Individual skill

ml-system-design-review

Use when reviewing ML system design docs, ML/AI project repos, design-doc PRs, RAG/LLM/foundation-model architectures, agentic AI workflows, or production ML readiness. Applies the ML System Design framework by Kravchenko and Babushkin to grade designs, compare docs with code, find critical gaps and low-hanging fruit, and give specific non-cringy praise.

skills/ml-system-design-review/SKILL.md

Read pinned source

Source commit 8dd0d88852fe7445e9d2627c59124f0f161040c1

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: Yes
Skill scan complete: Yes
Observed behavior: Instructions only
Last checked: Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

Claude Code

Destination .claude/skills/ml-system-design-review

(
  set -euo pipefail
  destination='./.claude/skills/ml-system-design-review'
  if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi
  work=$(mktemp -d)
  trap 'rm -rf -- "$work"' EXIT
  git clone --filter=blob:none --no-checkout -- 'https://github.com/ML-SystemDesign/MLSystemDesign.git' "$work/repo"
  git -C "$work/repo" checkout --detach 8dd0d88852fe7445e9d2627c59124f0f161040c1
  git -C "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ml-system-design-review' > "$work/skill.tar"
  mkdir -p -- './.claude/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

Codex

Destination .agents/skills/ml-system-design-review

(
  set -euo pipefail
  destination='./.agents/skills/ml-system-design-review'
  if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi
  work=$(mktemp -d)
  trap 'rm -rf -- "$work"' EXIT
  git clone --filter=blob:none --no-checkout -- 'https://github.com/ML-SystemDesign/MLSystemDesign.git' "$work/repo"
  git -C "$work/repo" checkout --detach 8dd0d88852fe7445e9d2627c59124f0f161040c1
  git -C "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ml-system-design-review' > "$work/skill.tar"
  mkdir -p -- './.agents/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

Cursor

Destination .cursor/skills/ml-system-design-review

(
  set -euo pipefail
  destination='./.cursor/skills/ml-system-design-review'
  if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi
  work=$(mktemp -d)
  trap 'rm -rf -- "$work"' EXIT
  git clone --filter=blob:none --no-checkout -- 'https://github.com/ML-SystemDesign/MLSystemDesign.git' "$work/repo"
  git -C "$work/repo" checkout --detach 8dd0d88852fe7445e9d2627c59124f0f161040c1
  git -C "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ml-system-design-review' > "$work/skill.tar"
  mkdir -p -- './.cursor/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

Gemini CLI

Destination .gemini/skills/ml-system-design-review

(
  set -euo pipefail
  destination='./.gemini/skills/ml-system-design-review'
  if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi
  work=$(mktemp -d)
  trap 'rm -rf -- "$work"' EXIT
  git clone --filter=blob:none --no-checkout -- 'https://github.com/ML-SystemDesign/MLSystemDesign.git' "$work/repo"
  git -C "$work/repo" checkout --detach 8dd0d88852fe7445e9d2627c59124f0f161040c1
  git -C "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ml-system-design-review' > "$work/skill.tar"
  mkdir -p -- './.gemini/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

GitHub Copilot

Destination .github/skills/ml-system-design-review

(
  set -euo pipefail
  destination='./.github/skills/ml-system-design-review'
  if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi
  work=$(mktemp -d)
  trap 'rm -rf -- "$work"' EXIT
  git clone --filter=blob:none --no-checkout -- 'https://github.com/ML-SystemDesign/MLSystemDesign.git' "$work/repo"
  git -C "$work/repo" checkout --detach 8dd0d88852fe7445e9d2627c59124f0f161040c1
  git -C "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ml-system-design-review' > "$work/skill.tar"
  mkdir -p -- './.github/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

OpenCode

Destination .opencode/skills/ml-system-design-review

(
  set -euo pipefail
  destination='./.opencode/skills/ml-system-design-review'
  if [ -e "$destination" ] || [ -L "$destination" ]; then printf '%s\n' 'Destination already exists; nothing overwritten.' >&2; exit 1; fi
  work=$(mktemp -d)
  trap 'rm -rf -- "$work"' EXIT
  git clone --filter=blob:none --no-checkout -- 'https://github.com/ML-SystemDesign/MLSystemDesign.git' "$work/repo"
  git -C "$work/repo" checkout --detach 8dd0d88852fe7445e9d2627c59124f0f161040c1
  git -C "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ml-system-design-review' > "$work/skill.tar"
  mkdir -p -- './.opencode/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

Repository context

Repository stars (not skill ratings): 890
Repository last updated: Aug 22, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

design Derived category
docs Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 5,937 bytes
references/modern-ai-systems.mddoc · 6,295 bytes
references/output-templates.mddoc · 4,105 bytes
references/praise-patterns.mddoc · 3,652 bytes
references/red-flags-and-fixes.mddoc · 5,574 bytes
references/repo-and-doc-audit.mddoc · 3,440 bytes
references/review-workflow.mddoc · 4,659 bytes
references/rubrics.mddoc · 8,253 bytes

Read excerpt


# ML System Design Review

Use this skill to help book readers apply the ML System Design framework by Kravchenko and Babushkin to a real project. The useful output is not a generic checklist. It is a pragmatic review that tells the team what is blocking, what is cheap to improve, what is already strong, and what lesson is worth sharing.

## Activation

Use when the user asks to review, grade, audit, or improve:

- An ML system design document.
- An ML/AI repository or implementation plan.
- A design-doc PR or architecture proposal.
- A production ML readiness plan.
- A RAG, LLM, foundation-model, fine-tuning, or agentic AI system.