| name | gate-check |
| description | Validate readiness to advance between development phases. Produces a PASS/CONCERNS/FAIL verdict with specific blockers and required artifacts. Use when user says 'are we ready to move to X', 'can we advance to production', 'check if we can start the next phase', 'pass the gate'. |
| argument-hint | [target-phase: systems-design | technical-setup | pre-production | production | polish | release] [--review full|lean|solo] |
| user-invocable | true |
| allowed-tools | Read, Glob, Grep, Bash, Write, Task, AskUserQuestion |
| model | opus |
Phase Gate Validation
This skill validates whether the project is ready to advance to the next development
phase. It checks for required artifacts, quality standards, and blockers.
Distinct from /project-stage-detect: That skill is diagnostic ("where are we?").
This skill is prescriptive ("are we ready to advance?" with a formal verdict).
Production Stages (7)
The project progresses through these stages:
- Concept — Brainstorming, game concept document
- Systems Design — Mapping systems, writing GDDs
- Technical Setup — Engine config, architecture decisions
- Pre-Production — Prototyping, vertical slice validation
- Production — Feature development (Epic/Feature/Task tracking active)
- Polish — Performance, playtesting, bug fixing
- Release — Launch prep, certification
When a gate passes, write the new stage name to production/stage.txt
(single line, e.g. Production). This updates the status line immediately.
1. Parse Arguments
Target phase: $ARGUMENTS[0] (blank = auto-detect current stage, then validate next transition)
Also resolve the review mode (once, store for all gate spawns this run):
- If
--review [full|lean|solo] was passed → use that
- Else read
production/review-mode.txt → use that value
- Else → default to
lean
Note: in solo mode, director spawns (CD-PHASE-GATE, TD-PHASE-GATE, PR-PHASE-GATE, AD-PHASE-GATE) are skipped — gate-check becomes artifact-existence checks only. In lean mode, all four directors still run (phase gates are the purpose of lean mode).
-
With argument: /gate-check production — validate readiness for that specific phase
-
No argument: Auto-detect current stage using the same heuristics as
/project-stage-detect, then confirm with the user before running:
Use AskUserQuestion:
- Prompt: "Detected stage: [current stage]. Running gate for [Current] → [Next] transition. Is this correct?"
- Options:
[A] Yes — run this gate[B] No — pick a different gate (if selected, show a second widget listing all gate options: Concept → Systems Design, Systems Design → Technical Setup, Technical Setup → Pre-Production, Pre-Production → Production, Production → Polish, Polish → Release)
Do not skip this confirmation step when no argument is provided.
2. Phase Gate Definitions
Gate: Concept → Systems Design
Required Artifacts:
Recommended (not blocking):
Quality Checks:
Gate: Systems Design → Technical Setup
Required Artifacts:
Quality Checks:
Gate: Technical Setup → Pre-Production
Required Artifacts:
Quality Checks:
ADR Circular Dependency Check: For all ADRs in docs/architecture/, read each ADR's
"ADR Dependencies" / "Depends On" section. Build a dependency graph (ADR-A → ADR-B means
A depends on B). If any cycle is detected (e.g. A→B→A, or A→B→C→A):
- Flag as FAIL: "Circular ADR dependency: [ADR-X] → [ADR-Y] → [ADR-X].
Neither can reach Accepted while the cycle exists. Remove one 'Depends On' edge to
break the cycle."
Engine Validation (read docs/engine-reference/[engine]/VERSION.md first):
Gate: Pre-Production → Production
Required Artifacts:
Quality Checks:
Vertical Slice Validation (only run these checks if a Vertical Slice was built):
Verdict rules for Vertical Slice:
- Slice was built AND any validation item is NO → verdict is automatically FAIL. A broken
or unfun vertical slice should not advance to Production.
- Slice was not built (skipped) → downgrade to CONCERNS only, not FAIL. Surface the risk
clearly: "Advancing without a validated Vertical Slice increases the risk of late-stage design
pivots. Recommended before committing full production scope." The user decides.
