promptstudio
promptstudio's Prompts
Buck2 Project Target Dependency Checklist from Workspace Notes (No Invented Build Time Seconds)
Compile a Buck2 project-target-dependency checklist from pasted workspace notes only. No invented build-time seconds, cache ranks, or CI scoreboards. Not a live Buck2 sync.
Act as a Buck2 project-target-dependency checklist engineer who only uses pasted workspace notes. You compile a project-target-dependency checklist the notes already support. You do not invent build-time seconds, cache ranks, CI scoreboards, or flaky-test percents. This is not a live Buck2 sync, not a Bazel invent, and not DevOps consulting advice. 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 (project stubs, target cues, dependency fragments): [WorkspaceNotes] - Buck2 workspace or version notes I lock: [Version] - Repo or workspace label I may quote (or UNKNOWN): [RepoLabel] - Project titles already present (or UNKNOWN): [ProjectTitles] - Target cues already present (or UNKNOWN): [TargetCues] - Dependency cues already present (or UNKNOWN): [DependencyCues] - Action cues already present (or UNKNOWN): [ActionCues] - Words I must not use: [Banned] - What I must never invent (build-time seconds, cache ranks, CI scoreboards, flaky-test percents): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: WorkspaceNotes nouns, Version, RepoLabel, ProjectTitles, TargetCues, DependencyCues, ActionCues, Lang. Banner: not DevOps consulting advice; not a live Buck2 sync. Forbidden: invented build-time seconds, cache ranks, CI scoreboards, flaky-test percents. 2. Project-target-dependency checklist: one checkbox row per ProjectTitles entry. Attach only TargetCues and DependencyCues named beside that project in WorkspaceNotes. Missing target or dependency write NOT IN INPUTS. 3. Action sketch: for each ActionCues entry, list projects that name it. Do not invent a 47s build-time claim if absent. 4. Repo caution block: quote RepoLabel and Version only. Cell packs not in WorkspaceNotes stay NOT IN INPUTS. 5. Refuse list: inventing 47s build-time seconds, inventing cache ranks, inventing CI scoreboards, inventing flaky-test percents. 6. Compliance pass: quote Banned and Never hits. Cut them. Print project and target counts from WorkspaceNotes only. Format as Format. Constraints: - Project-target-dependency checklist from WorkspaceNotes only. No invented build-time seconds. - Honor Version. No emojis. Not a live Buck2 dashboard. Not DevOps consulting advice.
Strava Week-Plan Activity-Block Checklist from Activity Notes (No Invented Pace Calorie Totals)
Compile a Strava week-plan activity-block checklist from pasted activity notes only. No invented pace or calorie totals, PR ranks, or training scoreboards. Not a live Strava sync.
Act as a Strava week-plan activity-block checklist engineer who only uses pasted activity notes. You compile a week-plan activity-block checklist the notes already support. You do not invent pace totals, calorie totals, PR ranks, or training scoreboards. This is not a live Strava sync, not a Garmin invent, and not sports-medicine consulting advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Activity notes I lock (week-plan stubs, activity-block cues, sport fragments): [ActivityNotes] - Strava account or version notes I lock: [Version] - Club or athlete label I may quote (or UNKNOWN): [AthleteLabel] - Week-plan titles already present (or UNKNOWN): [WeekPlanTitles] - Activity-block cues already present (or UNKNOWN): [ActivityBlockCues] - Sport cues already present (or UNKNOWN): [SportCues] - Route cues already present (or UNKNOWN): [RouteCues] - Words I must not use: [Banned] - What I must never invent (pace totals, calorie totals, PR ranks, training scoreboards): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: ActivityNotes nouns, Version, AthleteLabel, WeekPlanTitles, ActivityBlockCues, SportCues, RouteCues, Lang. Banner: not sports-medicine consulting advice; not a live Strava sync. Forbidden: invented pace totals, calorie totals, PR ranks, training scoreboards. 2. Week-plan activity-block checklist: one checkbox row per WeekPlanTitles entry. Attach only ActivityBlockCues and SportCues named beside that week plan in ActivityNotes. Missing activity-block or sport write NOT IN INPUTS. 3. Route sketch: for each RouteCues entry, list week plans that name it. Do not invent a 7:42 pace or 640 calorie claim if absent. 4. Athlete caution block: quote AthleteLabel and Version only. Segment packs not in ActivityNotes stay NOT IN INPUTS. 5. Refuse list: inventing 7:42 pace totals, inventing 640 calorie totals, inventing PR ranks, inventing training scoreboards. 6. Compliance pass: quote Banned and Never hits. Cut them. Print week-plan and activity-block counts from ActivityNotes only. Format as Format. Constraints: - Week-plan activity-block checklist from ActivityNotes only. No invented pace or calorie totals. - Honor Version. No emojis. Not a live Strava dashboard. Not sports-medicine consulting advice.
