nccgs 2.1.1 → 3.0.0-rc.2

package/.claude/skills/new-unity-project/SKILL.md

@@ -1,179 +0,0 @@
----
-name: new-unity-project
-description: Use when starting a brand-new Unity game or project from scratch — "make/start/create a new game", "bootstrap a Unity project", "I want to build a <genre> game", "scaffold/prototype a game", game jam, greenfield, blank project, project setup. A guided flow that gathers the concept, target platforms, and monetization, installs the Editor in the background while it asks, then creates the project and source control and installs packages — delegating the mechanics to the unity-cli and unity-package-management skills and handing off monetization to the dedicated skills. Does not scaffold gameplay code.
-allowed-tools:
-  - Bash
-  - Read
-  - Write
-  - Edit
-  - AskUserQuestion
----
-
-# New Unity Project
-
-A guided flow from an idea to a running, version-controlled Unity project. This skill owns the
-**flow** — the questions, their ordering, running slow installs in the background while you ask,
-and the handoffs. It deliberately does **not** re-document commands; it delegates the mechanics
-to other skills.
-
-**Delegates to (read these for the actual commands — don't reinvent them):**
-- **`unity-cli`** — CLI install, auth/license, Editor install, project creation, source control,
-  opening the project. Its "Bootstrap a new project from scratch" workflow is the backbone here.
-- **`unity-package-management`** — installing packages via the C# PackageManager Client API, and
-  choosing packages by genre / platform / monetization.
-- **`implement-in-app-purchases`**, **`levelplay-unity-integration`**, **`build-live-game`** —
-  monetization / backend *integration* (invoked at the end).
-
-**Work one step at a time.** Ask only the current step's questions and wait for the user before
-moving on — platform and monetization answers change what you install, so don't gather everything
-up front or scaffold before they're settled.
-
-## The flow — and where the parallelism is
-
-1. **Concept** — what they're building.
-2. **Platforms & monetization** — then, as soon as platforms are known, **kick off the Editor
-   install in the background** (it takes minutes) and keep talking.
-3. **(joins)** Editor + platform modules finish installing.
-4. **Project + source control** — create from a matching template; init git.
-5. **Packages** — install via the C# Client API.
-6. **Save & first commit.**
-7. **Hand off** monetization / backend.
-
-The whole point of a guided flow over a raw recipe: the multi-minute Editor install overlaps the
-minutes the user spends answering concept questions, so setup feels instant.
-
-## Step 1 — Concept
-
-Use `AskUserQuestion` so the user can pick fast, but let them answer freely too. Cover:
-
-- **Genre / core loop** — platformer, top-down shooter, puzzle, idle, RPG, racing, card, tower
-  defense, sim, hyper-casual, first-person, etc.
-- **Dimension & look** — 2D or 3D; art style (pixel, low-poly, stylized, realistic, UI-only).
-- **Gameplay** — the one-sentence "what the player does moment to moment."
-- **Scope** — single-screen prototype vs. multi-scene game; single-player or multiplayer.
-
-Also settle on a **project name**. Write a 2–4 line **project brief**, read it back to confirm.
-The brief drives template choice (Step 4) and packages (Step 5).
-
-## Step 2 — Platforms & monetization, then start installing
-
-Two decisions, because both change what you install:
-
-- **Target platforms** (multi-select): Desktop (Win/macOS/Linux), Mobile (iOS/Android), WebGL,
-  Console. These map to Editor **modules** (Step 3) and argue for leaner packages on mobile/WebGL.
-- **Monetization**: none / premium / in-app purchases / ads / mix. This only decides which
-  handoff skill you invoke in Step 7 — don't integrate it now.
-
-Confirm the Editor version to use (**default: latest LTS** — see `unity-cli` for the LTS vs. Tech
-vs. beta trade-off). Ask this *now*, before kicking off the install, so you don't install the
-wrong one.
-
-Then confirm prerequisites and **launch the Editor install as a background task** so it runs while
-you continue. See the `unity-cli` skill for exact syntax, module names per platform, and auth /
-license setup:
-
-```bash
-unity --version
-unity auth status --format json      # if signed out:  unity auth login
-unity license status --format json   # if none active: unity license activate
-
-# Start in the BACKGROUND, then go straight back to the conversation. Module names per platform
-# (android / ios / webgl / …) are in the unity-cli skill.
-unity install lts --module <platform-modules> --yes --accept-eula
-```
-
-Run that install as a **background task** (don't block on it). If you have nothing left to ask,
-it's fine to just wait — the parallelism only helps when there's a conversation to overlap.
