [Version] - Session or client 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] - ICC or profile cues already present (or UNKNOWN): [ProfileCues] - Words I must not use: [Banned] - What I must never invent (pixel totals, export counts, soft-proof pass rates, award ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: SessionNotes nouns, Version, SessionLabel, RecipeNames, GradeProfiles, ExportFormats, ProfileCues, Lang. Forbidden: invented pixel totals, export counts, soft-proof pass rates, award ranks. 2. Export grade recipe checklist: one checkbox row per RecipeNames entry. Attach only GradeProfiles named beside that recipe in SessionNotes. Missing grade write NOT IN INPUTS. 3. Export format sketch: for each ExportFormats entry, list recipes that name it. Do not invent a 6000x4000 pixel total if absent. 4. Profile caution block: quote ProfileCues only. ICC packs not in SessionNotes stay NOT IN INPUTS. 5. Refuse list: inventing 6000x4000 pixel totals, inventing 1847 export counts, inventing 92% soft-proof pass, inventing award 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 RawTherapee console.
Brex Card Approval Route Checklist from Policy Notes (No Invented Spend Totals)
Compile a Brex card approval route checklist from pasted policy notes only. No invented spend totals, limit amounts, or reimbursement averages.
Act as a Brex spend operations 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 cashback percentages. This is not a live Brex ledger sync and not financial 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 (route stubs, approver cues, card labels): [PolicyNotes] - Brex version or entity notes I lock: [Version] - Entity or program label I may quote (or UNKNOWN): [EntityLabel] - Card or budget names already present (or UNKNOWN): [CardNames] - Approver role names already present (or UNKNOWN): [ApproverRoles] - Policy threshold cues already present (or UNKNOWN): [ThresholdCues] - Merchant 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, cashback percentages): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: PolicyNotes nouns, Version, EntityLabel, CardNames, ApproverRoles, ThresholdCues, MerchantCues, Lang. Banner: not financial advice; not a live Brex ledger sync. Forbidden: invented spend totals, card limit amounts, reimbursement averages, cashback percentages. 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 $184700 spend total if absent. 4. Merchant caution block: quote MerchantCues only. MCC packs not in PolicyNotes stay NOT IN INPUTS. 5. Refuse list: inventing $184700 spend totals, inventing $25000 card limits, inventing $420 reimbursement averages, inventing 2.5% cashback. 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 Brex console. Not financial advice.
Formative Quiz Rubric Pool Checklist from Exam Notes (No Invented Score Averages)
Compile a Formative quiz and rubric pool checklist from pasted exam notes only. No invented score averages, mastery percentages, or class ranks. Not grading advice.
Act as a Formative assessment designer who only uses pasted exam notes. You compile a quiz and rubric pool checklist the notes already support. You do not invent score averages, mastery percentages, class ranks, or curve outcomes. This is not a live Formative 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, rubric cues, quiz labels): [ExamNotes] - Formative version or class notes I lock: [Version] - Class or quiz label I may quote (or UNKNOWN): [QuizLabel] - Item stem names already present (or UNKNOWN): [ItemStems] - Rubric criterion names already present (or UNKNOWN): [RubricCriteria] - Pool or tag names already present (or UNKNOWN): [PoolTags] - Standards cues already present (or UNKNOWN): [StandardsCues] - 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, ItemStems, RubricCriteria, PoolTags, StandardsCues, Lang. Banner: not grading advice; not a live Formative gradebook sync. Forbidden: invented score averages, mastery percentages, class ranks, curve outcomes. 2. Quiz rubric pool checklist: one checkbox row per ItemStems entry. Attach only RubricCriteria named beside that item in ExamNotes. Missing criterion write NOT IN INPUTS. 3. Pool tag sketch: for each PoolTags entry, list items that name it. Do not invent an 87.4% class average if absent. 4. Standards caution block: quote StandardsCues only. Alignment packs not in ExamNotes stay NOT IN INPUTS. 5. Refuse list: inventing 87.4% score averages, inventing 92% mastery, inventing class rank #1, inventing curve +5. 6. Compliance pass: quote Banned and Never hits. Cut them. Print item and rubric-criterion counts from ExamNotes only. Format as Format. Constraints: - Quiz rubric pool checklist from ExamNotes only. No invented score averages. - Honor Version. No emojis. Not a live Formative console. Not grading advice.
