* Add /vertical-slice skill, prototype overhaul, and workflow integration - Add /vertical-slice skill for pre-production validation (Phase 4 gate) - Overhaul /prototype skill with two-mode design: concept prototype (Phase 1) vs vertical slice (Phase 4), with clearer differentiation and higher standards for VS - Update prototyper agent to own both prototype and vertical-slice workflows - Add prototype-report.md and vertical-slice-report.md output templates - Update WORKFLOW-GUIDE, quick-start, skills-reference, agent-coordination-map, and skill-flow-diagrams to fully integrate both skills into the 7-phase pipeline - Remove orphaned empty quick-prototype/ directory Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * sync v1 counts + polish Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add entity inventory flow, relax vertical-slice gate, improve UX authoring prompts - /asset-spec: new Phase 0b entity & screen inventory when no argument and no existing inventory — reads GDDs/art-bible, proposes categorized list, writes design/assets/entity-inventory.md collaboratively - /asset-spec: entity/character target falls back to inline user description when no source doc exists, rather than failing - /gate-check: vertical slice changed from blocking to CONCERNS-only when absent; built-but-broken slice still fails; adds entity inventory as gate artifact - /ux-design: convert inline approval prompts to AskUserQuestion for structured option capture at key authoring decision points - workflow-catalog.yaml: entity-inventory step added to pre-production; UX spec min_count raised to 3; vertical-slice and prototype marked required: false with updated descriptions - .gitignore: exclude marrow/ eval tooling directory Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Add missing AskUserQuestion widgets to 7 skills Audit found 11 decision points across 7 skills where structured option prompts were missing — using plain text, auto-selection, or no gate at all. Skills patched: - create-epics: per-epic approval + producer CONCERNS verdict - sprint-plan: producer CONCERNS verdict with scope/timeline options - milestone-review: AT RISK / OFF TRACK producer verdicts require acknowledgement - retrospective: existing-retro handling converted from plain text [A]/[B] - quick-design: classification confirmation + draft approve/revise/redirect - tech-debt add mode: category (6 options) + effort (S/M/L/XL) structured capture - regression-suite: no-arg mode selection instead of silent auto-detect - hotfix: severity confirmation gate before workflow begins Also added AskUserQuestion to allowed-tools headers for retrospective, quick-design, tech-debt, regression-suite, and hotfix. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Prep v1 stable: fix WORKFLOW-GUIDE counts, stale agent names, and skill model fields - WORKFLOW-GUIDE.md: correct agent count (48→49), skill count (66/68→73), add 6 missing skills to Appendix B, fix Creative category count (2→4), replace 3 non-existent agent names with correct ue-*/unity-* specialists, add missing godot-csharp/gdextension specialists to hierarchy, fix production/stories/ paths → production/epics/ - coordination-rules.md: replace "not yet used" with opt-in env var note - quick-start.md: rename duplicate "Validate the concept" label → "Prototype the mechanic" - skill-flow-diagrams.md: remove duplicate legacy UX pipeline section - All 62 skills missing model: field now have explicit model: sonnet Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: comprehensive skill audit — consistency, UX, and flow gaps Two-pass audit fixing ~35 bugs across 41 files. Pre-production flow: - Brainstorm next-steps split into Path A (design-first) and Path B (prototype-first) — eliminates "prototype after architecture" confusion - /architecture-review added to pre-production flow in brainstorm and create-architecture handoffs - gate-check traceability check corrected to requirements-traceability.md - dev-story TR registry error now points to /architecture-review (not /create-epics) - start now writes production/stage.txt on first onboarding AskUserQuestion gaps filled: - balance-check, code-review, hotfix, day-one-patch, consistency-check all gain closing widgets and/or missing allowed-tools declarations - hotfix git branch creation now requires user confirmation - sprint-plan review-mode setup moved to Phase 0 (before gates run) - team-combat gains architecture→implementation approval gate - design-review APPROVED path consolidated from 3 widgets to 1 multiSelect All 9 team-* skills: - Phase 0 review-mode resolution added (solo/lean/full now respected) - team-audio output path fixed (design/gdd/ → design/audio/) - team-level final doc compilation delegated to level-designer subagent - team-narrative localization-lead added to composition list - team-qa