-
-## Step 3 — Join: Editor ready
-
-Before creating the project, confirm the background install finished:
-
-```bash
-unity editors --installed --format json
-```
-
-If it failed, surface the error (see `unity-cli` troubleshooting) and stop — nothing downstream
-works without an Editor.
-
-## Step 4 — Create the project + source control
-
-Follow the **`unity-cli`** "Bootstrap a new project from scratch" workflow verbatim:
-
-- List the **real** template ids the Editor offers (`unity templates list`) and pick one matching
-  2D/3D and render pipeline from the brief — don't guess ids.
-- Create with `unity projects create "<Name>" --path <dir> --editor-version <v> --template <id>`.
-- Set up source control — **ask the user which they want**, don't assume: Git (GitHub / GitLab;
-  add `--git-lfs` for asset-heavy games) or **Unity Version Control** (`--vcs uvcs`, which handles
-  large binary assets natively — no LFS), or a purely local `git init` + Unity `.gitignore`.
-  Publish in one step with `unity projects create --vcs … --git-token-stdin --no-initial-commit`
-  (tokens on stdin). Pass **`--no-initial-commit`** so the CLI doesn't commit the bare project
-  before packages and `.meta` files exist — you make the real first commit/check-in in Step 6.
-  See the `unity-cli` workflow for exact flags.
-
-## Step 5 — Packages
-
-Map the brief to a concrete package list and install it via the **`unity-package-management`**
-skill (C# PackageManager Client API — **never** hand-edit `manifest.json`). Read that skill for
-the genre/platform/monetization → package mapping, the installer script, and the `-quit` gotcha.
-Read the final list back to the user before installing; verify `manifest.json` afterward.
-
-## Step 6 — Save & first commit
-
-Open the project once so Unity imports the assets and generates every `.meta` file, then make
-the first commit **with whichever VCS you set up in Step 4**:
-
-```bash
-unity open "<project-path>"     # imports + generates .meta; for headless/CI use the
-                                # "Import & save headlessly" method in unity-package-management
-```
-
-- **Git (GitHub / GitLab / local):**
-  ```bash
-  cd "<project-path>"
-  git add -A
-  git status                    # Library/ Temp/ obj/ Build/ must NOT be staged
-  git commit -m "Initial Unity project: <Name>"
-  ```
-  Every `.cs`/asset must be committed together with its `.meta`.
-- **Unity Version Control (UVCS):** check in through your UVCS client/workspace (created during
-  Step 4) — there's no `git` step. Generated folders are still excluded by the ignore rules.
-
-If you published via `--vcs` in Step 4 **without** `--no-initial-commit`, the CLI already made an
-initial commit of the bare project — add a follow-up commit here rather than double-committing.
-
-## Step 7 — Hand off
-
-Based on Step 2 monetization, invoke the matching skill for the actual integration:
-- IAP → **implement-in-app-purchases**
-- Ads → **levelplay-unity-integration**
-- Accounts / cloud save / economy / remote config / leaderboards → **build-live-game**
-
-Report the project path, Editor version, installed packages, and next steps.
-
-## Scope — what this skill does NOT do
-
-- **No gameplay scaffolding.** It gets you to a running, empty-but-wired project; building the
-  actual game (scenes, controllers, art) is the next conversation — iterate there with the Editor
-  via the `unity-cli` MCP server and the Package Manager. Generic genre skeletons tend to produce
-  throwaway mocked primitives, so this skill intentionally stops at a clean starting point.
-- **No command reference.** Syntax lives in `unity-cli` / `unity-package-management`.
-
-## Checklist
-
-- [ ] Concept brief captured and confirmed (genre, look, gameplay, scope, name)
-- [ ] Platforms + monetization recorded; Editor version chosen
-- [ ] Editor + platform modules installed (started in the background during Step 2)
-- [ ] Project created from a matching template; git initialized with a Unity `.gitignore`
-- [ ] Packages installed via the C# Client API; `manifest.json` verified
-- [ ] Project opened/saved so `.meta` files exist; first commit made; `Library/` excluded
-- [ ] Handed off to the monetization/backend skill if applicable
-
-## Common mistakes
-
-- **Blocking on the Editor install** instead of backgrounding it while you ask questions.
-- **Installing the wrong Editor** because the version wasn't confirmed before the background install.
-- **Gathering all questions up front** — platform/monetization answers change the modules and packages.
-- **Hand-editing `manifest.json`** instead of using the Client API (see `unity-package-management`).
-- **Committing `Library/`/`Temp/`/`obj/`/`Build/`**, or scripts without their `.meta` files.
-- **Missing Editor modules** — a mobile target needs `android`/`ios`; WebGL needs `webgl`.

