Chatbot analytics — HIPAA-minded conversation metrics, token tracking, and dashboards
Implement AI chatbot analytics with HIPAA-compliant discipline — 13 core metrics (sessions, engagement, tokens, fallback/crisis rates), metadata-only tracking, SQL schema, alert configs, and dashboard aggregations
- What
- Implement AI chatbot analytics with HIPAA-compliant discipline — 13 core metrics (sessions, engagement, tokens, fallback/crisis rates), metadata-only tracking, SQL schema, alert configs, and dashboard aggregations
- Cost
- Free
- Needs
- a chatbot/AI chat codebase plus a database — the skill is an implementation guide the agent follows, not software
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @curiositech's chatbot-analytics skill: an implementation guide for AI chatbot analytics built around 13 industry-standard metrics (total sessions, messages per session, session duration, engagement, completion, abandonment, response time, token usage, error rate, fallback rate, topic categories, sentiment trend, crisis triggers), with TypeScript tracking patterns for conversation start/exchange/end, metadata-derived category detection (categories derived from AI-response flags, never from content), aggregate SQL queries for session stats, token costs, and category breakdown, alert configurations for crisis/error/abandonment spikes, a conversation_analytics table schema with indexes, and analytics tests. Its signature angle: HIPAA-minded tracking — conversation metadata only, with an explicit list of what must NEVER be stored (message content, user queries, AI responses, health-revealing specifics). Honest caveats: it's engineering guidance, not legal or HIPAA certification — validate compliance yourself; the examples assume a Drizzle-style ORM and a specific schema. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Chatbot analytics is a free Muse skill from @curiositech that guides AI chatbot analytics around 13 core metrics, from sessions and engagement to token usage and fallback and crisis rates. It uses TypeScript tracking patterns, metadata-only category detection, SQL aggregations and alert configurations, never storing message content, queries, responses or health-revealing specifics.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 6713fc7Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a chatbot/AI chat codebase plus a database — the skill is an implementation guide the agent follows, not software Install "Chatbot analytics — HIPAA-minded conversation metrics, token tracking, and dashboards" for me. It gives my agent @curiositech's implementation guide: track 13 chatbot metrics (sessions, messages/session, duration, engagement, completion, abandonment, response time, token usage, error/fallback rates, categories, sentiment, crisis triggers) with TypeScript tracking patterns for conversation start/exchange/end, derive categories from metadata flags only (never content), run aggregate SQL for session stats/token costs/category breakdown, configure alerts for crisis/error/abandonment spikes, apply the conversation_analytics schema, and keep tracking HIPAA-minded (metadata only — never store message content, queries, responses, or health-revealing specifics). MIT-licensed. Repository: https://raw.githubusercontent.com/curiositech/some_claude_skills/6713fc7a6451c8dee5903b98cd2063ff4cbf7317/.claude/skills/chatbot-analytics/SKILL.md Pinned version: install the code at commit 6713fc7a6451c8dee5903b98cd2063ff4cbf7317 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "chatbot-analytics". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. wire the tracking functions into my chat backend and create the conversation_analytics table; remember this is guidance, not HIPAA certification). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 6713fc7 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.