Truesight Workflows

Truesight Workflows

Use this skill as the routing entrypoint across all Truesight MCP skills.

Role and scope

This skill is a router. It decides intent and routes to exactly one skill path.

Do not execute deep workflow steps here unless the user already asked for a very specific action and no further routing is needed.

Routing map

• Build custom live eval from scratch -> create-evaluation
• Evaluate one or more traces with an existing live eval -> evaluate-trace
• Analyze failure modes in dataset traces -> error-analysis
• Judge flagged items and add labeled outputs back to dataset -> review-and-promote-traces
• Start quickly from pre-built template -> bootstrap-template-evaluation
• Audit current eval setup and maturity -> eval-audit
• Build custom review web interface -> build-review-interface
• Generate synthetic test data for evaluation -> generate-synthetic-data

Interactive Q&A protocol (mandatory)

BEFORE the first scoping question, search for a structured question tool (e.g., AskUserQuestion or similar interactive widget) and load it. Use that tool for EVERY scoping question. Fall back to plain-text lettered options ONLY if no such tool exists in the environment.

When user intent is unclear, ask one question at a time using the structured question tool (loaded per the HARD-GATE above). Structure each with a short header, options with labels and descriptions, and place the recommended option first. Do not add "(Recommended)" or similar annotations to option labels.

Question format:

Which workflow do you want to run first?
A) Evaluate traces with an existing live eval
B) Run error analysis on a dataset
C) Review and promote flagged traces
D) Bootstrap from a template
E) Create a new evaluation from scratch
F) Audit my eval setup
G) Build a custom review interface
H) Generate synthetic test data

Rules:

• Ask exactly one routing question per message.
• Use one follow-up question only if the answer is still ambiguous.
• After routing is clear, hand off immediately to the target skill.

Guardrails

• If user asks for create-evaluation, do not decompose it into smaller skills.
• Keep guidance scoped to currently available Truesight MCP tools.
• If user asks for functionality outside current MCP capabilities, state the gap clearly and offer the closest supported workflow.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: Goodeye-Labs
• Source: Goodeye-Labs/truesight-mcp-skills
• License: MIT
• Homepage: https://truesight.goodeyelabs.com/docs/mcp-integration

Install and usage instructions live in the source repository linked above.