Skip to content
Agentmart
Submit a tool

studio-gate-check

Check whether a project is ready to advance to the next development phase by verifying artifacts, quality evidence, manual unknowns, and advisory reviewer…

Skill by islee23520

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/islee23520-studio-gate-check

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Check whether a project is ready to advance to the next development phase by verifying artifacts, quality evidence, manual unknowns, and advisory reviewer feedback.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/studio-gate-check

What's inside

Skill name
studio-gate-check
Description
Check whether a project is ready to advance to the next development phase by verifying artifacts, quality evidence, manual unknowns, and advisory reviewer feedback.
License
MIT
Instructions
217 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Studio Gate Check

Use this skill to assess whether a project is ready to move from one development phase to the next.

This skill is prescriptive: it answers **"Are we ready to advance?"** rather than **"What phase are we in?"**

## Supported Stage Model

Use this generic stage sequence unless the repository defines its own equivalent:

1. Concept
2. Systems Design
3. Technical Setup
4. Pre-Production
5. Production
6. Polish
7. Release

If the project uses different names, map them explicitly before continuing.

## Phase 1 — Parse the Target Gate

If the user supplies a target phase, validate readiness for that transition.

If they do not, infer the current stage from available artifacts and confirm the inferred transition with `AskUserQuestion` before proceeding.

Do not skip that confirmation when the stage is inferred.

## Phase 2 — Define Gate Requirements

For the target transition, build a checklist of:

- required artifacts
- quality checks
- cross-reference checks
- manual checks that cannot be automated

Use repository evidence first. If the project already documents phase criteria, prefer that over generic assumptions.

### Default gate expectations

#### Concept → Systems Design

- concept brief exists
- pillars or design principles exist
- core loop and audience are defined

#### Systems Design → Technical Setup

- systems index exists
- MVP-level design docs exist
- design docs have been reviewed for internal consistency

#### Technical Setup → Pre-Production

- engine and technical baseline are chosen
- architecture docs and key decisions exist
- test framework exists
- at least minimal UX and accessibility intent exists

#### Pre-Production → Production

- playable prototype or vertical slice exists
- first sprint plan exists
- core design docs and architecture are coherent
- key playtest evidence exists

#### Production → Polish

- core gameplay path is playable end to end
- tests and QA evidence exist
- playtesting has identified and addressed major issues

#### Polish → Release

- features and content are complete
- regression checks pass
- release readiness artifacts exist

## Phase 3 — Run the Checks

For each requirement:

### Artifact checks

- verify file or directory existence
- verify content is meaningful, not just a placeholder
- verify counts or coverage when the gate implies more than one artifact

### Quality checks

- run tests when the gate depends on test health
- read review reports, architecture notes, or design evidence where required
- compare implementation against plans when the gate depends on coherence

### Cross-reference checks

- compare design docs with source structure
- compare sprint or milestone plans with actual work items
- compare architecture decisions with implementation patterns

## Phase 4 — Handle Unknowns Collaboratively

Some checks cannot be proven automatically.

Ask the user directly for items such as:

- whether the core loop has been playtested
- whether the experience is fun enough to move on
- whether informal testing exists when no report file is present
- whether performance evidence exists when no profiling output is available

Never silently convert unknowns into passes.

Mark them as **Manual Check Needed** until confirmed.

## Phase 5 — Optional Reviewer Panel

If the decision is high stakes, optionally spawn Task-based reviewers in parallel, such as:

From islee23520/lux, MIT.

More from islee23520/lux

Signals

Stars
3
Forks
0
Open issues
16
Last commit (this folder)
Jun 3, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from islee23520

Cite this page

studio-gate-check skill. Agent Mart. https://agentmart.dev/skills/islee23520-studio-gate-check (last updated 2026-10-24)