package/.claude/skills/performance-audit/SKILL.md

@@ -1,22 +0,0 @@
----
-name: performance-audit
-description: Profiles or reviews Unity CPU, GPU, memory, loading, allocations, and frame pacing against project budgets and reproducible scenarios.
-allowed-tools: Read, Glob, Grep, Bash, Agent
----
-
-# Performance Audit
-
-Resolve execution policy from .nccgs/execution.json before model routing. Missing
-execution.json means compatibility; model profile alone never removes obligations.
-
-- standalone: load the [shared standalone procedure](../../nccgs/protocols/standalone.md)
-  for this workflow, using its intake, mode, bounded domain steps and report rules.
-  Do not load the compatibility branches or inherit their external approval chain.
-- compatibility: read models.profile from .nccgs/project.yaml and load exactly one:
-  astra-claude uses [Astra/Claude procedure](references/astra.md); quality, balanced
-  or inherit uses [Legacy procedure](references/legacy.md). Existing task records
-  retain their original gates even after project execution policy changes.
-
-Unknown execution policies or model profiles are configuration errors. External
-review in standalone is off, advisory or required according to execution policy;
-configured routes do not prove actual provider model or effort.

package/.claude/skills/performance-audit/references/astra.md

@@ -1,17 +0,0 @@
-# Performance Audit — astra-claude
-
-Read [the pipeline protocol](../../../nccgs/protocols/astra-claude.md) and
-[generated routing](../../../nccgs/routing.generated.md). Use Astra's supplied plan,
-requirements, and exact context references. Never substitute a legacy procedure.
-
-Domain objective: Profiles or reviews Unity CPU, GPU, memory, loading, allocations, and frame pacing against project budgets and reproducible scenarios.
-
-Work only inside the supplied plan and assigned write set. Activate an optional
-specialist with the agents command only when its domain is required. Keep one writer
-per path and use official Unity Skills for Editor/assets/runtime operations.
-
-This procedure is read-only: return evidence-backed findings and decisions to Astra
-or the implementer. Supplemental analysis does not replace the mandatory Fable gate.
-
-Use [task gate commands](../../../nccgs/protocols/task-gates.md) for evidence and
-state transitions. Report outcome, evidence, pending decisions, and next owner.

package/.claude/skills/performance-audit/references/legacy.md

@@ -1,7 +0,0 @@
-# Performance Audit
-
-Read `.nccgs/project.yaml`, `.nccgs/state.md`, and the active context packet when present. Preserve Product Owner authority and unrelated work.
-
-Remain read-only unless explicitly asked to optimize. Define platform, scene, hardware/environment, scenario, baseline, and budget. Use official Unity Skills and profiling tools where available. Measure before attributing cause. Report bottlenecks with evidence, player impact, confidence, and prioritized experiment or remediation. For implemented optimizations, compare identical before/after conditions and regression risk.
-
-Return outcome, evidence, affected records, blockers or decisions, residual risk, and the exact next workflow. Do not claim DONE unless this is the `closure` skill and every configured gate passes.