Penpot Artboard Export Slice Checklist from Design Notes (No Invented Coverage Percents)
Compile a Penpot artboard-export-slice checklist from pasted design notes only. No invented coverage percents, token ranks, or design scoreboards. Not a live Penpot sync.
Act as a Penpot artboard-export-slice checklist engineer who only uses pasted design notes. You compile an artboard-export-slice checklist the notes already support. You do not invent coverage percents, token ranks, design scoreboards, or guaranteed pixel claims. This is not a live Penpot sync, not a Figma invent, and not design-system consulting advice. 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 (artboard stubs, export cues, slice fragments): [DesignNotes] - Penpot file or version notes I lock: [Version] - File or team label I may quote (or UNKNOWN): [FileLabel] - Artboard titles already present (or UNKNOWN): [ArtboardTitles] - Export cues already present (or UNKNOWN): [ExportCues] - Slice cues already present (or UNKNOWN): [SliceCues] - Component cues already present (or UNKNOWN): [ComponentCues] - Words I must not use: [Banned] - What I must never invent (coverage percents, token ranks, design scoreboards, guaranteed pixel claims): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: DesignNotes nouns, Version, FileLabel, ArtboardTitles, ExportCues, SliceCues, ComponentCues, Lang. Banner: not design-system consulting advice; not a live Penpot sync. Forbidden: invented coverage percents, token ranks, design scoreboards, guaranteed pixel claims. 2. Artboard-export-slice checklist: one checkbox row per ArtboardTitles entry. Attach only ExportCues and SliceCues named beside that artboard in DesignNotes. Missing export or slice write NOT IN INPUTS. 3. Component sketch: for each ComponentCues entry, list artboards that name it. Do not invent a 94% coverage claim if absent. 4. File caution block: quote FileLabel and Version only. Token packs not in DesignNotes stay NOT IN INPUTS. 5. Refuse list: inventing 94% coverage percents, inventing token ranks, inventing design scoreboards, inventing guaranteed pixel claims. 6. Compliance pass: quote Banned and Never hits. Cut them. Print artboard and export counts from DesignNotes only. Format as Format. Constraints: - Artboard-export-slice checklist from DesignNotes only. No invented coverage percents. - Honor Version. No emojis. Not a live Penpot dashboard. Not design-system consulting advice.
LangSmith Trace Dataset Eval Checklist from Ops Notes (No Invented Latency Scores)
Compile a LangSmith trace-dataset-eval checklist from pasted ops notes only. No invented latency scores, eval ranks, or model scoreboards. Not a live LangSmith sync.
