From vthink-agent-toolkit
Generate a privacy-safe version of the current technical problem, safe to paste into external tools. Strips company names, project names, class names, URLs, and internal terminology while preserving the technical substance. Use when you need to search externally without leaking proprietary details.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vthink-agent-toolkit:anonymize-promptThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate a privacy-safe, anonymized prompt that the user can paste into external search engines and AI chatbots to get help — without exposing ANY proprietary details.
Generate a privacy-safe, anonymized prompt that the user can paste into external search engines and AI chatbots to get help — without exposing ANY proprietary details.
From the conversation context and user's argument, identify:
Apply ALL of the following replacements systematically:
| Category | Example Before | Example After |
|---|---|---|
| Company/product names | AcmeCorp, my-service | "our application", "the project" |
| Class names | OrderManager, PaymentTracker | DataManager, ProcessTracker |
| Variable/method names | buildOrderInstance() | buildDataStructure() |
| Package paths | com.acme.app.apiImpl | com.example.app.impl |
| Internal URLs | localhost:8080/internal/api/v0 | localhost:8080/app/api/v1 |
| Database/table names | acme_metadata, order_definitions | app_metadata, entity_definitions |
| Internal jargon | proprietary domain terms | describe functionally in plain language |
| File paths | /src/main/java/com/acme/... | /src/main/java/com/example/... |
| Config keys | acme.security.* | app.security.* |
| Ticket IDs | PROJ-1931 | remove entirely |
| Branch names | PROJ-1931-add-offline-access | remove entirely |
| Colleague names | any person names | remove entirely |
| Docker/service names | my-api, acme-web | "the api service", "the web service" |
Keep ALL of the following (they are public knowledge):
IMPORTANT: Only describe the problem — never include solutions, fixes, or workarounds. The goal is to get unbiased answers from external engines. Including a fix will bias the response toward confirming that fix rather than exploring all options.
Produce the anonymized prompt in this format:
## Context
[1-2 sentences: what the app is, what tech stack, what area you're working in — all anonymized]
## Problem
[Clear description of the technical issue — specific enough to be searchable]
## What I've Tried
[List of approaches attempted, if any — anonymized]
## Error / Symptoms
[Any error messages, stack traces, or unexpected behavior — anonymized]
## Question
[Open-ended question asking for solutions — do NOT suggest any answers]
Before outputting, verify:
Present the anonymized prompt inside a fenced code block so the user can easily copy-paste it.
Add a brief note above the code block: "Here's your anonymized prompt — safe to paste into external search engines and AI chatbots:"
If anything couldn't be fully anonymized (e.g., a very unique architectural pattern), flag it with a warning so the user can review before pasting.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub vthinkdeveloper/vthink-agent-toolkit --plugin vthink-toolkit