sprint path fixed (flat files, not directories) - team-release NO-GO override captures written justification - team-live-ops Cancel verdict now explicitly BLOCKED Other fixes: - Art bible path standardized to design/art/art-bible.md (3 wrong refs) - AD-PHASE-GATE added to lean-mode skip list in director-gates.md - design-system duplicate 5d heading fixed; skeleton decline path added; mandatory agent spawns now respect review mode - story-readiness acceptance criteria thresholds now type-aware - create-stories gains multi-ADR and no-ADR handling guidance - consistency-check creates docs/consistency-failures.md on first run - retrospective frontmatter bash injection replaced with explicit Bash call - smoke-check ls -t gains PowerShell fallback - Conventional Commits format documented in coding-standards.md - gate-check: ADR acceptance gate, QA plan check, chain-of-verification tool-action requirement all added Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: expose --review flag in argument-hints for all team-* skills All 9 team-* skills already implement Phase 0 review-mode resolution internally (full/lean/solo), but none advertised [--review full|lean|solo] in their argument-hint. Users had no way to discover the per-run override. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add SECURITY.md with coordinated disclosure policy Defines scope, reporting process (GitHub private vulnerability reporting), contributor security guidelines for hooks/skills/agents, and 90-day coordinated disclosure timeline. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add CONTRIBUTING.md with framework contribution guidelines Covers what PRs are welcome, skill/hook/agent technical requirements, the collaborative principle, testing expectations, commit format, and platform compatibility requirements. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add v1.0.0-beta → v1.0 upgrade section to UPGRADING.md Documents the 17 commits since the beta tag: new /vertical-slice gate, entity inventory flow in /map-systems, AskUserQuestion widgets across 7 skills, --review flag exposure on team-* skills, bug fixes (#21, #36, #42, #43, #45), and the new CONTRIBUTING.md and SECURITY.md. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
12 KiB
name, description, argument-hint, user-invocable, allowed-tools, model
| name | description | argument-hint | user-invocable | allowed-tools | model |
|---|---|---|---|---|---|
| test-helpers | Generate engine-specific test helper libraries for the project's test suite. Reads existing test patterns and produces tests/helpers/ with assertion utilities, factory functions, and mock objects tailored to the project's systems. Reduces boilerplate in new test files. | [system-name | all | scaffold] | true | Read, Glob, Grep, Write | sonnet |
Test Helpers
Writing test cases is faster and more consistent when common setup, teardown,
and assertion patterns are abstracted into helpers. This skill generates a
tests/helpers/ library tailored to the project's actual engine, language,
and systems — so every developer writes less boilerplate and more assertions.
Output: tests/helpers/ directory with engine-specific helper files
When to run:
- After
/test-setupscaffolds the framework (first time) - When multiple test files repeat the same setup boilerplate
- When starting to write tests for a new system
1. Parse Arguments
Modes:
/test-helpers [system-name]— generate helpers for a specific system (e.g.,/test-helpers combat)/test-helpers all— generate helpers for all systems with test files/test-helpers scaffold— generate only the base helper library (no system-specific helpers); use this on first run- No argument — run
scaffoldif no helpers exist, elseall
2. Detect Engine and Language
Read .claude/docs/technical-preferences.md and extract:
Engine:valueLanguage:valueFramework:from the Testing section
If engine is not configured: "Engine not configured. Run /setup-engine first."
3. Load Existing Test Patterns
Scan the test directory for patterns already in use:
Glob pattern="tests/**/*_test.*" (all test files)
For a representative sample (up to 5 files), read the test files and extract:
- Setup patterns (how
before_each/setUp/ fixtures are written) - Common assertion patterns (what is being asserted most often)
- Object creation patterns (how game objects or scenes are instantiated in tests)
- Mock/stub patterns (how dependencies are replaced)
This ensures generated helpers match the project's existing style, not a generic template.
Also read:
design/gdd/systems-index.md— to know which systems exist- In-scope GDD(s) — to understand what data types and values need testing
docs/architecture/tr-registry.yaml— to map requirements to tested systems
4. Generate Engine-Specific Helpers
Godot 4 (GDUnit4 / GDScript)
Base helper (tests/helpers/game_assertions.gd):