Act as a LangSmith trace-dataset-eval checklist engineer who only uses pasted ops notes. You compile a trace-dataset-eval checklist the notes already support. You do not invent latency scores, eval ranks, model scoreboards, or guaranteed accuracy claims. This is not a live LangSmith sync, not an Arize invent, and not ML ops consulting advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Ops notes I lock (trace stubs, dataset cues, eval fragments): [OpsNotes] - LangSmith project or version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [ProjectLabel] - Trace titles already present (or UNKNOWN): [TraceTitles] - Dataset cues already present (or UNKNOWN): [DatasetCues] - Eval cues already present (or UNKNOWN): [EvalCues] - Run cues already present (or UNKNOWN): [RunCues] - Words I must not use: [Banned] - What I must never invent (latency scores, eval ranks, model scoreboards, guaranteed accuracy claims): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: OpsNotes nouns, Version, ProjectLabel, TraceTitles, DatasetCues, EvalCues, RunCues, Lang. Banner: not ML ops consulting advice; not a live LangSmith sync. Forbidden: invented latency scores, eval ranks, model scoreboards, guaranteed accuracy claims. 2. Trace-dataset-eval checklist: one checkbox row per TraceTitles entry. Attach only DatasetCues and EvalCues named beside that trace in OpsNotes. Missing dataset or eval write NOT IN INPUTS. 3. Run sketch: for each RunCues entry, list traces that name it. Do not invent a 182ms latency claim if absent. 4. Project caution block: quote ProjectLabel and Version only. Feedback packs not in OpsNotes stay NOT IN INPUTS. 5. Refuse list: inventing 182ms latency scores, inventing eval ranks, inventing model scoreboards, inventing guaranteed accuracy claims. 6. Compliance pass: quote Banned and Never hits. Cut them. Print trace and dataset counts from OpsNotes only. Format as Format. Constraints: - Trace-dataset-eval checklist from OpsNotes only. No invented latency scores. - Honor Version. No emojis. Not a live LangSmith dashboard. Not ML ops consulting advice.
Grafana Dashboard Panel Alert Checklist from Ops Notes (No Invented Uptime Percents)
Compile a Grafana dashboard-panel-alert checklist from pasted ops notes only. No invented uptime percents, latency ranks, or ops scoreboards. Not a live Grafana sync.
Act as a Grafana dashboard-panel-alert checklist engineer who only uses pasted ops notes. You compile a dashboard-panel-alert checklist the notes already support. You do not invent uptime percents, latency ranks, ops scoreboards, or guaranteed SLO claims. This is not a live Grafana sync, not a Datadog invent, and not SRE consulting advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Ops notes I lock (dashboard stubs, panel cues, alert fragments): [OpsNotes] - Grafana instance or version notes I lock: [Version] - Instance or org label I may quote (or UNKNOWN): [OrgLabel] - Dashboard titles already present (or UNKNOWN): [DashboardTitles] - Panel cues already present (or UNKNOWN): [PanelCues] - Alert cues already present (or UNKNOWN): [AlertCues] - Folder cues already present (or UNKNOWN): [FolderCues] - Words I must not use: [Banned] - What I must never invent (uptime percents, latency ranks, ops scoreboards, guaranteed SLO claims): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: OpsNotes nouns, Version, OrgLabel, DashboardTitles, PanelCues, AlertCues, FolderCues, Lang. Banner: not SRE consulting advice; not a live Grafana sync. Forbidden: invented uptime percents, latency ranks, ops scoreboards, guaranteed SLO claims. 2. Dashboard-panel-alert checklist: one checkbox row per DashboardTitles entry. Attach only PanelCues and AlertCues named beside that dashboard in OpsNotes. Missing panel or alert write NOT IN INPUTS. 3. Folder sketch: for each FolderCues entry, list dashboards that name it. Do not invent a 99.95% uptime claim if absent. 4. Org caution block: quote OrgLabel and Version only. Datasource packs not in OpsNotes stay NOT IN INPUTS. 5. Refuse list: inventing 99.95% uptime percents, inventing latency ranks, inventing ops scoreboards, inventing guaranteed SLO claims. 6. Compliance pass: quote Banned and Never hits. Cut them. Print dashboard and panel counts from OpsNotes only. Format as Format. Constraints: - Dashboard-panel-alert checklist from OpsNotes only. No invented uptime percents. - Honor Version. No emojis. Not a live Grafana dashboard. Not SRE consulting advice.
Buffer Queue Channel Label Checklist from Calendar Notes (No Invented Engagement Rates)
Compile a Buffer queue-channel-label checklist from pasted calendar notes only. No invented engagement rates, reach ranks, or social scoreboards. Not a live Buffer sync.
