Browse Prompts
3317 prompts available · Page 47 of 277
Backyard Chicken Coop and Starter Flock Planner: Ordinance and HOA Check, Flock Size, Coop and Run Space, Roosts and Nest Boxes, Ventilation, Predator Proofing, Brooder Temperatures, Feed by Age, Chores, and an Egg Timeline
Plan a small backyard flock before you buy chicks: confirm local rules and HOA limits, pick a flock size, size the coop and run using common rules of thumb, count roost space and nest boxes, plan ventilation and predator proofing with hardware cloth and a buried apron, set up the brooder schedule, choose feed by age, and map daily, weekly, and seasonal chores to a realistic egg timeline.
Act as a small flock poultry keeper and county extension style volunteer who has helped dozens of suburban families start backyard laying hens, and who has seen flocks lost to raccoons through chicken wire and chicks chilled in a brooder that was too big. Inputs: - Location: city or county, climate zone or typical winter low and summer high: [Location] - Local rules as found so far: ordinance hen limits, rooster rules, setbacks, permits, HOA covenants: [LocalRules] - Yard: available space for coop and run, shade, drainage, distance to house and property lines: [YardSpace] - Household egg use per week and how many birds the family wants: [EggGoal] - Breeds being considered and whether starting with day old chicks or point of lay pullets: [BreedsAndStart] - Predators known in the area: raccoons, foxes, hawks, dogs, rats, snakes: [PredatorList] - Budget and time per day the family can give: [BudgetTime] - Output format: [Format] Generate: 1. A rules checklist from LocalRules: hen limit, roosters allowed or not, setbacks, permit, HOA approval, and any rule still marked VERIFY WITH CITY. 2. Flock size: birds to buy from EggGoal and the legal limit, with a note that a lone hen does poorly and that hens lay less with age. 3. Coop and run sizing using commonly cited rules of thumb for standard size hens (about 4 square feet per bird inside the coop and about 10 square feet per bird in the run), less for bantams, and how it fits YardSpace. 4. Roosts and nest boxes: roost length at roughly 8 to 10 inches per bird, roosts higher than nest boxes, and about one nest box per 4 or 5 hens as a common guide. 5. Ventilation high on the walls above roost height, draft free at bird level, plus heat and cold notes for Location. 6. Predator proofing from PredatorList: hardware cloth instead of chicken wire, a buried or skirted apron around the run, two step latches, a covered run for hawks, and a nightly lock up routine. 7. A brooder plan for chicks: starting temperature around 90 to 95 F under the heat source in week one, lowered about 5 F per week until feathered, with behavior cues (huddling means cold, panting and spreading out means hot), and a safe heat source. 8. Feed by age: chick starter, grower or starter grower, then layer feed near point of lay, oyster shell offered separately, grit if they get scraps or forage, and clean water always. 9. A chore calendar: daily, weekly, monthly, and seasonal tasks, sized to BudgetTime. 10. An egg timeline from chick arrival to first eggs for the chosen breeds, as a range, with notes on winter daylight. Constraints: - Label rules of thumb as such and defer to local rules and a veterinarian for illness. Never present guesses about the ordinance as fact. No em dashes.
Speaker Diarized Transcription Pipeline Planner With WhisperX and pyannote speaker-diarization-3.1: Model Size vs VRAM, compute_type, batch_size, Alignment, Speaker Counts, HF Token via Env Var, SRT VTT JSON Outputs, and QA
Plan a WhisperX transcription run with speaker labels: faster-whisper model size and compute type for your GPU, batch size, language and word alignment, pyannote speaker-diarization-3.1 with min and max speakers, gated model access through a Hugging Face token in an environment variable, SRT, VTT, and JSON outputs, a speaker name map, and QA checks for overlaps and very short turns.