## Game-specific assertion utilities for [Project Name] tests.
## Extends GdUnitAssertions with domain-specific helpers.
##
## Usage:
## var assert = GameAssertions.new()
## assert.health_in_range(entity, 0, entity.max_health)
class_name GameAssertions
extends RefCounted
## Assert a value is within the inclusive range [min_val, max_val].
## Use for any formula output that has defined bounds in a GDD.
static func assert_in_range(
value: float,
min_val: float,
max_val: float,
label: String = "value"
) -> void:
assert(
value >= min_val and value <= max_val,
"%s %.2f is outside expected range [%.2f, %.2f]" % [label, value, min_val, max_val]
)
## Assert a signal was emitted during a callable block.
## Usage: assert_signal_emitted(entity, "health_changed", func(): entity.take_damage(10))
static func assert_signal_emitted(
obj: Object,
signal_name: String,
action: Callable
) -> void:
var emitted := false
obj.connect(signal_name, func(_args): emitted = true)
action.call()
assert(emitted, "Expected signal '%s' to be emitted, but it was not." % signal_name)
## Assert that a callable does NOT emit a signal.
static func assert_signal_not_emitted(
obj: Object,
signal_name: String,
action: Callable
) -> void:
var emitted := false
obj.connect(signal_name, func(_args): emitted = true)
action.call()
assert(not emitted, "Expected signal '%s' NOT to be emitted, but it was." % signal_name)
## Assert a node exists at path within a parent.
static func assert_node_exists(parent: Node, path: NodePath) -> void:
assert(
parent.has_node(path),
"Expected node at path '%s' to exist." % str(path)
)
Factory helper (tests/helpers/game_factory.gd):
## Factory functions for creating test game objects.
## Returns minimal objects configured for unit testing (no scene tree required).
##
## Usage: var player = GameFactory.make_player(health: 100)
class_name GameFactory
extends RefCounted
## Create a minimal player-like object for testing.
## Override fields as needed.
static func make_player(health: int = 100) -> Node:
var player = Node.new()
player.set_meta("health", health)
player.set_meta("max_health", health)
return player
Scene helper (tests/helpers/scene_runner_helper.gd):
## Utilities for scene-based integration tests.
## Wraps GdUnitSceneRunner for common patterns.
class_name SceneRunnerHelper
extends GdUnitTestSuite
## Load a scene and wait one frame for _ready() to complete.
func load_scene_and_wait(scene_path: String) -> Node:
var scene = load(scene_path).instantiate()
add_child(scene)
await get_tree().process_frame
return scene
Unity (NUnit / C#)
Base helper (tests/helpers/GameAssertions.cs):
using NUnit.Framework;
using UnityEngine;
/// <summary>
/// Game-specific assertion utilities for [Project Name] tests.
/// Extends NUnit's Assert with domain-specific helpers.
/// </summary>
public static class GameAssertions
{
/// <summary>
/// Assert a value is within an inclusive range [min, max].
/// Use for any formula output defined in GDD Formulas sections.
/// </summary>
public static void AssertInRange(float value, float min, float max, string label = "value")
{
Assert.That(value, Is.InRange(min, max),
$"{label} ({value:F2}) is outside expected range [{min:F2}, {max:F2}]");
}
/// <summary>Assert a UnityEvent or C# event was raised during an action.</summary>
public static void AssertEventRaised(ref bool wasCalled, System.Action action, string eventName)
{
wasCalled = false;
action();
Assert.IsTrue(wasCalled, $"Expected event '{eventName}' to be raised, but it was not.");
}
/// <summary>Assert a component exists on a GameObject.</summary>
public static void AssertHasComponent<T>(GameObject obj) where T : Component
{
var component = obj.GetComponent<T>();
Assert.IsNotNull(component,
$"Expected GameObject '{obj.name}' to have component {typeof(T).Name}.");
}
}
Factory helper (tests/helpers/GameFactory.cs):
using UnityEngine;
/// <summary>
/// Factory methods for creating minimal test objects without loading scenes.
/// </summary>
public static class GameFactory
{
/// <summary>Create a minimal GameObject with a named component for testing.</summary>
public static GameObject MakeGameObject(string name = "TestObject")
{
var go = new GameObject(name);
return go;
}
/// <summary>
/// Create a ScriptableObject of type T for data-driven tests.
/// Dispose with Object.DestroyImmediate after test.
/// </summary>
public static T MakeScriptableObject<T>() where T : ScriptableObject
{
return ScriptableObject.CreateInstance<T>();
}
}
Unreal Engine (C++)
Base helper (tests/helpers/GameTestHelpers.h):
#pragma once
#include "CoreMinimal.h"
#include "Misc/AutomationTest.h"
/**
* Game-specific assertion macros and helpers for [Project Name] automation tests.
* Include in any test file that needs domain-specific assertions.
