generate-synthetic-data

generate-synthetic-data is a skill for Claude Code from Goodeye-Labs/truesight-mcp-skills. It costs 43 tokens per session (1,575 once invoked), scanned A, original, MIT.

A workflow for creating artificial test examples for evaluations of AI systems. It varies chosen dimensions, such as request types or system behaviours, to produce synthetic traces when real examples are missing or limited.

In plain words
What is it for?
It is for generating synthetic traces and test cases for chatbots, retrieval systems, tool-using agents, support bots, and other AI pipelines.
Why use it?
It gives an evaluation something to test when there are not enough production traces. Targeted variation can also expand a small real dataset with additional cases.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the truesight plugin — 9 skills, 1 MCP server shipped together

Good fit It is for generating synthetic traces and test cases for chatbots, retrieval systems, tool-using agents, support bots, and other AI pipelines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goodeye-labs/truesight-mcp-skills/generate-synthetic-data
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 Goodeye-Labs/truesight-mcp-skills --skill generate-synthetic-data
Clone the repo
git clone --depth 1 https://github.com/Goodeye-Labs/truesight-mcp-skills

Made for: Claude Code.

Or install truesight, the plugin that ships this one along with the rest of its 9 skills, 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 generate-synthetic-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/goodeye-labs/truesight-mcp-skills/generate-synthetic-data/github.svg)](https://agentmods.dev/skills/goodeye-labs/truesight-mcp-skills/generate-synthetic-data)
Your own site
<a href="https://agentmods.dev/skills/goodeye-labs/truesight-mcp-skills/generate-synthetic-data"><img src="https://agentmods.dev/badge/skills/goodeye-labs/truesight-mcp-skills/generate-synthetic-data/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 generate-synthetic-data

Your own site · 80×15
<a href="https://agentmods.dev/skills/goodeye-labs/truesight-mcp-skills/generate-synthetic-data"><img src="https://agentmods.dev/badge/skills/goodeye-labs/truesight-mcp-skills/generate-synthetic-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,575 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.
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 $0.00043 $0.01575
Opus 5 $0.00022 $0.00788
Sonnet 5 $0.00009 $0.00315
Haiku 4.5 $0.00004 $0.00158

Measured 12d ago against content hash 618a2bfe9b0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

generate-synthetic-data 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 12d 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/generate-synthetic-data/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Synthetic Data

Generate realistic synthetic traces for LLM evaluation datasets using dimension-based variation.

When to use

  • User needs test data for an evaluation but has no production traces.
  • create-evaluation delegates here when real traces are unavailable.
  • User wants to augment sparse real data with targeted synthetic examples.

Scoping protocol

Ask these five questions. Skip any already answered in the conversation (e.g., if create-evaluation already established the system type, do not re-ask).

  1. System type. What kind of AI system produces the traces?
    • Simple RAG, tool-calling agent, multi-turn chat, support bot, classification pipeline, other
  2. Trace structure. What columns does each trace contain?
    • Offer common patterns based on system type:
      • Simple RAG: user_query, retrieved_context, response
      • Tool-calling agent: user_request, tool_calls, final_answer
      • Multi-turn chat: conversation_history, assistant_response
      • Support bot: customer_message, kb_lookup, agent_reply
    • Let the user rename, add, or remove columns
  3. Dimensions of variation. What axes should drive diversity?
    • Propose 3-5 starter dimensions based on system type and known failure modes
    • Each dimension needs 3-6 discrete values
    • Example for RAG: query complexity (simple factual, multi-hop, ambiguous, comparative), domain coverage (billing, technical support, account management), context quality (perfect match, partial match, irrelevant, missing)
  4. Dataset size. How many final traces?
    • Default recommendation: 50-100 for initial eval scoping, 200+ for statistical significance
  5. Output destination. Where should the data go?
    • Default: MCP upload when called from create-evaluation, file when standalone
    • Options: Truesight dataset (via MCP), JSONL file, CSV file, both

Read the full file on GitHub · 146 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. 12d ago First seen · 146 lines · 43 tokens per session scan A 618a2bfe9b0c

Subscribe to this mod's changes

generate-synthetic-data is a skill published in the GitHub repository Goodeye-Labs/truesight-mcp-skills (7 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,575 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

firebase-ai

Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.

evanca/flutter-ai-rules · 30 tokens

setup

Configure the Qdrant Power after installation. Use this skill for missing uvx, missing environment variables, unapproved environment variables, unavailable Qdrant tools, "Failed to connect" errors, and setup requests.

qdrant/mcp-server-qdrant · 45 tokens

standalone-python-scripts

Skill "standalone-python-scripts" from iloveitaly/llm-ide-rules, covering standalone python scripts, /// script, requires-python = ">=3.13", dependencies = [] and ///.

iloveitaly/llm-ide-rules · 9 tokens

rag-implementation

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

LuizEduPP/Rememb · 49 tokens

context-optimization

Optimize effective context capacity through compression, masking, caching, and partitioning strategies. Use when the user asks to reduce token costs, improve context efficiency, implement KV-cache optimization, or extend context-window effectiveness.

LuizEduPP/Rememb · 45 tokens