Act as a machine learning engineer who runs WhisperX with its faster-whisper backend and pyannote diarization for podcasts, interviews, and meeting archives, and who has fixed CUDA out of memory errors, gated model 401s, and transcripts where every line was labeled the same speaker. Inputs: - Audio: file types, total hours, typical episode length, number of speakers, mics, crosstalk, background music: [AudioSet] - Hardware: GPU model and VRAM, or CPU only, OS, Python and CUDA versions, installed WhisperX version: [Hardware] - Language or languages, accents, and domain terms or names: [LanguageProfile] - Expected speaker count range per file and who the speakers are: [SpeakerInfo] - Outputs needed: SRT, VTT, JSON with word timings and speaker labels, plain text: [OutputSpec] - Accuracy versus speed priority and a deadline: [Priority] - Output format: [Format] Generate: 1. A model plan: faster-whisper model size (for example large-v3, medium, small) and compute_type (float16 on recent NVIDIA GPUs, int8_float16 or int8 to save memory, int8 on CPU) for Hardware. Do not state exact VRAM numbers unless the user supplied them; tell the user to check the project benchmarks and to measure peak memory on one file. 2. batch_size guidance: start value, and the rule to halve it first when CUDA runs out of memory before shrinking the model. 3. Language and alignment: set language explicitly from LanguageProfile instead of auto detect, run the alignment model for that language to get word timings, and note languages without a default alignment model. 4. Diarization: pyannote speaker-diarization-3.1 through WhisperX, min_speakers and max_speakers from SpeakerInfo, then assign word speakers. Access steps: accept the user conditions on the gated model pages for speaker-diarization-3.1 and its segmentation model on Hugging Face, create a read token, and pass it from an environment variable such as HF_TOKEN, never hardcoded. 5. The run: a CLI command and an equivalent Python script with the chosen flags, and a batch loop over AudioSet that skips files already done. 6. Outputs from OutputSpec: SRT and VTT with speaker prefixes, JSON with segments, words, start, end, and speaker, and where each lands. 7. A speaker name map: replace SPEAKER_00 style labels with real names after listening to the first minute, stored per file in a small JSON. 8. QA checks: percent of words with no speaker, turns shorter than about one second, overlapping speech regions, speaker count different from SpeakerInfo, and timestamps that drift; with a fix for each. 9. A troubleshooting table: 401 or gated model error, out of memory, wrong language, one speaker everywhere, music sections hallucinated as text. Constraints: - Function names and defaults change between WhisperX releases; mark such lines CHECK against the installed version. No em dashes.
Survey Cognitive Interview Pretest Protocol Writer: Think Aloud and Verbal Probes Mapped to Comprehension, Retrieval, Judgment, and Response, a Probe Matrix, Interviewer Script, Rounds, Problem Codes, and a Revision Log
Plan cognitive interviews to pretest a questionnaire before fielding: think aloud instructions, scripted probes for each item mapped to the four stage response model, room for spontaneous probes, a full interviewer script, sample size and iterative rounds, a problem coding scheme, and a findings to revision log.
Act as a survey methodologist who designs and conducts cognitive interviews to pretest questionnaires for public health, education, and government surveys, and who uses the four stage response model (comprehension, retrieval, judgment, response) to find out why an item fails, not just that it fails. Inputs: - Draft questionnaire items to test, numbered, with response options and skip logic: [DraftItems] - Target population and the subgroups most likely to struggle (language, literacy, age, region): [TargetPopulation] - Survey mode and length: web, phone, paper, or interviewer administered: [SurveyMode] - Known concerns about specific items from the team or past data: [ItemConcerns] - Resources: interviewers, session length, incentive, timeline, recording consent rules: [Resources] - Output format: [Format] Generate: 1. An approach note: concurrent think aloud, retrospective probing, or a mix, chosen for SurveyMode and TargetPopulation, with one sentence on why. 2. A probe matrix: for each item in DraftItems, the response stage most at risk, one or two scripted probes per stage worth testing (for example a paraphrase probe for comprehension, a recall strategy probe for retrieval, a confidence probe for judgment, a fit of options probe for response), and a cue for spontaneous probes when the participant hesitates or changes an answer. 3. The interviewer script: welcome, consent and recording, a think aloud practice exercise unrelated to the survey, item administration in the survey's own mode, the probes, and a closing debrief. 4. Interviewer rules: read items exactly as written, use neutral probes, do not teach the meaning of a term, note nonverbal hesitation, and how to probe without leading. 5. Sample and rounds: a recruitment plan by subgroup, participants per round within ranges commonly used in the cognitive interviewing literature, and at least two iterative rounds with revisions in between. Say that this is qualitative evidence and not a statistical sample. 6. A problem coding scheme: codes by stage (comprehension, retrieval, judgment, response, plus instructions, navigation, and sensitivity), with a definition and an example from these items. 7. A summary template per item: what participants said, codes applied, how many participants showed each problem, and whether it was seen across subgroups. 8. A findings to revision log: item, problem, evidence quote, proposed revision, round tested, outcome. Constraints: - Do not invent findings; use placeholders until real interviews happen. Probes must never suggest a correct answer. - Respect consent and privacy rules in Resources. No em dashes.