package/.claude/skills/physics-3d-collision/references/troubleshooting.md

@@ -1,41 +0,0 @@
-# Troubleshooting & Resources
-
-## Troubleshooting Table
-
-| Symptom | Likely Cause | Fix |
-|---|---|---|
-| No callback, no Rigidbody on either object | Two static colliders never generate callbacks | `Rigidbody` should be added to the moving object |
-| `OnCollisionEnter` never fires on a player character | Player uses `CharacterController` instead of `Rigidbody` | Use `OnControllerColliderHit(ControllerColliderHit hit)` instead |
-| Callback fires in Editor, silent in build | IL2CPP stripping MonoBehaviour | `[Preserve]` should be added, or a `link.xml` created |
-| Callback fires once then stops | Rigidbody fell asleep | `Rigidbody.WakeUp()` should be called before applying force |
-| `OnTriggerStay` / `OnCollisionStay` stops mid-session | Rigidbody fell asleep inside trigger or on collider | `Rigidbody.WakeUp()` should be called, or the sleep threshold reduced |
-| All physics frozen — AddForce, gravity, callbacks all silent | `Time.timeScale` is `0` | Set `Time.timeScale = 1f` |
-| Trigger fires but `OnCollisionEnter` does not | `isTrigger` is enabled | **Is Trigger** should be disabled if physical blocking is needed |
-| Raycast hits everything except the target | Target layer excluded from layerMask | `target.layer` should be logged and the mask verified |
-| Raycast hits nothing at all | Origin inside a collider | The ray origin should be offset; `Physics.OverlapSphere` can find enclosing colliders |
-| Raycast misses the inside face of a wall or hollow mesh | Back-face hits disabled by default | Enable **Queries Hit Backfaces** in Edit > Project Settings > Physics |
-| Two kinematic objects never interact | Kinematic × Kinematic produces no `OnCollisionEnter` | At least one should be made Dynamic, or triggers used |
-| Fast bullet passes through wall | Tunneling — Discrete mode skips thin colliders | `Continuous Dynamic` should be used; or `Physics.SphereCast` for bullets |
-| Ghost collisions (phantom hits before contact) | `Continuous Speculative` over-predicts contacts | `Continuous Dynamic` should be used for object-vs-object |
-| Dynamic object with MeshCollider produces no callbacks | Non-convex MeshCollider on dynamic Rigidbody silently ignored | **Convex** should be enabled or compound primitives used |
-| Two mesh objects never collide | Two non-convex MeshColliders cannot collide in PhysX | At least one should be made Convex; primitives used for the simpler shape |
-| Collision fires at the wrong point on mesh | Convex hull diverges from visual mesh on concave shapes | Expected — hull contact only; visualized in Scene view (Gizmos > Physics) |
-| Objects launch apart on the first frame | Colliders overlapping at simulation start — depenetration spike | Colliders should be shrunk so none overlap at spawn |
-| Collider on child not part of parent physics body | Child has its own Rigidbody, splitting the compound | The unintended child Rigidbody should be removed |
-| Collision stopped working after respawn or pool return | `Physics.IgnoreCollision` is per-instance | `Physics.IgnoreCollision` should be re-called on `Awake` / `OnEnable` |
-| Objects outside a concave mesh pass through it | MeshCollider inverted normals — contacts deflect inward | Normals should be fixed in the DCC tool, or Convex enabled |
-| Collider shape wrong despite looking correct in Scene view | Non-uniform scale on parent distorts child colliders | Scale should be applied in DCC tool so root arrives at `(1,1,1)` |
-| Raycast misses a collider moved this frame | Physics broadphase not updated after `transform.position` write | `Physics.SyncTransforms()` should be called immediately after the position change |
-| Objects stop with a visible gap before touching | Contact Offset skin gap | `Default Contact Offset` should be reduced carefully in Project Settings; very low values can reduce stability |
-
----
-
-## Resources
-
-- [Unity Manual: Collision callbacks and Rigidbody interaction](https://docs.unity3d.com/Manual/CollidersOverview.html)
-- [Unity Manual: Layer Collision Matrix](https://docs.unity3d.com/Manual/LayerBasedCollision.html)
-- [Unity Manual: Physics.Raycast](https://docs.unity3d.com/ScriptReference/Physics.Raycast.html)
-- [Unity Manual: Rigidbody collision detection modes](https://docs.unity3d.com/Manual/RigidbodiesOverview.html)
-- [Unity Manual: Physics.SyncTransforms](https://docs.unity3d.com/ScriptReference/Physics.SyncTransforms.html)
-- [Unity Manual: Rigidbody.Sleep / WakeUp](https://docs.unity3d.com/ScriptReference/Rigidbody.WakeUp.html)
-- [Unity Manual: CharacterController](https://docs.unity3d.com/Manual/class-CharacterController.html)

