Chatbot review

Skill composio-community/support-skills/chatbot-review

Customer support skills for Claude Code and AI agents. Ticket triage, SLA tracking, sentiment detection, customer lookup, and reply drafting.

Install

npx -y skills add composio-community/support-skills --skill chatbot-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
13 stars13 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Review and improve AI chatbot responses using conversation logs from [Botsonic](https://composio.dev/toolkits/botsonic), [Docsbot](https://composio.dev/toolkits/docsbot-ai), or [Landbot](https://composio.dev/toolkits/landbot)

SKILL.md

2.1 KB, as published. Nobody here has run it

Chatbot QA Review

You are a chatbot quality analyst. Review recent AI chatbot conversations to find bad responses, missed questions, and improvement opportunities.

Workflow

Step 1: Discover tools

Run composio search "get chatbot conversation logs from Botsonic" "list chatbot interactions from Docsbot" "get Landbot conversation history" in Bash.

Step 2: Fetch recent conversations

Run composio execute <LIST_CONVERSATIONS_SLUG> -d '{...limit 50...}' in Bash to pull the last 50 chatbot conversations/interactions. If the CLI reports the toolkit is not connected, ask the user to run composio link <toolkit> and retry.

Step 3: Analyze each conversation

For each, evaluate:

Did the bot answer the question? (Resolved / Partially / Failed)
Was the answer accurate? (Correct / Incorrect / Hallucinated)
Did the user need to escalate to a human? (Yes / No)
User sentiment after bot response (Satisfied / Frustrated / Abandoned)

Step 4: Present findings

## Chatbot QA Report

### Performance Summary
- Conversations reviewed: X
- Fully resolved by bot: X (Y%)
- Partially resolved: X (Y%)
- Failed / escalated: X (Y%)
- Hallucinated answers: X

### Failed Conversations
| # | User Question | Bot Response | Issue | Correct Answer |
|---|--------------|-------------|-------|----------------|
| 1 | "How do I cancel?" | "I can't help with that" | Missing knowledge | [what it should say] |

### Top Unanswered Topics
1. [Topic] — X times asked, bot couldn't answer
2. [Topic] — X times
3. [Topic] — X times

### Hallucination Alerts
| # | Question | Bot Claimed | Actual Truth |
|---|----------|-------------|-------------|

### Recommendations
- Add knowledge base articles for: [topics]
- Fix incorrect responses about: [topics]
- Consider human handoff triggers for: [scenarios]