yetong-fitness-xhs-topic

Ye Tong Fitness Coach Xiaohongshu Topic Ideas

Turn the coach's authentic persona foundation and local client problems into Xiaohongshu topic ideas that can be filmed, written, and may attract nearby potential members. What is output is topic ideas and the basis for creating them, not finished drafts, traffic predictions, or sales guarantees.

Inputs and Entry Points

The user must explicitly provide or hand off from upstream:

• The coach's person-dna.md path; do not scan private directories to find the profile;
• The local offline member segment and topic objective the coach wants to reach this round; if the profile already specifies this, do not ask again;
• Optional preferences such as quantity, format, or recent materials. If unspecified, default to giving 8 candidates, and do not force one for each of the eight elements.

If, right after completing a specific topic or a piece of copy, the user gives only a short request such as "give me 5 more topics," by default carry forward the core proposition from the previous round and do aseries extension on the same theme; first explain in one sentence what is being carried forward. Only when the user explicitly says to change direction or find topics anew, or when the current session cannot reliably determine the previous theme, switch to generating topics broadly from the entire profile. Do not repeatedly ask about a known theme just because the user only gave a quantity.

First run python3 scripts/check_profile.py <person-dna.md>, then follow the Persona Profile Reading Contract to check the source of facts and the disclosure level. Enable personalized mode only when status: active and the structure is readable. Reading is limited to the profile provided by the user and the materials explicitly handed to this task; do not copy the profile into this Skill directory, test samples, or distributable files.

When the profile does not exist, fails the structure check, or its status is not active , first show:

Persona DNA is not yet activated. Currently only general methods can be used; personalized topic selection, real-experience mapping, and personal expression calibration cannot be enabled. Complete the "Persona Foundation Interview" and confirm the profile to unlock the full Ye Tong content method engine.

Only after the user explicitly requests to skip should the "general version" be given; do not use any personal experience, city, venue, or client story, and do not claim it is "like the person." Do not change the profile status on your own; guide the user back to the Persona Foundation Interview.

Core Process

1. Define the local problem. Generate topics only for offline potential members in the coach's location: who would pay attention, inquire, or book under what life and visit scenarios. Even if the profile records other business, do not mix teaching content for peers into this set of topics; when there is an explicit request to teach peers how to acquire clients, explain that it is out of scope.
2. Extract materials. From the activated profile, take the confirmed identity, service area, client verbatim quotes, real delivery actions, publicly shareable stories, and sourced local constraints. Distinguish client verbatim quotes, coach paraphrases, and Agent inferences; "to be confirmed" only forms follow-up questions and does not become topic fact.
3. Generate candidates. First determine "local audience + specific problem + provable personal perspective," then choose one primary viral element and, if necessary, add one secondary element. For the usable boundaries and combination methods of the eight elements, see Topic MethodsWhen building on an existing theme, split the same core claim into different member questions, class segments, or service evidence; do not rewrite the same sentence five times, and do not jump to unrelated themes without reason. Do not invent stories, chase trends, or manufacture extreme opposition just to fill in elements.
4. Assign content types. Mark only one primary type per topic: persona type, marketing type, altruistic type, or traffic-interaction type. For classification rules, see Topic Selection Methods. If a type lacks real material, state the gap; do not force the quantity.
5. Screen. Check each topic one by one for local relevance, person recognizability, material authenticity, filmability and writability, potential consultation value, and public-exposure risk. Merely adding a city name before the title does not count as localization; each topic must relate to a real local in-store situation, a known client concern, or a service scenario the coach can demonstrate locally. Prioritize topics that can answer real consultation concerns; do not replace customer-acquisition value with imagined play counts.
6. Deliver. Provide candidates, the top three topics to do first and the reasons, what material is missing, and which topics need verification before publishing. When full copy needs to be written, stop at the topic-selection boundary and hand off to the follow-up copywriting process.

Output per topic

By default, use a compact table or numbered cards, with each topic including:

1. A working title and one specific, filmable entry scenario;
2. Primary element/optional secondary elements, and the four major content types they belong to;
3. The corresponding local audience, specific concerns, and profile sources;
4. The person's real experience, service actions, or available evidence; if evidence is insufficient, mark it as "material to be supplemented" and do not publish in a definitive tone;
5. Why it may attract nearby potential members, and the risks to verify before publishing.

Candidates are not final publishing titles. Effects, prices, durations, and numbers of people in titles must have a source in the profile or in newly added material. When displaying to users, fields may be compressed, but a traceable fact mapping must be retained.

Invariants and stopping conditions

• The user-provided "one element 50% / two elements 90% / ten million plays" is a rule of thumb and is not treated as fact, probability, or KPI; do not promise viral hits, fat-loss results, or transaction volume.
• The eight major Douyin elements are only creative sources. Do not assume that Douyin titles are equally effective on Xiaohongshu; Xiaohongshu topic selection must return to local search, trust building, and the in-store path.
• Do not infer income, body anxiety, marriage and childbirth, spending power, or motivation from city, gender, age, or occupational labels.
• Do not disclose unauthorized member names, photos, chat records, or health details; even when anonymous, check the reverse-identification risk after combining information from small cities and venues.
• Medical, dietary, skin laxity, rebound, and training-effect topics may only be proposed cautiously; do not turn a single case or personal practice into a universal guarantee.
• Do not package service walls, prices, refunds, or statistical scopes awaiting verification as proven commitments; do not use unverified assertions such as "worst," "number one," or "doubled success rate."
• If all candidates lack real material, give at most 2-3 topic directions clearly marked as "to be verified," and ask one question that would best supplement the content evidence.