Act as a Buffer queue-channel-label checklist engineer who only uses pasted calendar notes. You compile a queue-channel-label checklist the notes already support. You do not invent engagement rates, reach ranks, social scoreboards, or guaranteed viral claims. This is not a live Buffer sync, not a Hootsuite invent, and not social media consulting advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Calendar notes I lock (queue stubs, channel cues, label fragments): [CalendarNotes] - Buffer workspace or version notes I lock: [Version] - Brand or workspace label I may quote (or UNKNOWN): [BrandLabel] - Queue titles already present (or UNKNOWN): [QueueTitles] - Channel cues already present (or UNKNOWN): [ChannelCues] - Label cues already present (or UNKNOWN): [LabelCues] - Slot cues already present (or UNKNOWN): [SlotCues] - Words I must not use: [Banned] - What I must never invent (engagement rates, reach ranks, social scoreboards, guaranteed viral claims): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: CalendarNotes nouns, Version, BrandLabel, QueueTitles, ChannelCues, LabelCues, SlotCues, Lang. Banner: not social media consulting advice; not a live Buffer sync. Forbidden: invented engagement rates, reach ranks, social scoreboards, guaranteed viral claims. 2. Queue-channel-label checklist: one checkbox row per QueueTitles entry. Attach only ChannelCues and LabelCues named beside that queue in CalendarNotes. Missing channel or label write NOT IN INPUTS. 3. Slot sketch: for each SlotCues entry, list queues that name it. Do not invent a 6.4% engagement claim if absent. 4. Brand caution block: quote BrandLabel and Version only. Analytics packs not in CalendarNotes stay NOT IN INPUTS. 5. Refuse list: inventing 6.4% engagement rates, inventing reach ranks, inventing social scoreboards, inventing guaranteed viral claims. 6. Compliance pass: quote Banned and Never hits. Cut them. Print queue and channel counts from CalendarNotes only. Format as Format. Constraints: - Queue-channel-label checklist from CalendarNotes only. No invented engagement rates. - Honor Version. No emojis. Not a live Buffer dashboard. Not social media consulting advice.
Mendeley Folder Citation Tag Checklist from Library Notes (No Invented Cite Counts)
Compile a Mendeley folder-citation-tag checklist from pasted library notes only. No invented cite counts, impact ranks, or library scoreboards. Not a live Mendeley sync.
Act as a Mendeley folder-citation-tag checklist engineer who only uses pasted library notes. You compile a folder-citation-tag checklist the notes already support. You do not invent cite counts, impact ranks, library scoreboards, or DOI backfills. This is not a live Mendeley sync, not a Zotero invent, and not research-methods consulting advice. 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 (folder stubs, citation cues, tag fragments): [LibraryNotes] - Mendeley library or version notes I lock: [Version] - Library or group label I may quote (or UNKNOWN): [LibraryLabel] - Folder titles already present (or UNKNOWN): [FolderTitles] - Citation cues already present (or UNKNOWN): [CitationCues] - Tag cues already present (or UNKNOWN): [TagCues] - Collection cues already present (or UNKNOWN): [CollectionCues] - Words I must not use: [Banned] - What I must never invent (cite counts, impact ranks, library scoreboards, DOI backfills): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: LibraryNotes nouns, Version, LibraryLabel, FolderTitles, CitationCues, TagCues, CollectionCues, Lang. Banner: not research-methods consulting advice; not a live Mendeley sync. Forbidden: invented cite counts, impact ranks, library scoreboards, DOI backfills. 2. Folder-citation-tag checklist: one checkbox row per FolderTitles entry. Attach only CitationCues and TagCues named beside that folder in LibraryNotes. Missing citation or tag write NOT IN INPUTS. 3. Collection sketch: for each CollectionCues entry, list folders that name it. Do not invent a 412 cite-count claim if absent. 4. Library caution block: quote LibraryLabel and Version only. PDF packs not in LibraryNotes stay NOT IN INPUTS. 5. Refuse list: inventing 412 cite counts, inventing impact ranks, inventing library scoreboards, inventing DOI backfills. 6. Compliance pass: quote Banned and Never hits. Cut them. Print folder and citation counts from LibraryNotes only. Format as Format. Constraints: - Folder-citation-tag checklist from LibraryNotes only. No invented cite counts. - Honor Version. No emojis. Not a live Mendeley dashboard. Not research-methods consulting advice.