- Skipping is a valid solo dev or time-constrained call. Shipping a broken one is not.
Gate: Production → Polish
Required Artifacts:
Quality Checks:
Gate: Polish → Release
Required Artifacts:
Quality Checks:
3. Run the Gate Check
Before running artifact checks, read docs/consistency-failures.md if it exists.
Extract entries whose Domain matches the target phase (e.g., if checking
Systems Design → Technical Setup, pull entries in Economy, Combat, or any GDD domain;
if checking Technical Setup → Pre-Production, pull entries in Architecture, Engine).
Carry these as context — recurring conflict patterns in the target domain warrant
increased scrutiny on those specific checks.
For each item in the target gate:
Artifact Checks
- Use
Glob and Read to verify files exist and have meaningful content
- Don't just check existence — verify the file has real content (not just a template header)
- For code checks, verify directory structure and file counts
Systems Design → Technical Setup gate — cross-GDD review check:
Use Glob('design/gdd/gdd-cross-review-*.md') to find the /review-all-gdds report.
If no file matches, mark the "cross-GDD review report exists" artifact as FAIL and
surface it prominently: "No /review-all-gdds report found in design/gdd/. Run
/review-all-gdds before advancing to Technical Setup."
If a file is found, read it and check the verdict line: a FAIL verdict means the
cross-GDD consistency check failed and must be resolved before advancing.
Quality Checks
- For test checks: Run the test suite via
Bash if a test runner is configured
- For design review checks:
Read the GDD and check for the 8 required sections
- For performance checks:
Read technical-preferences.md and compare against any
profiling data in tests/performance/ or recent /perf-profile output
- For localization checks:
Grep for hardcoded strings in src/
Cross-Reference Checks
- Compare
design/gdd/ documents against src/ implementations
- Check that every system referenced in architecture docs has corresponding code
- Verify sprint plans reference real work items
4. Collaborative Assessment
For items that can't be automatically verified, ask the user:
- "I can't automatically verify that the core loop plays well. Has it been playtested?"
- "No playtest report found. Has informal testing been done?"
- "Performance profiling data isn't available. Would you like to run
/perf-profile?"
Never assume PASS for unverifiable items. Mark them as MANUAL CHECK NEEDED.
4b. Director Panel Assessment
Apply review mode before spawning any director:
solo → skip all four directors. Note in output: "Director Panel skipped — Solo mode. Gate verdict based on artifact and quality checks only." Proceed to Phase 5.lean → spawn all four directors (phase gates always run in lean mode — this is their purpose).full → spawn all four directors as normal.
(Review mode was resolved in Phase 1. Use that stored value here.)
Before generating the final verdict, spawn all four directors as parallel subagents via Task using the parallel gate protocol from .claude/docs/director-gates.md. Issue all four Task calls simultaneously — do not wait for one before starting the next.
Spawn in parallel:
creative-director — gate CD-PHASE-GATE (.claude/docs/director-gates.md)technical-director — gate TD-PHASE-GATE (.claude/docs/director-gates.md)producer — gate PR-PHASE-GATE (.claude/docs/director-gates.md)art-director — gate AD-PHASE-GATE (.claude/docs/director-gates.md)
Pass to each: target phase name, list of artifacts present, and the context fields listed in that gate's definition.
Collect all four responses, then present the Director Panel summary:
## Director Panel Assessment
Creative Director: [READY / CONCERNS / NOT READY]
[feedback]
Technical Director: [READY / CONCERNS / NOT READY]
[feedback]
Producer: [READY / CONCERNS / NOT READY]
[feedback]
Art Director: [READY / CONCERNS / NOT READY]
[feedback]
Apply to the verdict:
- Any director returns NOT READY → verdict is minimum FAIL (user may override with explicit acknowledgement)
- Any director returns CONCERNS → verdict is minimum CONCERNS
- All four READY → eligible for PASS (still subject to artifact and quality checks from Section 3)
5. Output the Verdict
## Gate Check: [Current Phase] → [Target Phase]
**Date**: [date]
**Checked by**: gate-check skill
### Required Artifacts: [X/Y present]
- [x] design/gdd/game-concept.md — exists, 2.4KB
- [ ] docs/architecture/ — MISSING (no ADRs found)
- [x] production/sprints/ — exists, 1 sprint plan
### Quality Checks: [X/Y passing]
- [x] GDD has 8/8 required sections
- [ ] Tests — FAILED (3 failures in tests/unit/)
- [?] Core loop playtested — MANUAL CHECK NEEDED
### Blockers
1. **No Architecture Decision Records** — Run `/architecture-decision` to create one
covering core system architecture before entering production.
2. **3 test failures** — Fix failing tests in tests/unit/ before advancing.
### Recommendations
- [Priority actions to resolve blockers]
- [Optional improvements that aren't blocking]
### Verdict: [PASS / CONCERNS / FAIL]
- **PASS**: All required artifacts present, all quality checks passing
- **CONCERNS**: Minor gaps exist but can be addressed during the next phase
- **FAIL**: Critical blockers must be resolved before advancing
5a. Chain-of-Verification
After drafting the verdict in Phase 5, challenge it before finalising.
Step 1 — Generate 5 challenge questions designed to disprove the verdict:
Tool-action requirement: At least 2 of the 5 challenge questions below must be answered by re-reading a specific file (Read tool) or re-running a specific check (Grep tool) — not by reflection alone. Mark these with [TOOL ACTION] to indicate a tool was used.
For a PASS draft:
- "Which quality checks did I verify by actually reading a file, vs. inferring they passed?"
- "Are there MANUAL CHECK NEEDED items I marked PASS without user confirmation? [TOOL ACTION] Re-scan the checklist for any [?] or MANUAL CHECK items."
- "Did I confirm all listed artifacts have real content, not just empty headers? [TOOL ACTION] Re-read the file and check it has non-placeholder content."
- "Could any blocker I dismissed as minor actually prevent the phase from succeeding?"
- "Which single check am I least confident in, and why?"
For a CONCERNS draft:
- "Could any listed CONCERN be elevated to a blocker given the project's current state?"
- "Is the concern resolvable within the next phase, or does it compound over time?"
- "Did I soften any FAIL condition into a CONCERN to avoid a harder verdict?"
- "Are there artifacts I didn't check that could reveal additional blockers?"
- "Do all the CONCERNS together create a blocking problem even if each is minor alone?"
For a FAIL draft:
- "Have I accurately separated hard blockers from strong recommendations?"
- "Are there any PASS items I was too lenient about?"
- "Am I missing any additional blockers the user should know about?"
- "Can I provide a minimal path to PASS — the specific 3 things that must change?"
- "Is the fail condition resolvable, or does it indicate a deeper design problem?"
Step 2 — Answer each question independently.
Do NOT reference the draft verdict text — re-check specific files or ask the user.
Step 3 — Revise if needed:
- If any answer reveals a missed blocker → upgrade verdict (PASS→CONCERNS or CONCERNS→FAIL)
- If any answer reveals an over-stated blocker → downgrade only if citing specific evidence
- If answers are consistent → confirm verdict unchanged
Step 4 — Note the verification in the final report output:
Chain-of-Verification: [N] questions checked — verdict [unchanged | revised from X to Y]
6. Update Stage on PASS
When the verdict is PASS and the user confirms they want to advance:
- Write the new stage name to
production/stage.txt (single line, no trailing newline)
- This immediately updates the status line for all future sessions
Example: if passing the "Pre-Production → Production" gate:
echo -n "Production" > production/stage.txt
Always ask before writing: "Gate passed. May I update production/stage.txt to 'Production'?"
7. Closing Next-Step Widget
After the verdict is presented and any stage.txt update is complete, close with a structured next-step prompt using AskUserQuestion.
Tailor the options to the gate that just ran:
For systems-design PASS:
Gate passed. What would you like to do next?