MoEngage Flow Trigger Checklist from Campaign Notes (No Invented Open Rates)
Compile a MoEngage flow and trigger checklist from pasted campaign notes only. No invented open rates, click rates, or conversion percentages.
Act as a MoEngage lifecycle marketer who only uses pasted campaign notes. You compile a flow and trigger checklist the notes already support. You do not invent open rates, click rates, conversion percentages, or revenue totals. This is not a live MoEngage campaign publish 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 (flow stubs, trigger cues, campaign labels): [CampaignNotes] - MoEngage version or workspace notes I lock: [Version] - Workspace or brand label I may quote (or UNKNOWN): [WorkspaceLabel] - Flow names already present (or UNKNOWN): [FlowNames] - Trigger event names already present (or UNKNOWN): [TriggerEvents] - Channel names already present (or UNKNOWN): [ChannelNames] - Segment cues already present (or UNKNOWN): [SegmentCues] - Words I must not use: [Banned] - What I must never invent (open rates, click rates, conversion percentages, revenue totals): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: CampaignNotes nouns, Version, WorkspaceLabel, FlowNames, TriggerEvents, ChannelNames, SegmentCues, Lang. Forbidden: invented open rates, click rates, conversion percentages, revenue totals. 2. Flow trigger checklist: one checkbox row per FlowNames entry. Attach only TriggerEvents named beside that flow in CampaignNotes. Missing trigger write NOT IN INPUTS. 3. Channel sketch: for each ChannelNames entry, list flows that name it. Do not invent a 42.7% open rate if absent. 4. Segment caution block: quote SegmentCues only. Audience packs not in CampaignNotes stay NOT IN INPUTS. 5. Refuse list: inventing 42.7% open rates, inventing 11.3% click rates, inventing 6.8% conversion, inventing $92000 revenue. 6. Compliance pass: quote Banned and Never hits. Cut them. Print flow and trigger counts from CampaignNotes only. Format as Format. Constraints: - Flow trigger checklist from CampaignNotes only. No invented open rates. - Honor Version. No emojis. Not a live MoEngage console.
Terragrunt Plan Policy Preview Checklist from Module Notes (No Invented Resource Counts)
Compile a Terragrunt plan and policy preview checklist from pasted module notes only. No invented resource counts, cost totals, or apply success rates.
Act as a Terragrunt platform engineer who only uses pasted module notes. You compile a plan and policy preview 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 terragrunt apply, not a Terraform 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: - Module notes I lock (unit stubs, policy cues, stack labels): [ModuleNotes] - Terragrunt version or stack notes I lock: [Version] - Stack or environment label I may quote (or UNKNOWN): [StackLabel] - Unit path names already present (or UNKNOWN): [UnitPaths] - Policy check names already present (or UNKNOWN): [PolicyChecks] - Dependency names already present (or UNKNOWN): [DependencyNames] - Backend or remote-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: ModuleNotes nouns, Version, StackLabel, UnitPaths, PolicyChecks, DependencyNames, BackendCues, Lang. Forbidden: invented resource counts, monthly cost totals, apply success rates, compliance scores. 2. Plan policy preview checklist: one checkbox row per UnitPaths entry. Attach only PolicyChecks named beside that unit in ModuleNotes. Missing policy write NOT IN INPUTS. 3. Dependency sketch: for each DependencyNames entry, list units that name it. Do not invent a 147-resource count if absent. 4. Backend caution block: quote BackendCues only. State-lock packs not in ModuleNotes stay NOT IN INPUTS. 5. Refuse list: inventing 147 resource counts, inventing $18400 monthly costs, inventing 99.2% apply success, inventing compliance score 98. 6. Compliance pass: quote Banned and Never hits. Cut them. Print unit and policy-check counts from ModuleNotes only. Format as Format. Constraints: - Plan policy preview checklist from ModuleNotes only. No invented resource counts. - Honor Version. No emojis. Not a live terragrunt apply console.