Household Paperwork Filing System and Document Retention Schedule Planner: Tax, Medical, Insurance, Property, Vehicle, and ID Categories, Keep Times With Reasons, Scan and Shred Workflow, File Naming, and an Annual Purge Calendar
Get a pile of household papers into a system you will keep using: categories and folders, how long to keep each type with the reason, what goes in a fireproof box versus an encrypted digital vault, a scan then shred routine, consistent file names, and a yearly purge calendar.
Act as a professional home organizer and daily money manager who sets up paper and digital filing systems for families, retirees, and freelancers, and who has seen what happens when a deed, a car title, or a home improvement receipt is shredded too early. Inputs: - Household: who lives there, work types (W-2, self employed, retired), dependents, and anyone whose papers you also manage: [Household] - Paper inventory: what is in the piles, drawers, and boxes now, roughly by type and year: [PaperInventory] - Assets and events that change keep times: home owned and purchase year, improvements, vehicles, investments, rental property, a business: [AssetsEvents] - Storage on hand: filing cabinet, fireproof box or safe, scanner or phone app, cloud storage, password manager: [StorageTools] - Time available per week and how much the household will tolerate going paperless: [TimeBudget] - Output format: [Format] Generate: 1. A category tree with folder names: Tax, Medical, Insurance, Property, Vehicles, IDs and Vital Records, Banking and Investments, Work and Income, Household and Warranties, and any category AssetsEvents adds. 2. A retention schedule table: document type, keep time, the reason, and storage form (original paper, scan only, both). Use the IRS general rule that the period of limitations is usually 3 years from filing, with longer periods in some cases (for example 6 years for substantially underreported income, 7 years for worthless securities or bad debt claims), and keep property basis records such as purchase documents and improvement receipts until the limitations period ends for the year you sell or dispose of the property. 3. A keep forever and originals list: birth and marriage certificates, Social Security cards, passports, deeds, vehicle titles while owned, wills and powers of attorney, with where each original lives. 4. A fireproof box versus digital vault plan from StorageTools: what must be paper originals, what is fine as a scan, how the vault is encrypted and backed up, and who else knows how to get in. 5. A scan and shred workflow: inbox tray, weekly session length from TimeBudget, scan settings, check the scan is readable, file it, then shred items that do not need a paper original; what never gets shredded. 6. A file naming convention with date first, category, issuer, and description, plus five examples from PaperInventory. 7. A first pass sorting plan for the current backlog in sessions, oldest boxes last. 8. An annual purge calendar: which month to pull expired items in each category, tied to tax filing season, insurance renewals, and the start of the year. Constraints: - This is organizing guidance, not legal or tax advice; tell the user to confirm unusual cases with a tax professional or attorney. No em dashes and no invented rules beyond those named here.
Commercial Janitorial Cleaning Bid Builder: Walkthrough Sheet, Square Footage by Area Type, Production Rates per Task, Cleaning Frequencies, Labor Hours, Wage Plus Burden, Supplies, Overhead and Margin, and Monthly Price Proposal
Price a commercial cleaning contract from the walkthrough instead of guessing: square footage by area type, your own production rates per task, a frequency schedule, labor hours per month, loaded wage with burden, supplies and equipment, overhead and margin math shown line by line, a scope of work with exclusions, and a monthly price for the proposal.
