Individual skill

ai-stage-gate

Use when running a stage-gate or gate review for an AI product, deciding Go/Kill/Pivot at a gate, judging whether an AI initiative is ready to advance to the next stage, triaging a portfolio of AI ideas, or choosing between a full and a fast-track path. Applies a Stage-Gate process built for AI products — incremental investment, dual value-and-technical validation, alignment/ethics/data checks at every gate — to reach an evidence-based gate decision.

skills/ai-stage-gate/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/ai-stage-gate

(
  set -euo pipefail
  destination='./.claude/skills/ai-stage-gate'
  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 "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ai-stage-gate' > "$work/skill.tar"
  mkdir -p -- './.claude/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

Codex

Destination .agents/skills/ai-stage-gate

(
  set -euo pipefail
  destination='./.agents/skills/ai-stage-gate'
  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 "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ai-stage-gate' > "$work/skill.tar"
  mkdir -p -- './.agents/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

Cursor

Destination .cursor/skills/ai-stage-gate

(
  set -euo pipefail
  destination='./.cursor/skills/ai-stage-gate'
  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 "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ai-stage-gate' > "$work/skill.tar"
  mkdir -p -- './.cursor/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

Gemini CLI

Destination .gemini/skills/ai-stage-gate

(
  set -euo pipefail
  destination='./.gemini/skills/ai-stage-gate'
  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 "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ai-stage-gate' > "$work/skill.tar"
  mkdir -p -- './.gemini/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

GitHub Copilot

Destination .github/skills/ai-stage-gate

(
  set -euo pipefail
  destination='./.github/skills/ai-stage-gate'
  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 "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ai-stage-gate' > "$work/skill.tar"
  mkdir -p -- './.github/skills'
  mkdir -- "$destination"
  tar -xf "$work/skill.tar" -C "$destination"
)

OpenCode

Destination .opencode/skills/ai-stage-gate

(
  set -euo pipefail
  destination='./.opencode/skills/ai-stage-gate'
  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 "$work/repo" archive --format=tar '8dd0d88852fe7445e9d2627c59124f0f161040c1:skills/ai-stage-gate' > "$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.

finance Derived category
operations Derived category
data 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 · 13,654 bytes
references/ai-validation.mddoc · 5,852 bytes
references/fast-track.mddoc · 4,228 bytes
references/gate-decisions.mddoc · 9,316 bytes
references/modern-ai-overlay.mddoc · 7,725 bytes
references/output-templates.mddoc · 11,096 bytes
references/review-workflow.mddoc · 7,115 bytes
references/stage-gates.mddoc · 11,163 bytes

Read excerpt


# AI Stage-Gate Review

Use this skill to run a gate review for an AI product and reach a defensible decision: advance, fix-and-recycle, or stop. Stage-Gate is a portfolio-management process that structures an AI product from idea to scale: each **stage** of work ends at a **gate** where results are defended and a Go/Conditional/Kill decision is made. The useful output is not a checklist stamp. It is a decision that says what is proven, what is still a risk, what must be true to advance, and how much to invest next.

**Provenance.** This skill was inspired by and builds on work from [Hushpar](https://github.com/Hushpar). It encodes a generic Stage-Gate process adapted for AI products — six stages on Discovery and Delivery tracks, traffic-light gates, and dual value-and-technical validation. It is a distilled, vendor-neutral adaptation, not a transcription of any one organization's internal playbook; tune the stages, criteria, and thresholds to your own portfolio. It is a sibling of `ml-system-design-review` in the same [ML System Design](https://arseny.info/ml_design_book) skill collection: that skill judges *how good a design is*; this one judges *whether it has earned the next investment*.

The process runs on two tracks — **Discovery** (find and validate ideas) and **Delivery** (build and scale) — across six stages, with an optional **Fast Track** for low-uncertainty products. The AI difference is that value alone is never enough: technical feasibility, data, and alignment must clear each gate too.

## Activation

Use when the user asks to run, prepare for, or judge:

- A gate review or gate defense for an AI product or feature.
- A Go / Kill / Pivot / Conditional-Go decision at any stage.