agentleFS
Sign inStart free
Goodeye-LabsGoodeye-Labs/truesight-mcp-skills/skills/truesight-workflows/SKILL.md

truesight-workflows

Skill7 starsChanged 8 months agoMITView on GitHub

Orchestrator for Truesight MCP skills. Use this when the user needs help choosing the right Truesight workflow or when intent is ambiguous across LLM evaluate, error analysis, review, templates, or evaluation creation.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

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

    line 8
  2. Distinctive:

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

    line 14
  3. Very specific:

    Start quickly from pre-built template -> bootstrap-template-evaluation

    line 22
  4. Very specific:

    BEFORE the first scoping question, search for a structured question tool (e.g., AskUserQuestion or similar interactive widget) and load it.

    line 30
  5. Distinctive:

    Ask exactly one routing question per message.

    line 50
  6. Distinctive:

    Use one follow-up question only if the answer is still ambiguous.

    line 51
  7. Distinctive:

    After routing is clear, hand off immediately to the target skill.

    line 52
  8. Very specific:

    If user asks for create-evaluation, do not decompose it into smaller skills.

    line 56
  9. Distinctive:

    Keep guidance scoped to currently available Truesight MCP tools.

    line 57
  10. Distinctive:

    If user asks for functionality outside current MCP capabilities, state the gap clearly and offer the closest supported workflow.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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)

<HARD-GATE> 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. </HARD-GATE>

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free