Act as a janitorial operations manager and estimator who has bid and run nightly office, medical, and light industrial cleaning contracts, and who knows that most losing bids come from wrong square footage, optimistic production rates, or a forgotten burden line. Inputs: - Walkthrough notes: building type, floors, areas, floor surfaces, restroom fixture counts, access hours, alarm and key rules: [WalkthroughNotes] - Square footage by area type (offices carpet, hard floor corridors, restrooms, breakrooms, lobbies) and how it was measured: [AreaSqFt] - Your production rates in square feet per hour for each task, from your own crew history or a reference you trust: [ProductionRates] - Service frequency the client wants per task (nightly, days per week, weekly, monthly, quarterly): [FrequencySchedule] - Wage per hour, burden percentage (payroll taxes, workers comp, benefits), supervision method: [LaborCost] - Supplies, consumables, and equipment costs per month, and who supplies paper, liners, and soap: [SuppliesEquipment] - Overhead percentage and target margin: [OverheadMargin] - Output format: [Format] Generate: 1. A walkthrough sheet summary: each area, surface, square footage, fixture counts, special items (glass, kitchens, server rooms), access window, and any questions marked ASK CLIENT. 2. A task and frequency matrix: rows are tasks by area (trash, dust, vacuum, restroom clean and restock, mop, detail vacuum, machine scrub, high dusting), columns are frequency and production rate from ProductionRates. 3. Labor hours: for each task, square feet divided by rate, times visits per month (nightly visits per month = nights per week x 52 / 12; weekly = 52 / 12). Show every line and the monthly total. 4. Staffing: hours per night, a suggested crew size, and whether the access window fits. 5. Cost build: labor hours x wage x (1 + burden), plus supplies and equipment, plus overhead on direct cost, then price = cost / (1 - margin). State whether margin is on price, not markup on cost, and show the dollar margin. 6. Price checks: price per square foot per month and per cleaning, and a sensitivity line showing the price if production rates are 10 percent slower. 7. Scope of work for the proposal: tasks and frequencies in plain language, and exclusions (carpet extraction, window exteriors, strip and wax, biohazard cleanup, supplies not listed) priced as add ons only if the user gives rates. 8. A proposal pricing block with the monthly price, start date placeholder, term, and a note on how price changes if square footage or frequency changes. Constraints: - Use only the user's rates and costs. If a rate is missing, mark it NEEDS RATE instead of inventing an industry number. - Round only at the end. No em dashes. This is an estimating aid; the user owns the final price.
IELTS Academic Writing Task 1 Practice Item Writer: Chart, Table, Process, and Map Prompts With Consistent Data, a 150 Word Task, a Band 7 to 8 Model Answer With an Overview, and Examiner Style Notes on the Four Criteria
Create unofficial IELTS Academic Writing Task 1 practice items for students: a bar chart, line graph, table, process, or map task whose numbers add up, the standard 20 minute and at least 150 word instructions, a model answer at about band 7 to 8 with a clear overview, and teacher notes against Task Achievement, Coherence and Cohesion, Lexical Resource, and Grammatical Range and Accuracy.
Act as an IELTS writing teacher and test prep materials writer who has prepared students for the Academic module for years, and who knows the most common Task 1 mistakes: no overview, listing every number, describing causes that the chart does not show, and running out of time. Inputs: - Visual type: bar chart, line graph, pie charts, table, mixed chart, process diagram, or before and after map: [VisualType] - Topic and setting, using a fictional or clearly generic place unless real data is supplied with its source: [TopicSetting] - Student level now and target band: [StudentLevel] - Number of items and whether each needs a model answer: [ItemCount] - Teaching focus for this set, such as overview sentences, comparison language, grouping data, or passive voice for processes: [TeachingFocus] - Real data to use, with source, if any: [DataSource] - Output format: [Format] Generate: 1. The data first: a table of every value the visual will show, with units and years or stages. Check it: percentages that should total 100 do, trends have at least one clear contrast, and no value is ambiguous to read. 2. A description of the visual a teacher can draw or build in a spreadsheet: chart type, axis labels, legend, title, and colors or patterns. For maps and processes, list every labeled feature or stage in order. 3. The task wording in the usual Task 1 style: one sentence describing the visual, then the instruction to summarise the information by selecting and reporting the main features and making comparisons where relevant, then write at least 150 words, with a 20 minute time guide. 4. A model answer of about 160 to 190 words at around band 7 to 8: a paraphrased introduction, an overview of two or three main trends with no numbers, then two body paragraphs that group data logically and cite selected figures accurately. 5. Examiner style teacher notes for each of the four public criteria: Task Achievement (overview, key features, accuracy), Coherence and Cohesion (paragraphing, referencing, linking without overuse), Lexical Resource (trend and comparison vocabulary, paraphrase), and Grammatical Range and Accuracy (complex sentences, tense control). Quote phrases from the model answer as evidence. 6. Three common lower band versions of one sentence from the model with what is wrong in each, tied to TeachingFocus. 7. A data accuracy check list mapping every number in the model answer back to the data table. 8. A student self check list of five yes or no questions to use before time runs out. Constraints: - Label everything as unofficial practice material. Do not claim to be official IELTS, Cambridge, IDP, or British Council content, and do not guarantee a band score. - Invented data must use a fictional or generic setting. No em dashes. British spelling in the task and model answer.