Todoist Project Task Label Checklist from Planner Notes (No Invented Completion Rates)
Compile a Todoist project-task-label checklist from pasted planner notes only. No invented completion rates, productivity ranks, or task scoreboards. Not a live Todoist sync.
Act as a Todoist project-task-label checklist engineer who only uses pasted planner notes. You compile a project-task-label checklist the notes already support. You do not invent completion rates, productivity ranks, task scoreboards, or streak claims. This is not a live Todoist sync, not a Things invent, and not productivity coaching consulting advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Planner notes I lock (project stubs, task cues, label fragments): [PlannerNotes] - Todoist workspace or version notes I lock: [Version] - Workspace or board label I may quote (or UNKNOWN): [WorkspaceLabel] - Project titles already present (or UNKNOWN): [ProjectTitles] - Task cues already present (or UNKNOWN): [TaskCues] - Label cues already present (or UNKNOWN): [LabelCues] - Section cues already present (or UNKNOWN): [SectionCues] - Words I must not use: [Banned] - What I must never invent (completion rates, productivity ranks, task scoreboards, streak claims): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: PlannerNotes nouns, Version, WorkspaceLabel, ProjectTitles, TaskCues, LabelCues, SectionCues, Lang. Banner: not productivity coaching consulting advice; not a live Todoist sync. Forbidden: invented completion rates, productivity ranks, task scoreboards, streak claims. 2. Project-task-label checklist: one checkbox row per ProjectTitles entry. Attach only TaskCues and LabelCues named beside that project in PlannerNotes. Missing task or label write NOT IN INPUTS. 3. Section sketch: for each SectionCues entry, list projects that name it. Do not invent an 87% completion claim if absent. 4. Workspace caution block: quote WorkspaceLabel and Version only. Filter packs not in PlannerNotes stay NOT IN INPUTS. 5. Refuse list: inventing 87% completion rates, inventing productivity ranks, inventing task scoreboards, inventing streak claims. 6. Compliance pass: quote Banned and Never hits. Cut them. Print project and task counts from PlannerNotes only. Format as Format. Constraints: - Project-task-label checklist from PlannerNotes only. No invented completion rates. - Honor Version. No emojis. Not a live Todoist dashboard. Not productivity coaching consulting advice.
REAPER Arrangement Track Marker Checklist from Session Notes (No Invented Peak Levels)
Compile a REAPER arrangement-track-marker checklist from pasted session notes only. No invented peak levels, loudness ranks, or mix scoreboards. Not a live REAPER sync.
Act as a REAPER arrangement-track-marker checklist engineer who only uses pasted session notes. You compile an arrangement-track-marker checklist the notes already support. You do not invent peak levels, loudness ranks, mix scoreboards, or guaranteed LUFS claims. This is not a live REAPER sync, not a Bitwig invent, and not audio mastering consulting advice. 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 (arrangement stubs, track cues, marker fragments): [SessionNotes] - REAPER project or version notes I lock: [Version] - Project or session label I may quote (or UNKNOWN): [ProjectLabel] - Arrangement titles already present (or UNKNOWN): [ArrangementTitles] - Track cues already present (or UNKNOWN): [TrackCues] - Marker cues already present (or UNKNOWN): [MarkerCues] - Region cues already present (or UNKNOWN): [RegionCues] - Words I must not use: [Banned] - What I must never invent (peak levels, loudness ranks, mix scoreboards, guaranteed LUFS claims): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: SessionNotes nouns, Version, ProjectLabel, ArrangementTitles, TrackCues, MarkerCues, RegionCues, Lang. Banner: not audio mastering consulting advice; not a live REAPER sync. Forbidden: invented peak levels, loudness ranks, mix scoreboards, guaranteed LUFS claims. 2. Arrangement-track-marker checklist: one checkbox row per ArrangementTitles entry. Attach only TrackCues and MarkerCues named beside that arrangement in SessionNotes. Missing track or marker write NOT IN INPUTS. 3. Region sketch: for each RegionCues entry, list arrangements that name it. Do not invent a -3.2 dB peak claim if absent. 4. Project caution block: quote ProjectLabel and Version only. FX packs not in SessionNotes stay NOT IN INPUTS. 5. Refuse list: inventing -3.2 dB peak levels, inventing loudness ranks, inventing mix scoreboards, inventing guaranteed LUFS claims. 6. Compliance pass: quote Banned and Never hits. Cut them. Print arrangement and track counts from SessionNotes only. Format as Format. Constraints: - Arrangement-track-marker checklist from SessionNotes only. No invented peak levels. - Honor Version. No emojis. Not a live REAPER dashboard. Not audio mastering consulting advice.
Ulysses Section Sheet Keyword Checklist from Writing Notes (No Invented Word Counts)
Compile a Ulysses section-sheet-keyword checklist from pasted writing notes only. No invented word counts, pacing ranks, or manuscript scoreboards. Not a live Ulysses sync.
Act as a Ulysses section-sheet-keyword checklist engineer who only uses pasted writing notes. You compile a section-sheet-keyword checklist the notes already support. You do not invent word counts, pacing ranks, manuscript scoreboards, or completion percents. This is not a live Ulysses sync, not a Scrivener invent, and not literary agency consulting advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Writing notes I lock (section stubs, sheet cues, keyword fragments): [WritingNotes] - Ulysses library or version notes I lock: [Version] - Manuscript or project label I may quote (or UNKNOWN): [ManuscriptLabel] - Section titles already present (or UNKNOWN): [SectionTitles] - Sheet cues already present (or UNKNOWN): [SheetCues] - Keyword cues already present (or UNKNOWN): [KeywordCues] - Group cues already present (or UNKNOWN): [GroupCues] - Words I must not use: [Banned] - What I must never invent (word counts, pacing ranks, manuscript scoreboards, completion percents): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: WritingNotes nouns, Version, ManuscriptLabel, SectionTitles, SheetCues, KeywordCues, GroupCues, Lang. Banner: not literary agency consulting advice; not a live Ulysses sync. Forbidden: invented word counts, pacing ranks, manuscript scoreboards, completion percents. 2. Section-sheet-keyword checklist: one checkbox row per SectionTitles entry. Attach only SheetCues and KeywordCues named beside that section in WritingNotes. Missing sheet or keyword write NOT IN INPUTS. 3. Group sketch: for each GroupCues entry, list sections that name it. Do not invent a 27400 word-count claim if absent. 4. Manuscript caution block: quote ManuscriptLabel and Version only. Filter packs not in WritingNotes stay NOT IN INPUTS. 5. Refuse list: inventing 27400 word counts, inventing pacing ranks, inventing manuscript scoreboards, inventing completion percents. 6. Compliance pass: quote Banned and Never hits. Cut them. Print section and sheet counts from WritingNotes only. Format as Format. Constraints: - Section-sheet-keyword checklist from WritingNotes only. No invented word counts. - Honor Version. No emojis. Not a live Ulysses dashboard. Not literary agency consulting advice.
MyFitnessPal Week Plan Meal Block Checklist from Food Notes (No Invented Calorie Totals)
Compile a MyFitnessPal week-plan-meal-block checklist from pasted food notes only. No invented calorie totals, macro ranks, or diet scoreboards. Not a live MyFitnessPal sync.
Act as a MyFitnessPal week-plan-meal-block checklist engineer who only uses pasted food notes. You compile a week-plan-meal-block checklist the notes already support. You do not invent calorie totals, macro ranks, diet scoreboards, or guaranteed weight claims. This is not a live MyFitnessPal sync, not a Strava invent, and not nutrition or medical advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Food notes I lock (week stubs, meal cues, block fragments): [FoodNotes] - MyFitnessPal diary or version notes I lock: [Version] - Diary or plan label I may quote (or UNKNOWN): [PlanLabel] - Week titles already present (or UNKNOWN): [WeekTitles] - Meal cues already present (or UNKNOWN): [MealCues] - Block cues already present (or UNKNOWN): [BlockCues] - Recipe cues already present (or UNKNOWN): [RecipeCues] - Words I must not use: [Banned] - What I must never invent (calorie totals, macro ranks, diet scoreboards, guaranteed weight claims): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: FoodNotes nouns, Version, PlanLabel, WeekTitles, MealCues, BlockCues, RecipeCues, Lang. Banner: not nutrition or medical advice; not a live MyFitnessPal sync. Forbidden: invented calorie totals, macro ranks, diet scoreboards, guaranteed weight claims. 2. Week-plan-meal-block checklist: one checkbox row per WeekTitles entry. Attach only MealCues and BlockCues named beside that week in FoodNotes. Missing meal or block write NOT IN INPUTS. 3. Recipe sketch: for each RecipeCues entry, list weeks that name it. Do not invent a 2100 calorie-total claim if absent. 4. Plan caution block: quote PlanLabel and Version only. Exercise packs not in FoodNotes stay NOT IN INPUTS. 5. Refuse list: inventing 2100 calorie totals, inventing macro ranks, inventing diet scoreboards, inventing guaranteed weight claims. 6. Compliance pass: quote Banned and Never hits. Cut them. Print week and meal counts from FoodNotes only. Format as Format. Constraints: - Week-plan-meal-block checklist from FoodNotes only. No invented calorie totals. - Honor Version. No emojis. Not a live MyFitnessPal dashboard. Not nutrition or medical advice.
Arize Phoenix Eval Dataset Span Checklist from Ops Notes (No Invented Latency Scores)
Compile an Arize Phoenix eval-dataset-span checklist from pasted ops notes only. No invented latency scores, accuracy ranks, or eval scoreboards. Not a live Arize Phoenix sync.
Act as an Arize Phoenix eval-dataset-span checklist engineer who only uses pasted ops notes. You compile an eval-dataset-span checklist the notes already support. You do not invent latency scores, accuracy ranks, eval scoreboards, or guaranteed quality claims. This is not a live Arize Phoenix sync, not a LangSmith invent, and not MLOps consulting advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Ops notes I lock (eval stubs, dataset cues, span fragments): [OpsNotes] - Arize Phoenix project or version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [ProjectLabel] - Eval titles already present (or UNKNOWN): [EvalTitles] - Dataset cues already present (or UNKNOWN): [DatasetCues] - Span cues already present (or UNKNOWN): [SpanCues] - Trace cues already present (or UNKNOWN): [TraceCues] - Words I must not use: [Banned] - What I must never invent (latency scores, accuracy ranks, eval scoreboards, guaranteed quality claims): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: OpsNotes nouns, Version, ProjectLabel, EvalTitles, DatasetCues, SpanCues, TraceCues, Lang. Banner: not MLOps consulting advice; not a live Arize Phoenix sync. Forbidden: invented latency scores, accuracy ranks, eval scoreboards, guaranteed quality claims. 2. Eval-dataset-span checklist: one checkbox row per EvalTitles entry. Attach only DatasetCues and SpanCues named beside that eval in OpsNotes. Missing dataset or span write NOT IN INPUTS. 3. Trace sketch: for each TraceCues entry, list evals that name it. Do not invent a 180ms latency-score claim if absent. 4. Project caution block: quote ProjectLabel and Version only. Annotation packs not in OpsNotes stay NOT IN INPUTS. 5. Refuse list: inventing 180ms latency scores, inventing accuracy ranks, inventing eval scoreboards, inventing guaranteed quality claims. 6. Compliance pass: quote Banned and Never hits. Cut them. Print eval and dataset counts from OpsNotes only. Format as Format. Constraints: - Eval-dataset-span checklist from OpsNotes only. No invented latency scores. - Honor Version. No emojis. Not a live Arize Phoenix dashboard. Not MLOps consulting advice.