GTDataworks

Convert a repeatable workflow into a reusable agent skill or staged skillchain with contracts and a build receipt.

Turn loose prompts into structured records with variables, contracts, and eval cases for Cursor, Claude, and Promptfoo-style gates.

Five compact operator skills for artifact intake, zip preflight, test planning, session handoff, and MCP tool-candidate inspection.

Run a buyer-readiness check before you publish an AI agent skill. PASS/WARN/FAIL on structure, claims, secrets, and listing clarity.

Generate a source-safe repository audit and repair handoff without mutating your code. Secret scan, risk register, Map of Change, Codex/GPT prompts.

A mechanical evaluation engine for testing specific agent failure patterns using strict JSON schemas and Python.

AI Agent Testing and Evaluation Bundle

by GTDataworks

$19

Five skills to compare agent runs, turn failures into regression tests, build eval datasets, gate provenance, and inspect untrusted content.

Agent Tool Trace: Debug Receipts

by GTDataworks

$7

Capture tool-trace receipts, label failures, and emit replay prompts so you can debug an agent run after it finishes.

MCP Client Evidence Gate for Codex and Qwen

by GTDataworks

$7/mo

Compatibility evidence for MCP servers against Codex CLI and Qwen: discovery receipts, report.md, and receipt.json.