*
* Usage:
* GAME_TEST_ASSERT_IN_RANGE(TestName, DamageValue, 10.0f, 50.0f, TEXT("Damage"));
*/
// Assert a float value is within inclusive range [Min, Max]
#define GAME_TEST_ASSERT_IN_RANGE(TestName, Value, Min, Max, Label) \
TestTrue( \
FString::Printf(TEXT("%s (%.2f) in range [%.2f, %.2f]"), Label, Value, Min, Max), \
(Value) >= (Min) && (Value) <= (Max) \
)
// Assert a UObject pointer is valid (not null, not garbage collected)
#define GAME_TEST_ASSERT_VALID(TestName, Ptr, Label) \
TestTrue( \
FString::Printf(TEXT("%s is valid"), Label), \
IsValid(Ptr) \
)
// Assert an Actor is in the world (spawned successfully)
#define GAME_TEST_ASSERT_SPAWNED(TestName, ActorPtr, ClassName) \
TestNotNull( \
FString::Printf(TEXT("Spawned actor of class %s"), TEXT(#ClassName)), \
ActorPtr \
)
/**
* Helper to create a minimal test world.
* Remember to call World->DestroyWorld(false) in teardown.
*/
namespace GameTestHelpers
{
inline UWorld* CreateTestWorld(const FString& WorldName = TEXT("TestWorld"))
{
UWorld* World = UWorld::CreateWorld(EWorldType::Game, false);
FWorldContext& WorldContext = GEngine->CreateNewWorldContext(EWorldType::Game);
WorldContext.SetCurrentWorld(World);
return World;
}
}
5. Generate System-Specific Helpers
For [system-name] or all modes, generate a helper per system:
Read the system's GDD to extract:
- Data types (entity types, component names)
- Formula variables and their bounds
- Common test scenarios mentioned in Edge Cases
Generate tests/helpers/[system]_factory.[ext] with factory functions
specific to that system's objects.
Example pattern for a combat system (Godot/GDScript):
## Factory and assertion helpers for Combat system tests.
## Generated by /test-helpers combat on [date].
## Based on: design/gdd/combat.md
class_name CombatTestFactory
extends RefCounted
const DAMAGE_MIN := 0
const DAMAGE_MAX := 999 # From GDD: damage formula upper bound
## Create a minimal attacker object for damage formula tests.
static func make_attacker(attack: float = 10.0, crit_chance: float = 0.0) -> Node:
var attacker = Node.new()
attacker.set_meta("attack", attack)
attacker.set_meta("crit_chance", crit_chance)
return attacker
## Create a minimal target object for damage receive tests.
static func make_target(defense: float = 0.0, health: float = 100.0) -> Node:
var target = Node.new()
target.set_meta("defense", defense)
target.set_meta("health", health)
target.set_meta("max_health", health)
return target
## Assert damage output is within GDD-specified bounds.
static func assert_damage_in_bounds(damage: float) -> void:
GameAssertions.assert_in_range(damage, DAMAGE_MIN, DAMAGE_MAX, "damage")
6. Write Output
Present a summary of what will be created:
## Test Helpers to Create
Base helpers (engine: [engine]):
- tests/helpers/game_assertions.[ext]
- tests/helpers/game_factory.[ext]
[engine-specific extras]
System helpers ([mode]):
- tests/helpers/[system]_factory.[ext] ← from [system] GDD
Ask: "May I write these helper files to tests/helpers/?"
Never overwrite existing files. If a file already exists, report:
"Skipping [path] — already exists. Remove the file manually if you want it
regenerated."
After writing: Verdict: COMPLETE — helper files created.
"Helper files created. To use them in a test:
- Godot:
class_nameis auto-imported — no explicit import needed - Unity: Add
usingdirective or reference the test assembly - Unreal:
#include \"tests/helpers/GameTestHelpers.h\""
Collaborative Protocol
- Never overwrite existing helpers — they may contain hand-written customisations. Only generate new files that don't exist yet
- Generated code is a starting point — the generated factory functions use metadata patterns for simplicity; adapt to the actual class structure once the code exists
- Helpers should reflect the GDD — bounds and constants in helpers should trace to GDD Formulas sections, not invented values
- Ask before writing — always confirm before creating files in
tests/
Next Steps
- Run
/test-setupif the test framework has not been scaffolded yet. - Use
/dev-storyto implement stories — helpers reduce boilerplate in new test files. - Run
/skill-testto validate other skills that may need helper coverage.