query-translator

query-translator is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 51 tokens per session (1,491 once invoked), scanned A, original, MIT.

A FullStory query translator that turns vague product questions into measurable questions. FullStory is a service that records user sessions and interaction data for product analysis.

In plain words
What is it for?
Use it to formulate FullStory queries about engagement, ease of use, feature adoption, redesign results, or similar product questions.
Why use it?
It helps when you know what you want to learn but do not know which user behavior or metric can answer it. It replaces broad questions with concrete measures such as usage or task completion.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fullstory-claude-plugin plugin — 46 skills, 3 agents, 1 MCP server shipped together

Good fit Use it to formulate FullStory queries about engagement, ease of use, feature adoption, redesign results, or similar product questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/query-translator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add reatlat/fullstory-claude-plugin --skill query-translator
Clone the repo
git clone --depth 1 https://github.com/reatlat/fullstory-claude-plugin

Made for: Claude Code.

Or install fullstory-claude-plugin, the plugin that ships this one along with the rest of its 46 skills, 3 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for query-translator

README.md
[![agentmods](https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/query-translator/github.svg)](https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/query-translator)
Your own site
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/query-translator"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/query-translator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for query-translator

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/query-translator"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/query-translator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01491
Opus 5 $0.00026 $0.00745
Sonnet 5 $0.00010 $0.00298
Haiku 4.5 $0.00005 $0.00149

Measured 10d ago against content hash 01f08ad4ee10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

query-translator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/query-translator/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Query Translator

Help users who know what they want to ask but not how to phrase it for Fullstory. Turn "I want to know if people like the new feature" into measurable, query-able questions.

When to Use

  • "I want to know if users are happy with the redesign — how do I ask that?"
  • "What's the right way to measure engagement?"
  • "I know what I want to learn but I don't know what to ask Fullstory"
  • "Help me formulate a query"
  • "Is there a way to measure X?"

The query-translator is invoked when the user's question is vague, abstract, or not directly answerable with Fullstory tools. It helps bridge the gap between "what I want to know" and "what Fullstory can measure."

Mental Model

Most business questions are too vague to query directly. The skill of query translation is finding a measurable proxy:

Vague Question Measurable Proxy
"Do users like the new feature?" Adoption rate, repeat usage, rage clicks on the feature
"Is our product easy to use?" Task completion rate, rage clicks, dead clicks, time-on-task
"Are users engaged?" Session frequency, pages per session, features used, return rate
"Is the redesign better?" Before/after: conversion, errors, rage clicks, scroll depth
"Are we losing users?" Churn rate, at-risk user count, declining session frequency
"Is our support experience good?" Sessions visiting help pages, search usage, rage clicks on help content

Workflow

Step 1: Understand the real question

When the user asks something vague, dig deeper:

User: "I want to know if users like the new dashboard." You: "That's a great question. Let me break that down. 'Like' could mean a few different things. Are you more interested in:

  • Whether they're actually using it? (adoption metrics)
  • Whether they're coming back to it? (retention metrics)
  • Whether they're struggling with it? (frustration metrics)
  • How it compares to the old dashboard? (comparison metrics)"

Read the full file on GitHub · 128 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 128 lines · 51 tokens per session scan A 01f08ad4ee10

Subscribe to this mod's changes

query-translator is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 28d ago), licensed MIT. It adds 51 tokens to every session and 1,491 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.