agentleFS
Postpartum-genushyacinthus29Postpartum-genushyacinthus29/dotnet-skills/skills/dotnet-mcaf-ml-ai-delivery/SKILL.md

dotnet-mcaf-ml-ai-delivery

Skill13 starsChanged 8 months agoMITView on GitHub

Apply MCAF ML/AI delivery guidance for data exploration, feasibility, experimentation, testing, responsible AI, and operating ML systems. Use when the repo includes model training, inference, data science workflows, or ML-specific delivery planning.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    leave reusable project context so future tasks are faster and safer

    line 21
  2. Distinctive:

    Read the nearest AGENTS.md and confirm scope and constraints.

    line 36
  3. Very specific:

    Run this skill's Workflow through the Ralph Loop until outcomes are acceptable.

    line 37
  4. Distinctive:

    Keep experimentation traceable and testable.

    line 43
  5. Distinctive:

    Treat responsible AI, data quality, and ML-specific verification as first-class requirements.

    line 44
  6. Distinctive:

    Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.

    line 61
  7. Distinctive:

    write a detailed execution plan from the chosen direction

    line 69
  8. Distinctive:

    Update the plan after each iteration.

    line 74
  9. Very specific:

    If a dependency is missing, bootstrap it or return status: not_applicable with explicit reason and fallback path.

    line 76

≈ “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

MCAF: ML/AI Delivery

Trigger On

  • the repo contains model training, inference, experimentation, or data-science workflow
  • ML work needs explicit process, testing, or responsible-AI guidance
  • delivery discussion is mixing product, data, and model concerns

Value

  • produce a concrete project delta: code, docs, config, tests, CI, or review artifact
  • reduce ambiguity through explicit planning, verification, and final validation skills
  • leave reusable project context so future tasks are faster and safer

Do Not Use For

  • generic software delivery with no ML or data-science component
  • loading all ML references when only one stage is active

Inputs

  • the current ML stage: framing, data exploration, experimentation, training, inference, or operations
  • product assumptions, data assumptions, and model assumptions
  • current verification and responsible-AI expectations

Quick Start

  1. Read the nearest AGENTS.md and confirm scope and constraints.
  2. Run this skill's Workflow through the Ralph Loop until outcomes are acceptable.
  3. Return the Required Result Format with concrete artifacts and verification evidence.

Workflow

  1. Separate product assumptions, data assumptions, and model assumptions.
  2. Keep experimentation traceable and testable.
  3. Treat responsible AI, data quality, and ML-specific verification as first-class requirements.
  4. Load only the references that match the current ML stage.

Deliver

  • clearer ML/AI delivery guidance
  • better links between data, experimentation, verification, and responsible AI
  • docs that match how the ML system is built and validated

Validate

  • the active ML stage is explicit
  • experimentation and evaluation are traceable
  • responsible-AI and data-quality requirements are not bolted on at the end

Ralph Loop

Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.

  1. Brainstorm first (mandatory):
    • analyze current state
    • define the problem, target outcome, constraints, and risks
    • generate options and think through trade-offs before committing
    • capture the recommended direction and open questions
  2. Plan second (mandatory):
    • write a detailed execution plan from the chosen direction
    • list final validation skills to run at the end, with order and reason
  3. Execute one planned step and produce a concrete delta.
  4. Review the result and capture findings with actionable next fixes.
  5. Apply fixes in small batches and rerun the relevant checks or review steps.
  6. Update the plan after each iteration.
  7. Repeat until outcomes are acceptable or only explicit exceptions remain.
  8. If a dependency is missing, bootstrap it or return status: not_applicable with explicit reason and fallback path.

Required Result Format

  • status: complete | clean | improved | configured | not_applicable | blocked
  • plan: concise plan and current iteration step
  • actions_taken: concrete changes made
  • validation_skills: final skills run, or skipped with reasons
  • verification: commands, checks, or review evidence summary
  • remaining: top unresolved items or none

For setup-only requests with no execution, return status: configured and exact next commands.

Load References

  • read references/ml-ai-projects.md first
  • open references/data-exploration.md, references/feasibility-studies.md, references/ml-fundamentals-checklist.md, references/model-experimentation.md, references/testing-data-science-and-mlops-code.md, references/responsible-ai.md, or references/ml-model-checklist.md only when that stage is active

Example Requests

  • "Define the delivery workflow for this ML feature."
  • "We need responsible-AI and testing guidance for this model."
  • "Separate product, data, and model decisions in our docs."

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.