package/.claude/skills/plan-feature/SKILL.md

@@ -1,22 +0,0 @@
----
-name: plan-feature
-description: Creates an executable feature plan with dependencies, role ownership, write sets, verification, decisions, and closure gates. Use for meaningful STANDARD or CONTROLLED implementation before edits begin.
-allowed-tools: Read, Glob, Grep, Write, Edit, Agent, AskUserQuestion
----
-
-# Plan Feature
-
-Resolve execution policy from .nccgs/execution.json before model routing. Missing
-execution.json means compatibility; model profile alone never removes obligations.
-
-- standalone: load the [shared standalone procedure](../../nccgs/protocols/standalone.md)
-  for this workflow, using its intake, mode, bounded domain steps and report rules.
-  Do not load the compatibility branches or inherit their external approval chain.
-- compatibility: read models.profile from .nccgs/project.yaml and load exactly one:
-  astra-claude uses [Astra/Claude procedure](references/astra.md); quality, balanced
-  or inherit uses [Legacy procedure](references/legacy.md). Existing task records
-  retain their original gates even after project execution policy changes.
-
-Unknown execution policies or model profiles are configuration errors. External
-review in standalone is off, advisory or required according to execution policy;
-configured routes do not prove actual provider model or effort.

package/.claude/skills/plan-feature/references/astra.md

@@ -1,12 +0,0 @@
-# Plan Feature — astra-claude
-
-Read [the pipeline protocol](../../../nccgs/protocols/astra-claude.md) and
-[generated routing](../../../nccgs/routing.generated.md). Use Astra's supplied plan,
-requirements, and exact context references. Never substitute a legacy procedure.
-
-Astra owns this workflow and its canonical outputs. Claude only inspects relevant
-inputs and returns factual constraints, missing information, or proposed amendments.
-Do not create a replacement plan/document or sign off as Astra.
-
-Use [task gate commands](../../../nccgs/protocols/task-gates.md) for evidence and
-state transitions. Report outcome, evidence, pending decisions, and next owner.

package/.claude/skills/plan-feature/references/legacy.md

@@ -1,7 +0,0 @@
-# Plan Feature
-
-Read `.nccgs/project.yaml`, `.nccgs/state.md`, and the active context packet when present. Preserve Product Owner authority and unrelated work.
-
-Read policy, state, feature contract, and context packet. Define approved outcome, non-goals, risk, execution DAG, role per node, one writer per path, checkpoints, rollback, evidence, PO decisions, and closure artifacts. Use the [orchestration protocol](../../../nccgs/protocols/orchestration.md). Parallelize only independent nodes. Persist the plan in the mapped planning source or `.nccgs/features/` when no canonical plan exists. A plan authorizes no extra product scope.
-
-Return outcome, evidence, affected records, blockers or decisions, residual risk, and the exact next workflow. Do not claim DONE unless this is the `closure` skill and every configured gate passes.