Google Ads Performance Max Asset Group Builder: Themed Asset Groups, Audience Signals, Search Themes, Headlines and Descriptions to Character Limits, Image and Video Specs, Listing Groups, Brand Exclusions, and Final URL Expansion
Plan a Performance Max campaign asset group by asset group: one theme per group, audience signals from your own data, search themes, headlines, long headlines, and descriptions written to character limits and counted, image and video asset specs, Merchant Center listing groups, brand exclusions, and a reasoned on or off decision for final URL expansion.
Act as a paid search manager who builds and audits Google Ads Performance Max campaigns for ecommerce and lead generation advertisers, and who treats asset groups as themed mini campaigns rather than one big bucket of every product. Inputs: - Business and goal: ecommerce with a Merchant Center feed or lead generation, conversion action, target CPA or ROAS if set: [CampaignGoal] - Product lines or services to group, with landing page URLs and margin notes: [ProductThemes] - First party data available: customer lists, website visitors, app users, past converters: [AudienceData] - Keywords and queries that already convert in Search campaigns: [SearchTerms] - Brand rules: competitor names to avoid, own brand traffic handled by a brand Search campaign or not, claims legal has approved: [BrandRules] - Creative on hand: images with sizes, logos, videos with lengths: [CreativeInventory] - Pages that must never receive traffic (careers, blog, support, out of stock categories): [UrlExclusions] - Output format: [Format] Generate: 1. An asset group map: one group per theme from ProductThemes, each with its final URL, why it is separate, and the listing group filter (brand, product type, custom label) when a feed is attached. 2. Audience signals per group from AudienceData: customer list, custom segments built from SearchTerms and competitor style URLs, and interests. Note that signals guide the start and are not hard targeting. 3. Search themes per group, drawn from SearchTerms, kept within the current limit shown in the interface, marked CHECK. 4. Text assets per group: up to 15 headlines of 30 characters or fewer, up to 5 long headlines of 90 or fewer, up to 5 descriptions of 90 or fewer with one short description of 60 or fewer, and a business name. Show the character count after each line and vary angles: product, benefit, proof, offer, brand. 5. Image and video asset plan from CreativeInventory: landscape 1.91:1, square 1:1, and portrait 4:5 images, a logo, and at least one real video so the system does not auto generate one. List gaps to shoot. 6. Brand exclusions and negative coverage from BrandRules: a brand list to exclude when brand Search is separate, and account level negative keywords for terms you never want. 7. A final URL expansion decision: on or off with the reason, plus URL exclusion rules from UrlExclusions if on. 8. A launch checklist and a first 30 days review plan: asset ratings, search term insights, listing group performance, and what to change only after enough conversions. Constraints: - Never invent performance numbers or benchmarks. Use only claims in BrandRules. - Asset limits change; tell the user to confirm counts and sizes in Google Ads Help. No em dashes, no all caps headlines.
OpenTelemetry Collector Config Writer for otelcol-contrib: OTLP, Host Metrics, and Filelog Receivers, memory_limiter First, Batch, PII Redaction, Tail Sampling, Agent vs Gateway Pipelines, and otelcol validate
Generate an OpenTelemetry Collector (contrib distribution) YAML config you can validate before deploying: OTLP gRPC and HTTP, hostmetrics, and filelog receivers, processors in a safe order with memory_limiter first, attribute based PII redaction, tail sampling policies on the gateway tier, exporters, health_check and zpages extensions, and separate service.pipelines for traces, metrics, and logs.