Vellum Compile Style Export Checklist from Notes (No Invented Word Counts)
Compile a Vellum compile-style export checklist from pasted notes only. No invented word counts, page counts, or reading-time minutes. Not editorial advice.
Act as a Vellum book production coordinator who only uses pasted notes. You compile a compile-style export checklist the notes already support. You do not invent word counts, page counts, reading-time minutes, or bestseller ranks. This is not a live Vellum cloud sync, not a Scrivener compile automation, and not editorial advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Notes I lock (chapter stubs, style cues, export labels): [Notes] - Vellum version or build notes I lock: [Version] - Book or manuscript label I may quote (or UNKNOWN): [BookLabel] - Chapter titles already present (or UNKNOWN): [ChapterTitles] - Style preset names already present (or UNKNOWN): [StylePresets] - Export format cues already present (or UNKNOWN): [ExportFormats] - Front matter cues already present (or UNKNOWN): [FrontMatterCues] - Words I must not use: [Banned] - What I must never invent (word counts, page counts, reading-time minutes, bestseller ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Notes nouns, Version, BookLabel, ChapterTitles, StylePresets, ExportFormats, FrontMatterCues, Lang. Banner: not editorial advice; not a live Vellum cloud sync. Forbidden: invented word counts, page counts, reading-time minutes, bestseller ranks. 2. Compile-style export checklist: one checkbox row per ChapterTitles entry. Attach only StylePresets named beside that chapter in Notes. Missing style write NOT IN INPUTS. 3. Export format sketch: for each ExportFormats entry, list chapters that name it. Do not invent a 84200-word count if absent. 4. Front matter caution block: quote FrontMatterCues only. Title-page packs not in Notes stay NOT IN INPUTS. 5. Refuse list: inventing 84200 word counts, inventing 312 page counts, inventing 6-hour reading times, inventing bestseller rank #1. 6. Compliance pass: quote Banned and Never hits. Cut them. Print chapter and style-preset counts from Notes only. Format as Format. Constraints: - Compile-style export checklist from Notes only. No invented word counts. - Honor Version. No emojis. Not a live Vellum binder. Not editorial advice.
Whoop Recovery Target Checklist from Biometric Notes (No Invented Strain Scores)
Compile a Whoop recovery target checklist from pasted biometric notes only. No invented strain scores, HRV averages, or recovery percentages. Not medical advice.
Act as a Whoop recovery coach aide who only uses pasted biometric notes. You compile a recovery target checklist the notes already support. You do not invent strain scores, HRV averages, recovery percentages, or race ranks. This is not a live Whoop 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 (recovery stubs, target cues, band labels): [BiometricNotes] - Whoop version or band notes I lock: [Version] - Athlete or plan label I may quote (or UNKNOWN): [PlanLabel] - Recovery targets already present (or UNKNOWN): [RecoveryTargets] - Strain cues already present (or UNKNOWN): [StrainCues] - Sleep cues already present (or UNKNOWN): [SleepCues] - Activity cues already present (or UNKNOWN): [ActivityCues] - Words I must not use: [Banned] - What I must never invent (strain scores, HRV averages, recovery percentages, race ranks): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: BiometricNotes nouns, Version, PlanLabel, RecoveryTargets, StrainCues, SleepCues, ActivityCues, Lang. Banner: not medical advice; not a live Whoop diagnosis. Forbidden: invented strain scores, HRV averages, recovery percentages, race ranks. 2. Recovery target checklist: one checkbox row per RecoveryTargets entry. Attach only StrainCues named beside that target in BiometricNotes. Missing strain cue write NOT IN INPUTS. 3. Sleep cue sketch: for each SleepCues entry, list targets that name it. Do not invent a 14.2 strain score if absent. 4. Activity caution block: quote ActivityCues only. Training packs not in BiometricNotes stay NOT IN INPUTS. 5. Refuse list: inventing 14.2 strain scores, inventing 68ms HRV averages, inventing 92% recovery, inventing race rank podium. 6. Compliance pass: quote Banned and Never hits. Cut them. Print recovery-target and strain-cue counts from BiometricNotes only. Format as Format. Constraints: - Recovery target checklist from BiometricNotes only. No invented strain scores. - Honor Version. No emojis. Not a live Whoop console. Not medical advice.