How to Write a Strava Activity Description from Workout Facts
Activity posts invent PRs. Distance and feel only from Facts.
The matching generator is the Strava Activity Description from Workout Facts (No Invented Paces) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Tag each Facts line title-ok or refuse
Write a Strava activity title and description from pasted workout facts only. Never invent paces, elevation, HR zones, or unlisted gear. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Workout facts (type, distance/time if known, route notes, feel): [Facts]
Title style I lock (short|playful|plain or NONE): [Style]
Pace or splits I may print (or NONE): [Pace]
Elevation I may print (or NONE): [Elev]
Gear I may name (exact list or NONE): [Gear]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Max sentences in description: [Max]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Leave pace blank when Pace is NONE
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: Facts items, Style status, Pace status, Elev status, Gear status, Lang, Max. Forbidden: invented paces, elevation, HR, gear.
- Fact map: each Facts line tagged title-ok / body-ok / refuse.
- Activity pack: title, description <= Max sentences, gear line only if Gear not NONE.
- Provenance: each claim mapped to a Facts or Pace/Elev/Gear field.
- Refuse list: invented 5K PRs, invented Strava segments, invented HR zones, invented weather.
- Diff notes: Banned/Never cuts. Caption-hashtag piles moved to refuse.
- Metric note: if Pace or Elev NONE write those metrics NOT IN INPUTS.
- Compliance pass: Banned/Never hits. Sentence count vs Max. Gaps list of five. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Refuse invented segments and weather numbers
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Strava copy from Facts only. Not a training plan and not a social caption engine.
- Never invent paces, elevation, HR zones, or unlisted gear.
- Stay at or under Max description sentences.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Print sentence count against the max
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (strava activity description, no invented paces, workout facts only) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.