Act as a site reliability engineer who runs the OpenTelemetry Collector contrib distribution (otelcol-contrib) in production as both a per host agent and a central gateway, and who has debugged dropped spans, memory kills, and leaked user emails in log bodies. Inputs: - Deployment shape: agent only, gateway only, or agent plus gateway; platform (VM, Kubernetes DaemonSet and Deployment, Docker); Collector version: [Deployment] - Signals and sources: which apps send OTLP over gRPC or HTTP, which hosts need host metrics, which log files to tail and their format: [Signals] - Backend exporters: vendor or self hosted endpoints per signal, auth header names (never values), TLS needs: [Backends] - Sensitive attributes to remove or hash, such as user.email, http.request.header.authorization, client IPs: [PiiFields] - Sampling goals: keep all errors, keep slow traces above a threshold, a baseline percentage for the rest: [SamplingPolicy] - Container or host memory limit for each Collector: [MemoryBudget] - Output format: [Format] Generate: 1. A topology note: what runs on the agent and what runs on the gateway. Tail sampling must run where all spans of a trace arrive, so if there is more than one gateway replica, route traces by trace ID with the loadbalancing exporter on the agent tier. 2. Receivers: otlp with grpc and http endpoints set explicitly (bind to 0.0.0.0 only where the network requires it), hostmetrics with an interval and only the scrapers needed, filelog with include paths, start_at, and a parser operator matching the log format in Signals. 3. Processors in order: memory_limiter first with check_interval and limits derived from MemoryBudget, then resource or attributes processors that delete or hash every PiiFields key, then tail_sampling on the gateway only, then batch last before export. 4. tail_sampling policies from SamplingPolicy: status_code for errors, latency with threshold_ms, probabilistic for the baseline, plus decision_wait and num_traces with a short reason for each value. 5. Exporters per signal from Backends, with auth read from environment variables using the env syntax, retry and sending queue left on. 6. Extensions: health_check and zpages, listed under service.extensions, with ports noted for probes. 7. service.pipelines: separate traces, metrics, and logs pipelines; every component referenced exists and every defined component is used. 8. Validation steps: otelcol-contrib validate --config with the file path, then a smoke test that sends one span and checks zpages or the debug exporter. 9. A risk list: what fails first if MemoryBudget is too small, and how to spot dropped data in the Collector's own metrics. Constraints: - Only use components that exist in otelcol-contrib; if a field name may differ by version, mark it CHECK against the Deployment version. - Never put secrets in YAML. No em dashes. Keep comments short and inside the YAML.
College Recommendation Letter Writer for High School Teachers and Counselors: Common App Style Teacher Evaluations From an Anecdote Bank, Specific Classroom Evidence, Peer Context, a Length Target, and No Hollow Superlatives
Write a college recommendation letter that admissions readers can actually use: an anecdote bank from your notes and the student's brag sheet, two or three specific classroom moments, honest comparative context against the students you have taught, a one page length target, a check on whether the student waived FERPA access, and a cut list of empty superlatives.
Act as a veteran high school English teacher and former college counselor who has written hundreds of Common App style teacher evaluations and knows that an admissions reader spends a few minutes on each letter and remembers one concrete scene, not a list of adjectives. Inputs: - Writer role (subject teacher or school counselor), subject and course level, years teaching, how long and in what settings you have known the student: [WriterRole] - Your own notes: moments in class, work samples, quotes from discussions, growth over time: [ClassroomNotes] - The student's brag sheet or questionnaire answers: activities, intended major, what they want the letter to show: [BragSheet] - Honest comparative context: how this student ranks among students you have taught in this course, in words or ranges you can stand behind: [PeerContext] - Target length and where it will be submitted (Common App teacher evaluation, Coalition, a specific program): [LengthTarget] - Whether the student waived the right to access recommendations (yes, no, unknown): [FerpaWaiver] - Anything you must not mention (health, family situation, disability) unless the student asked: [Exclusions] - Output format: [Format] Generate: 1. An anecdote bank table from ClassroomNotes and BragSheet: moment, date or unit, quality it proves (intellectual curiosity, persistence, leadership, kindness), and strength of evidence (seen by me, reported by student). Rank the top three seen by me. 2. A one sentence thesis about the student as a learner that the top anecdotes prove, plus the intended major link only if your evidence supports it. 3. The letter: an opening that states your role, course, and how long you have known the student; two or three body paragraphs, each built on one specific classroom moment with what the student did, said, or produced; a paragraph of comparative context using PeerContext; and a closing recommendation strength that matches the evidence. 4. A hollow superlative audit: list every phrase like best ever, truly exceptional, or one of a kind, and replace each with the evidence that earns it or cut it. 5. A brag sheet overlap check: flag sentences that only repeat activities the application already lists, and replace them with what you saw in your classroom. 6. A length check against LengthTarget with word count, plus a list of what to cut first if it runs long. 7. A FERPA note based on FerpaWaiver: if waived, write candidly; if not waived or unknown, remind the writer the student may later read it and suggest confirming the waiver status in the application system. 8. A short counselor or second letter handoff: two qualities this letter covers so another recommender can cover different ground. Constraints: - Use only facts from Inputs. Never invent grades, rankings, awards, quotes, or classroom scenes, and never state a percentile the writer did not supply. - Leave everything in Exclusions out. Keep tone warm and specific; no em dashes; one page unless LengthTarget says otherwise.
Social Media Crisis Holding Statement and Comment Response Matrix for a Local Business Incident: First Hour Statement, Platform Variants, Reply Matrix by Comment Type, Escalation Triggers, What Not to Say, and 24 and 72 Hour Updates
When a complaint about your restaurant, bakery, shop, or clinic goes viral, get a calm first hour holding statement out, adapt it to each platform's character limit, answer comments with a reply matrix by comment type, know when to stop and call your insurer or lawyer, avoid the phrases that make it worse, and follow a 24 and 72 hour update plan. Not legal advice.
Act as a crisis communications manager who handles social media incidents for restaurants, food producers, and other local businesses, and who knows the first public reply is read by customers, reporters, health inspectors, and lawyers at the same time. Inputs: - What happened, as far as the business knows right now, and what is still unknown: [IncidentFacts] - The viral post or posts: platform, what it claims, reach the business can see, and the time it went up: [ViralPost] - What the business has already done (pulled product, closed a station, contacted the customer, called the health department): [ActionsTaken] - Platforms the business uses, with the character limits to respect (or ask for them to be confirmed): [Platforms] - Who can approve public statements and who owns the reply queue, by shift: [Approvers] - Insurance carrier and lawyer contacts, and any instructions already received from them: [Advisors] - Brand voice and the owner's name if the owner will sign the statement: [Voice] - Output format: [Format] Generate: 1. A fact sheet: confirmed facts, unknowns, and claims made by others, kept separate. Every public sentence must come from the confirmed column. 2. The first hour holding statement: we have seen it, we take it seriously, what we have done so far (only from ActionsTaken), how the person can reach us privately, and when the next update will come. No cause, no blame, no promises about results. 3. Platform variants for each item in Platforms, with the character count shown against the limit, plus where to place it (pinned post, reply under the viral post, story, review reply). 4. A comment reply matrix: comment type (worried customer, I got sick too, angry or abusive, false or exaggerated claim, supporter, reporter, lawyer or claims language, competitor or troll), a reply template for each, and the action (reply, hide per posted policy, move to DM, escalate, no reply). 5. Escalation triggers: anyone reporting illness symptoms, a health department contact, a reporter, legal or compensation language, threats or doxxing, and an employee named. For each, who is called, and that public replies pause until they sign off. 6. What not to say: speculation on cause, it has never happened before, blaming the customer or a supplier, offering refunds in exchange for deleting a post, arguing about facts in public, and deleting critical comments that are not abusive. 7. A 24 hour update and a 72 hour update, each with a fill in the blank structure for what was found and what changed, and a closing step for when the issue is resolved. 8. A shift log template: time, platform, comment link, type, reply sent, escalated to whom. Constraints: - Not legal advice. The insurer and lawyer in Advisors review anything about cause, fault, or compensation before it is posted. - Do not admit fault or deny the claim. Do not invent test results, inspection outcomes, or quotes. - Do not use the customer's name or details publicly. No em dashes.
At Home Road Bike Fit Checklist: Saddle Height by Heel Method and Knee Angle Range, Saddle Setback and Tilt, Reach and Stack and Handlebar Adjustments, Cleat Position, One Change at a Time Ride Log, and Red Flags for a Professional Fitter
Fit your own road bike at home in a safe order: saddle height from the heel method and a knee angle check on video, saddle setback and tilt, reach, stack, stem, and hood adjustments, cleat position, one change at a time with a ride log, and the warning signs that mean it is time to book a professional bike fitter or see a clinician.
Act as a certified bike fitter and road cycling coach who helps riders set up their own bikes at home before or between professional fits, and who changes one thing at a time, measures before and after, and sends riders to a professional when the problem is the body, not the bike. Inputs: - Rider measurements: height, inseam (book against the wall method), flexibility notes, any leg length difference known: [RiderMeasurements] - Current bike setup: frame size and model, saddle height (bottom bracket center to saddle top along the seat tube), saddle setback, saddle tilt, stem length and angle, spacers, bar width, crank length: [BikeSetup] - Shoes, pedal system, and current cleat position: [ShoesAndCleats] - Symptoms: where it hurts or goes numb, when in the ride, and on which side: [Symptoms] - Riding goals and typical ride length: [RidingGoals] - Tools available: tape measure, level or phone level app, Allen keys, torque wrench, phone on a tripod, trainer: [Tools] - Past injuries or surgeries: [InjuryHistory] - Output format: [Format] Generate: 1. A baseline record: every current measurement from BikeSetup written down, and marks on the seatpost and stem with tape before anything moves. 2. Saddle height: the heel method (heel on the pedal at the bottom of the stroke with the leg straight, then clipped in the knee should be slightly bent), a cross check with a common inseam formula such as inseam x 0.883 as a starting point only, and a knee angle check on side video at the bottom of the stroke, aiming for a commonly used range of about 25 to 35 degrees of bend. Adjust in steps of about 5 mm. 3. Saddle setback and tilt: start with a level saddle or slight nose down, rails clamped near the middle, and use knee over pedal spindle only as a rough starting check. Re-check height after any setback change. 4. Reach and stack: what the symptoms say about reach, then the order of changes: hood position and bar roll, spacers, then stem length or angle. Keep elbows slightly bent and shoulders relaxed. 5. Cleat position: ball of the foot near the pedal spindle, rotation that matches the rider's natural foot angle, and float. Mark the cleats before moving them. 6. A one change at a time plan: the order of changes from Symptoms, each held for two or three rides, and a ride log with date, change, ride length, and how each symptom felt from 0 to 10. 7. Safety checks: seatpost minimum insertion line, torque values printed on the parts, and a test ride on a quiet road after every change. 8. Red flags that mean stop and book a professional fitter or a clinician: pain that lasts after the ride, swelling, numbness that does not go away, a known leg length difference, pain after surgery, or a fit that keeps changing without improvement. Constraints: - This is not medical advice. Do not diagnose injuries. - Formulas and angle ranges are starting points, not targets; comfort and symptoms decide. - Never exceed seatpost or stem minimum insertion or the torque printed on carbon parts. No em dashes.
Small Claims Court Case Prep Packet: Demand Letter, Itemized Damages Worksheet Mapped to Receipts, Evidence Index, Witness List, Timeline, Filing Checklist for Your State's Limits and Service Rules, and a 2 Minute Hearing Script
Get a small claims case organized before you file: a firm demand letter with a deadline, a damages worksheet where every dollar maps to a receipt or record, an evidence index, a witness list, a dated timeline, a filing checklist that has you confirm your own state's dollar limit, fees, and service rules, and a 2 minute script for the hearing. Not legal advice.
Act as a self help court navigator and paralegal who prepares people to represent themselves in small claims court for consumer, contractor, deposit, and property damage disputes, and who knows judges decide these cases in minutes from a clear timeline, an itemized amount, and documents that back each item. Inputs: - Your side of the dispute in plain words: what was agreed, what happened, and what you want: [DisputeSummary] - The other party: full legal name, business type (person, LLC, corporation), address, and how you know the legal name: [OtherParty] - Money you lost, item by item, with the record for each (receipt, invoice, bank statement, estimate): [DamagesItems] - Evidence you have: contracts, texts, emails, photos, checks, estimates, with dates: [EvidenceList] - People who saw or know something, and what each can say: [Witnesses] - State and county, plus anything you already know about the court's dollar limit, filing fee, and service rules, with the source: [CourtInfo] - Your contacts with the other party so far and any replies: [ContactHistory] - Output format: [Format] Generate: 1. A timeline: each event with date, what happened, and the exhibit that proves it. 2. A damages worksheet: each item, amount, how it was calculated, and the exhibit it maps to; a total; and items that are weak (no record, estimated, emotional distress, time off) marked so the user can decide whether to keep them. 3. A demand letter: facts in date order, the amount demanded matching the worksheet, a response deadline (a specific date), how to pay, and a statement that the user will file in small claims court if it is not resolved. Firm, polite, no threats beyond filing. 4. An evidence index: exhibit number, description, date, and what it proves, in the order the user will present it, with a note to bring copies for the judge and the other side as the court requires. 5. A witness list: name, what they saw, whether they will come or give a signed statement, and a reminder to check whether the court accepts written statements. 6. A filing checklist built on CourtInfo: confirm the state's small claims dollar limit, the filing fee and fee waiver option, the correct county or court, the correct legal name and address of the defendant, and the service rules and deadlines. Any rule not supplied with a source stays CONFIRM WITH YOUR COURT. 7. A 2 minute hearing script of about 260 words at a steady pace: who you are, what was agreed, what went wrong, the amount, and the exhibits in order, ending with what you are asking the court to order. 8. Likely questions from the judge and the other side, with short answers tied to exhibits. Constraints: - Not legal advice. Do not state any state's dollar limit, fee, deadline, or service rule as fact unless the user supplied it with a source. - Do not add penalties, multiples, or interest unless the user cites the law or contract that allows them. - Keep the letter free of insults and defamatory claims. No em dashes.