AI Blocks › Help your customers
Customer survey feedback analyst
Connect Delighted, GatherUp, Gleap, or Simplesat and choose a date range. It gathers recent feedback and groups the comments by topic. You get repeated problems, feature requests, praise, and suggested actions with counts and sample quotes.
Turn survey comments into a customer feedback report with themes, counts, quotes and next steps. Works with Delighted, GatherUp, Gleap or Simplesat.
Free · No account · MIT licence · Made by Composio · Tested · Updated 28 Oct 2026
What you get
What goes in
- A date range, such as the last 7 to 30 days
- At least one connected account: Delighted, GatherUp, Gleap or Simplesat
Before you start
- An AI that can run commands, with Composio CLI installed
- Your survey accounts linked in Composio
What comes out
- Header: The period, the sources pulled from and the total number of feedback items.
- Overall Sentiment: The share of positive, neutral and negative feedback, plus NPS and CSAT scores when the tools give them.
- Top Themes: A table of themes with count, sentiment, trend and one example quote each.
- Critical Issues: Feedback that needs quick attention, with counts and why it is serious.
- Feature Requests: Requests ranked by how often they come up, each with a sample quote.
- Wins: Positive quotes worth sharing, each with its source.
- Recommendations: Product changes, process fixes and help content gaps that follow from the top themes.
Is it for you?
Use it when
- You review customer feedback each week or month and want themes, not a pile of comments.
- You use at least one of Delighted, GatherUp, Gleap or Simplesat.
- A product or support lead asks what customers complain about most.
Skip it when
- You have one comment to answer: reply to it yourself, or ask your AI to draft a reply.
- You want to sort raw support tickets: use your help desk tool, which tracks each ticket.
- You use none of Delighted, GatherUp, Gleap or Simplesat: paste your comments into your AI and ask for themes by hand.
Fill it in
Add what this task works from, then copy the request.
- A date range, such as the last 7 to 30 days.
- At least one linked account from Delighted, GatherUp, Gleap or Simplesat.
Run it
Download the complete instructions and supporting files. Add them to Claude, ChatGPT or Gemini once, then ask for it by name in any chat. Pasting the instructions into a chat works too.
Before and after this skill
Choose the steps you need. Bring your own material when you have it.
Before
Bring the material listed under Fill it in.
After
- Support issue cause investigator
Use it if you have the audit report.
Specialists who do this
Each one uses this as one of its methods for a bigger job. Hire one for free and give it the job in your own AI.
Details
From Composio. See the original on GitHub; shared under its licence, with a plain name for this library.
What it does
Survey tools collect a lot of comments, and reading them one by one hides the pattern. This skill pulls recent feedback from the services you have linked, groups it by theme, and counts each one. You get a report with the share of positive, neutral and negative feedback, top themes with real quotes, urgent issues, ranked feature requests and suggested next steps. Every count and quote comes from your survey tools, never from your AI's guess. Composio and each survey service are separate products and may need a paid plan or API access. This is Composio's feedback-digest skill, shared under the MIT licence, with a plain name.
What goes in and out
You give it
- A date range, such as the last 7 to 30 days.
- At least one linked account from Delighted, GatherUp, Gleap or Simplesat.
You get
- A count of feedback items and the share that is positive, neutral and negative.
- A table of top themes with counts and example quotes.
- A list of urgent issues and ranked feature requests.
- Positive quotes you can share with your team.
- Suggested product, process and help content changes.
Use it when
- You review customer feedback each week or month and want themes, not a pile of comments.
- You use at least one of Delighted, GatherUp, Gleap or Simplesat.
- A product or support lead asks what customers complain about most.
- You need quotes and counts for a team meeting or a product plan.
More for Help your customers
- Customer support response writer
- Gorgias ticket priority planner
- Service outage update writer
- Zoho Desk ticket priority planner
Every help your customers skill
How the task works
- Gather recent feedback. Read feedback from the connected services for the chosen dates.
- Group common themes. Sort comments into problems, usability, pricing, support, praise, and feature requests.
- Write the report. Show theme counts, sample quotes, urgent concerns, and proposed product or help content changes.
Full instructions
- Add the downloaded folder to an AI that can read skill files and run commands.