package/.claude/skills/playtest/SKILL.md

@@ -1,22 +0,0 @@
----
-name: playtest
-description: Prepares and records a reproducible Product Owner or player playtest for subjective experience, usability, pacing, balance, readability, audio, or narrative gates.
-allowed-tools: Read, Glob, Grep, Write, Edit, AskUserQuestion
----
-
-# Playtest
-
-Resolve execution policy from .nccgs/execution.json before model routing. Missing
-execution.json means compatibility; model profile alone never removes obligations.
-
-- standalone: load the [shared standalone procedure](../../nccgs/protocols/standalone.md)
-  for this workflow, using its intake, mode, bounded domain steps and report rules.
-  Do not load the compatibility branches or inherit their external approval chain.
-- compatibility: read models.profile from .nccgs/project.yaml and load exactly one:
-  astra-claude uses [Astra/Claude procedure](references/astra.md); quality, balanced
-  or inherit uses [Legacy procedure](references/legacy.md). Existing task records
-  retain their original gates even after project execution policy changes.
-
-Unknown execution policies or model profiles are configuration errors. External
-review in standalone is off, advisory or required according to execution policy;
-configured routes do not prove actual provider model or effort.

package/.claude/skills/playtest/references/astra.md

@@ -1,31 +0,0 @@
-# Playtest — astra-claude
-
-Read [the pipeline protocol](../../../nccgs/protocols/astra-claude.md) and
-[generated routing](../../../nccgs/routing.generated.md). Use Astra's supplied plan,
-requirements, and exact context references. Never substitute a legacy procedure.
-
-Domain objective: Prepares and records a reproducible Product Owner or player playtest for subjective experience, usability, pacing, balance, readability, audio, or narrative gates.
-
-Work only inside the supplied plan and assigned write set. Activate an optional
-specialist with the agents command only when its domain is required. Keep one writer
-per path and use official Unity Skills for Editor/assets/runtime operations.
-
-For code changes: task init with Astra's plan and --risk FAST|STANDARD|CONTROLLED
-(default STANDARD), bind the session, and use the recorded implementation route.
-Keep one accountable implementer; use the scout only for missing facts. Implement,
-run relevant checks, and run task check --id ID --target review before requesting
-independent Fable review. Keep only one Fable review in flight for the task. Fix actionable findings
-within scope and re-review only within the remaining task budget. Re-recording
-implementation does not reset that budget. Exhaustion without a usable PASS means
-stop with evidence for an explicit external decision, never automatic approval.
-After task check --target report passes, write and record the report for Astra.
-Stop at AWAITING_ASTRA_CHECK. Astra checking and explicit Product Owner acceptance
-happen outside the Claude implementation session. FAST uses concise plan/report
-artifacts and keeps the full acceptance chain.
-
-For subjective uncertainty, prepare the smallest playable scenario and neutral
-observation questions that can resolve it. Record the build and actual feedback;
-do not substitute repeated model debate for player or Product Owner observation.
-
-Use [task gate commands](../../../nccgs/protocols/task-gates.md) for evidence and
-state transitions. Report outcome, evidence, pending decisions, and next owner.

package/.claude/skills/playtest/references/legacy.md

@@ -1,7 +0,0 @@
-# Playtest
-
-Read `.nccgs/project.yaml`, `.nccgs/state.md`, and the active context packet when present. Preserve Product Owner authority and unrelated work.
-
-Define build/version, participant assumptions, scenario, setup, tasks, observation prompts, success signals, and questions without leading the participant. Keep objective telemetry separate from subjective feedback. Record observations and decisions in the mapped playtest source or `.nccgs/playtests/`. A model may prepare and summarize; it must not fabricate player experience or close the PO gate.
-
-Return outcome, evidence, affected records, blockers or decisions, residual risk, and the exact next workflow. Do not claim DONE unless this is the `closure` skill and every configured gate passes.

package/.claude/skills/project-stage/SKILL.md

@@ -1,22 +0,0 @@
----
-name: project-stage
-description: Determines a Unity project's actual lifecycle stage and recommends the next NCCGS workflow from repository evidence without forcing a greenfield phase model.
-allowed-tools: Read, Glob, Grep, Bash
----
-
-# Project Stage
-
-Resolve execution policy from .nccgs/execution.json before model routing. Missing
-execution.json means compatibility; model profile alone never removes obligations.
-
-- standalone: load the [shared standalone procedure](../../nccgs/protocols/standalone.md)
-  for this workflow, using its intake, mode, bounded domain steps and report rules.
-  Do not load the compatibility branches or inherit their external approval chain.
-- compatibility: read models.profile from .nccgs/project.yaml and load exactly one:
-  astra-claude uses [Astra/Claude procedure](references/astra.md); quality, balanced
-  or inherit uses [Legacy procedure](references/legacy.md). Existing task records
-  retain their original gates even after project execution policy changes.
-
-Unknown execution policies or model profiles are configuration errors. External
-review in standalone is off, advisory or required according to execution policy;
-configured routes do not prove actual provider model or effort.

package/.claude/skills/project-stage/references/astra.md

@@ -1,12 +0,0 @@
-# Project Stage — astra-claude
-
-Read [the pipeline protocol](../../../nccgs/protocols/astra-claude.md) and
-[generated routing](../../../nccgs/routing.generated.md). Use Astra's supplied plan,
-requirements, and exact context references. Never substitute a legacy procedure.
-
-Astra owns this workflow and its canonical outputs. Claude only inspects relevant
-inputs and returns factual constraints, missing information, or proposed amendments.
-Do not create a replacement plan/document or sign off as Astra.
-
-Use [task gate commands](../../../nccgs/protocols/task-gates.md) for evidence and
-state transitions. Report outcome, evidence, pending decisions, and next owner.

package/.claude/skills/project-stage/references/legacy.md

@@ -1,7 +0,0 @@
-# Project Stage
-
-Read `.nccgs/project.yaml`, `.nccgs/state.md`, and the active context packet when present. Preserve Product Owner authority and unrelated work.
-
-Remain read-only. Inspect policy, state, canonical sources, code/assets, tests, builds, release evidence, and Git history. Classify discovery, concept, pre-production, production, stabilization, release, live operations, maintenance, or mixed/transition state. Report evidence, missing prerequisites that materially block the next outcome, and one recommended next workflow. Existing projects need not backfill ceremonial phases.
-
-Return outcome, evidence, affected records, blockers or decisions, residual risk, and the exact next workflow. Do not claim DONE unless this is the `closure` skill and every configured gate passes.

package/.claude/skills/prototype-feature/SKILL.md

@@ -1,22 +0,0 @@
----
-name: prototype-feature
-description: Creates an isolated, time-boxed Unity prototype to answer one explicit design or technical hypothesis, with measurement and keep/discard criteria.
-allowed-tools: Read, Glob, Grep, Write, Edit, Bash, Agent, AskUserQuestion
----
-
-# Prototype Feature
-
-Resolve execution policy from .nccgs/execution.json before model routing. Missing
-execution.json means compatibility; model profile alone never removes obligations.
-
-- standalone: load the [shared standalone procedure](../../nccgs/protocols/standalone.md)
-  for this workflow, using its intake, mode, bounded domain steps and report rules.
-  Do not load the compatibility branches or inherit their external approval chain.
-- compatibility: read models.profile from .nccgs/project.yaml and load exactly one:
-  astra-claude uses [Astra/Claude procedure](references/astra.md); quality, balanced
-  or inherit uses [Legacy procedure](references/legacy.md). Existing task records
-  retain their original gates even after project execution policy changes.
-
-Unknown execution policies or model profiles are configuration errors. External
-review in standalone is off, advisory or required according to execution policy;
-configured routes do not prove actual provider model or effort.

package/.claude/skills/prototype-feature/references/astra.md

@@ -1,31 +0,0 @@
-# Prototype Feature — astra-claude
-
-Read [the pipeline protocol](../../../nccgs/protocols/astra-claude.md) and
-[generated routing](../../../nccgs/routing.generated.md). Use Astra's supplied plan,
-requirements, and exact context references. Never substitute a legacy procedure.
-
-Domain objective: Creates an isolated, time-boxed Unity prototype to answer one explicit design or technical hypothesis, with measurement and keep/discard criteria.
-
-Work only inside the supplied plan and assigned write set. Activate an optional
-specialist with the agents command only when its domain is required. Keep one writer
-per path and use official Unity Skills for Editor/assets/runtime operations.
-
-For code changes: task init with Astra's plan and --risk FAST|STANDARD|CONTROLLED
-(default STANDARD), bind the session, and use the recorded implementation route.
-Keep one accountable implementer; use the scout only for missing facts. Implement,
-run relevant checks, and run task check --id ID --target review before requesting
-independent Fable review. Keep only one Fable review in flight for the task. Fix actionable findings
-within scope and re-review only within the remaining task budget. Re-recording
-implementation does not reset that budget. Exhaustion without a usable PASS means
-stop with evidence for an explicit external decision, never automatic approval.
-After task check --target report passes, write and record the report for Astra.
-Stop at AWAITING_ASTRA_CHECK. Astra checking and explicit Product Owner acceptance
-happen outside the Claude implementation session. FAST uses concise plan/report
-artifacts and keeps the full acceptance chain.
-
-Keep the experiment to the approved hypothesis and advisory timebox. Stop when its
-observation answers that question or exposes the precise blocker. Do not expand
-the prototype into production scope; subjective questions require a playable test.
-
-Use [task gate commands](../../../nccgs/protocols/task-gates.md) for evidence and
-state transitions. Report outcome, evidence, pending decisions, and next owner.

package/.claude/skills/prototype-feature/references/legacy.md

@@ -1,7 +0,0 @@
-# Prototype Feature
-
-Read `.nccgs/project.yaml`, `.nccgs/state.md`, and the active context packet when present. Preserve Product Owner authority and unrelated work.
-
-Define hypothesis, cheapest falsifiable experiment, isolation boundary, timebox, measurement, success/failure threshold, and disposal plan. Keep production contracts and source untouched unless integration is explicitly approved. Use official Unity Skills for operations. Record result, evidence, limitations, and recommendation: discard, iterate, or migrate through a separate CONTROLLED plan. Never silently promote prototype code.
-
-Return outcome, evidence, affected records, blockers or decisions, residual risk, and the exact next workflow. Do not claim DONE unless this is the `closure` skill and every configured gate passes.

package/.claude/skills/qa-plan/SKILL.md

@@ -1,22 +0,0 @@
----
-name: qa-plan
-description: Builds a risk-based Unity QA plan mapping requirements to automated, integration, runtime, build, performance, compatibility, and Product Owner validation scenarios.
-allowed-tools: Read, Glob, Grep, Write, Edit, Agent
----
-
-# Qa Plan
-
-Resolve execution policy from .nccgs/execution.json before model routing. Missing
-execution.json means compatibility; model profile alone never removes obligations.
-
-- standalone: load the [shared standalone procedure](../../nccgs/protocols/standalone.md)
-  for this workflow, using its intake, mode, bounded domain steps and report rules.
-  Do not load the compatibility branches or inherit their external approval chain.
-- compatibility: read models.profile from .nccgs/project.yaml and load exactly one:
-  astra-claude uses [Astra/Claude procedure](references/astra.md); quality, balanced
-  or inherit uses [Legacy procedure](references/legacy.md). Existing task records
-  retain their original gates even after project execution policy changes.
-
-Unknown execution policies or model profiles are configuration errors. External
-review in standalone is off, advisory or required according to execution policy;
-configured routes do not prove actual provider model or effort.

package/.claude/skills/qa-plan/references/astra.md

@@ -1,12 +0,0 @@
-# Qa Plan — astra-claude
-
-Read [the pipeline protocol](../../../nccgs/protocols/astra-claude.md) and
-[generated routing](../../../nccgs/routing.generated.md). