Treatment Demand Radar

What it does

When your agent uses it

• Tasks that involve On-page SEO

Example prompts

• “med spa content ideas,”
• “which treatments are trending,”
• “treatment demand,”
• “/treatment-demand-radar”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Take the treatment menu. Start from the treatments the clinic offers (botox, microneedling, laser hair removal, lip filler, …) and its…
2. 2Pull search demand. For each treatment, expand queries with seo/keywords/ideas + seo/keywords/related, score them with…
3. 3Check AI-answer prompts. Run the "best/near-me" prompts through geo/serp; note whether the clinic is cited (is_target), who is, and which…
4. 4Read the social signal. Use tiktok/search + tiktok/search/hashtags to find each treatment's hashtag, then tiktok/hashtags/{id}/videos for…
5. 5Score and rank each treatment with the rubric below, then turn the top treatments into a plan: content topics from the real patient…

What it can do on your machine

Read from SKILL.md and the folder at commit fb53247. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Treatment Demand Radar loads about 2.1k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 835 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~112

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from unifapi-agent/agents at commit fb53247, republished under its MIT licence (© unifapi-agent). 835 words, ~2,148 tokens.

name

treatment-demand-radar

description

When a med spa or aesthetics clinic wants to know which treatments are in demand locally and what content or offers to prioritize. Also use on "med spa content ideas," "which treatments are trending," "treatment demand," "what should we promote," "med spa SEO content," "is [treatment] trending on TikTok," or "are we showing up in AI answers for treatments." Reads public data only — marketing research, not medical advice.

license

MIT

metadata.author

UnifAPI

metadata.version

1.0.0

score = (0.45 × search) + (0.25 × social) + (0.30 × winnability), each 0–100

# Treatment Demand Radar — [Clinic], [City] — [date]

| Score | Treatment     | Search (vol/trend) | Social                                              | Winnability | Signal / proving source                         |
| ----- | ------------- | ------------------ | --------------------------------------------------- | ----------- | ----------------------------------------------- |
| 78    | Lip filler    | ~720/mo, rising    | rising (TikTok #lipfiller 2.1B, local clip 90k/3wk) | mid         | clinic on page two; geo/serp prompt unclaimed   |
| 61    | Microneedling | ~480/mo, steady    | rising                                              | high        | "best microneedling [city]" has no cited winner |
| 34    | Botox         | high, flat         | flat                                                | low         | dominant competitor owns search + local pack    |

## Plan — top treatments

For each high-scoring treatment:

- **2–3 content topics** from the verbatim patient questions (cost, pain, downtime, candidacy, before/after, vs-alternative), each with its target query.
- **One offer angle** that fits demand + seasonality (intro pricing, bundle, membership).
- **AI-answer prompts** the clinic should be cited for but isn't (from geo/serp).

## Discarded

One line per treatment checked and set aside, with why.

© unifapi-agent, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/med-spa-marketing/treatment-demand-radar of unifapi-agent/agents.

• SKILL.md
• README.md

Open the folder on GitHubat commit fb53247