- Install Composio CLI and link your accounts. Your AI will ask you to link any that are missing. Composio and each survey service are separate products. Check whether they need a paid plan or API access before you start.
- Ask your AI to run the Customer feedback report from survey tools and give it a date range.
- Check the theme counts and quotes against a few raw comments.
- Copy the Recommendations into your product backlog or team notes. The skill sends nothing and changes no accounts.
Full instruction file
Customer Feedback Digest
You are a voice-of-customer analyst. Aggregate feedback from multiple platforms, identify themes, and surface actionable insights.
What you need: the Composio CLI, and at least one linked account from Delighted, GatherUp, Gleap or Simplesat. Composio and each survey service are separate products. They may need a paid plan or API access, so check before you start.
When not to use: to reply to one comment, write the reply yourself. To sort raw support tickets, use your help desk tool. If you use none of the four services, paste your comments into your AI and ask for themes by hand.
Never invent feedback. Every count, score and quote in the report must come from what the tools returned.
Before you start
Use the material below to do this job. If facts or tool access are missing, explain what you can finish and what must wait.
What you need (use your own material or the linked skill):
- Your question (yours): the decision or problem, and what a good outcome looks like.
- A tool connection (yours): an AI connected to an outside tool or service, such as an MCP server.
How to start:
- Look first. Use what they've already attached, pasted or put in their about-me note. In a coding assistant with file access, look in the project too for these by name.
- Check what's missing. Look for your question, a tool connection. They can attach files, paste the details, or share a file path your assistant can read. Ask only for missing facts that change the result. If they ask you to start with what they have, complete the parts you can and mark the gaps.
- Do the job. Follow the skill below with the facts and tools you have. Mark each gap with
MISSING:where it belongs and never invent a fact to fill it.
Tools that do this best:
- Delighted, GatherUp, Gleap, or Simplesat: Live lookups need Composio CLI access and connected accounts for these services.
Workflow
Step 1: Discover tools
Run composio search "get customer feedback and survey responses from Delighted" "get customer reviews from GatherUp" "get bug reports and feedback from Gleap" "get CSAT survey responses from Simplesat" in Bash.
Step 2: Pull feedback
Fetch recent feedback from all connected platforms by running composio execute <FEEDBACK_SLUG> -d '{...date range 7-30 days...}' in Bash as parallel calls. For each connected service, copy its tool slug from the Step 1 search results and put it where <FEEDBACK_SLUG> is, with the date range for the last 7 to 30 days in the -d data (or use composio execute --parallel <SLUG_A> -d '{...}' <SLUG_B> -d '{...}'). If the CLI reports a toolkit isn't connected, ask the user to run composio link <toolkit> and retry.
Step 3: Analyze and theme
Group all feedback by theme using semantic analysis:
- Product issues (bugs, missing features)
- UX/usability complaints
- Pricing/billing feedback
- Praise/positive signals
- Support experience feedback
- Feature requests
Step 4: Present digest
For the Trend column, compare each theme's count with the equal-length period just before the chosen range. Write n/a when no earlier data was pulled. Never guess a trend.
## Customer Feedback Digest
**Period:** [date range]
**Sources:** [platforms pulled from]
**Total feedback items:** X
### Overall Sentiment
- Positive: X% | Neutral: X% | Negative: X%
- NPS: [score if available]
- CSAT: [score if available]
### Top Themes
| # | Theme | Count | Sentiment | Trend | Example |
|---|-------|-------|-----------|-------|---------|
| 1 | [theme] | X | Negative | Growing | "[quote]" |
| 2 | [theme] | X | Mixed | Stable | "[quote]" |
### Critical Issues
Feedback that needs immediate attention:
- [Issue with count and severity reasoning]
### Feature Requests (ranked by frequency)
| Request | Mentions | Sample Quote |
|---------|----------|-------------|
### Wins
Positive feedback worth celebrating:
- "[quote]" — [source]
### Recommendations
- [Product changes to address top negative themes]
- [Process improvements]
- [Knowledge base gaps to fill]
After this
When you've handed it back, suggest what they could do next in one short question. It's a suggestion: if they're done, that's fine. Offer these, and say they can type their own:
- The Support issue cause investigator. It takes the audit report. If they pick one and that skill is added here, carry straight on with what you just made. If not, give the link and say what to bring.