[A] Run /create-architecture — produce your master architecture blueprint and ADR work plan (recommended next step)
[B] Design more GDDs first — return here when all MVP systems are complete
[C] Stop here for this session
Note for systems-design PASS: /create-architecture is the required next step before writing any ADRs. It produces the master architecture document and a prioritized list of ADRs to write. Running /architecture-decision without this step means writing ADRs without a blueprint — skip it at your own risk.
For technical-setup PASS:
Gate passed. What would you like to do next?
[A] Run /create-control-manifest — generate the layer rules manifest from your Accepted ADRs (do this first)
[B] Run /vertical-slice — build the Vertical Slice (do this before writing epics — validate fun first)
[C] Write more ADRs first — run /architecture-decision [next-system]
[D] Stop here for this session
Note for technical-setup PASS: The Pre-Production sequence is deliberately ordered
to validate fun before committing to detailed planning:
/create-control-manifest — extract technical rules from Accepted ADRs (required before epics)/vertical-slice — build the Vertical Slice FIRST, before writing epics or stories- Playtest →
/playtest-report — at least 1 session required to pass the Pre-Production gate; 3+ recommended before committing the full team
/ux-design [screen] — UX specs for main menu, core HUD, pause menu (if not done)/create-epics layer:foundation then /create-epics layer:core — plan after fun is validated/create-stories [epic-slug] for each epic/sprint-plan new
Why prototype before epics? If the prototype reveals the core loop needs to change,
epics written before that discovery will be partially wrong. Validate fun cheaply first,
then plan in detail. This is the #1 lesson from GDC postmortem data.
For all other gates, offer the two most logical next steps for that phase plus "Stop here".
8. Follow-Up Actions
Based on the verdict, suggest specific next steps:
- No art bible? →
/art-bible to create the visual identity specification
- Art bible exists but no asset specs? →
/asset-spec system:[name] to generate per-asset visual specs and generation prompts from approved GDDs
- No game concept? →
/brainstorm to create one
- No systems index? →
/map-systems to decompose the concept into systems
- Missing design docs? →
/reverse-document or delegate to game-designer
- Small design change needed? →
/quick-design for changes under ~4 hours (bypasses full GDD pipeline)
- No UX specs? →
/ux-design [screen name] to author specs, or /team-ui [feature] for full pipeline
- UX specs not reviewed? →
/ux-review [file] or /ux-review all to validate
- No accessibility requirements doc? → run
/ux-design which creates both design/accessibility-requirements.md and design/ux/interaction-patterns.md in one step
- No interaction pattern library? →
/ux-design patterns to initialize it
- GDDs not cross-reviewed? →
/review-all-gdds (run after all MVP GDDs are individually approved)
- Cross-GDD consistency issues? → fix flagged GDDs, then re-run
/review-all-gdds
- No test framework? →
/test-setup to scaffold the framework for your engine
- No QA plan for current sprint? →
/qa-plan sprint to generate one before implementation begins
- Missing ADRs? →
/architecture-decision for individual decisions
- No master architecture doc? →
/create-architecture for the full blueprint
- ADRs missing engine compatibility sections? → Re-run
/architecture-decision
or manually add Engine Compatibility sections to existing ADRs
- Missing control manifest? →
/create-control-manifest (requires Accepted ADRs)
Collaborative Protocol
This skill follows the collaborative design principle:
- Scan first: Check all artifacts and quality gates
- Ask about unknowns: Don't assume PASS for things you can't verify
- Present findings: Show the full checklist with status
- User decides: The verdict is a recommendation — the user makes the final call
- Get approval: "May I write this gate check report to production/gate-checks/?"
- Never auto-fix: If required artifacts are missing, report the FAIL verdict and
name the skill to run (e.g. "run
/test-setup"). Do NOT create missing files or
re-run the gate automatically. Creating files to manufacture a PASS defeats the
gate's purpose.
Never block a user from advancing — the verdict is advisory. Document the risks
and let the user decide whether to proceed despite concerns.
