feedback-tools-platformfeedback-tools-platform/feedback-tools-mcp/skills/create-survey/SKILL.md

create-survey

Skill0 starsChanged 21 days agoMITView on GitHub

Create and set up a feedback.tools survey. Use when the user wants to start collecting feedback, add a CSAT, NPS, CES or open-text survey to their site or app, or change where and when an existing survey shows.

In this repository2 other files it gives its agents.
- bug-reportsSkill
- feedback-digestSkill

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Ask what the user wants to learn, then suggest one type:
line 12
Very specific:
Call create_survey with survey_type, title (internal name for the dashboard) and question, plus the labels and follow-up.
line 36
Very specific:
Ask where and when the survey should appear, then call update_survey with:
line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Create a survey

Help the user pick the right survey, then create and configure it with create_survey and update_survey.

1. Choose the type

Ask what the user wants to learn, then suggest one type:

Goal	Type	Scale
Was a specific step good (checkout, onboarding, support reply)	`csat_5`	1-5, stars, emoji or numbers
Quick yes/no reaction	`csat_2`	thumbs or emoji
How hard was it to get something done	`ces_7`	1-7 numbers
Would they recommend the product overall	`nps_10`	0-10 numbers
Open feedback, no score	`general`	none

The type cannot be changed after creation.

2. Write the question

One question, about one thing, max 127 characters.
Name the moment: "How easy was it to complete your order?" works better than "How do you like our site?".
For NPS keep the standard wording: "How likely are you to recommend <product> to a friend or colleague?"
Set min_label and max_label for csat_5, ces_7 and nps_10 (for example "Not likely" / "Very likely").
Suggest a follow-up text_question such as "What is the main reason for your score?". Comments are what AI themes are built from.

Show the user the type, question, labels and follow-up before creating.

3. Create

Call create_survey with survey_type, title (internal name for the dashboard) and question, plus the labels and follow-up. Everything else gets dashboard defaults.

The result contains notice_for_user with the trial end date and the survey link: pass it on to the user. Do not call create_survey twice for the same request; check list_surveys first if unsure whether it was created.

4. Targeting (optional)

Ask where and when the survey should appear, then call update_survey with:

show_on_pages to limit it to certain URLs (for example only the order confirmation page);
trigger to show it immediately, after a delay or after scrolling;
allowed_countries / disallowed_countries for country rules;
translations for other languages;
responses_limit to cap the number of responses.

5. Install

The widget is installed on the site or in the app with the survey's api_key from the result. Point the user to the survey link from notice_for_user: the dashboard shows the install snippet.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free