agentleFS
Sign inStart free
Goodeye-LabsGoodeye-Labs/truesight-mcp-skills/skills/bootstrap-template-evaluation/SKILL.md

bootstrap-template-evaluation

Skill7 starsChanged 8 months agoMITView on GitHub

Fastest route to a deployed live evaluation using a pre-built Truesight template. Use when the user wants a quick start without building judgment configs from scratch.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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 when a pre-built template likely covers the target use case.

    line 8
  2. Very specific:

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

    line 13
  3. Distinctive:

    If template choice is ambiguous, ask one question at a time using the structured question tool (loaded per the HARD-GATE above).

    line 16
  4. Distinctive:

    Ask one question per message.

    line 28
  5. Distinctive:

    Use the structured question tool for every question.

    line 29
  6. Distinctive:

    Ask one follow-up only when needed.

    line 30
  7. Very specific:

    Run run_eval with representative inputs.

    line 44
  8. Very specific:

    If no template fits, hand off to create-evaluation.

    line 52
  9. Distinctive:

    Do not skip verification after deployment.

    line 53

≈ “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

Bootstrap Template Evaluation

Use this skill when a pre-built template likely covers the target use case.

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>

If template choice is ambiguous, ask one question at a time using the structured question tool (loaded per the HARD-GATE above).

Example question structure:

Which template family best matches your goal?
A) AI writing detection
B) Code quality
C) Unsure, list all templates first

Rules:

  • Ask one question per message.
  • Use the structured question tool for every question. Structure each with a short header, 2-4 options with labels and descriptions, and place the recommended option first. Do not add "(Recommended)" or similar annotations to option labels.
  • Ask one follow-up only when needed.

Workflow

  1. Discover templates:
    • Call list_templates.
  2. Select template:
    • Match use case to template slug.
  3. Provision private dataset:
    • Call provision_template(slug).
  4. Deploy live evaluation:
    • Call create_and_deploy_evaluation(dataset_id).
    • Capture api_key immediately because it is returned only once.
  5. Verify:
    • Run run_eval with representative inputs.
  6. Return deployment artifacts:
    • dataset_id
    • live_evaluation_id
    • verification result

Guardrails

  • If no template fits, hand off to create-evaluation.
  • Do not skip verification after deployment.

Scopes reference

  • list_templates requires datasets:read
  • provision_template requires datasets:write
  • create_and_deploy_evaluation requires evaluations:write, live-evaluations:write
  • run_eval requires live-evaluations:execute

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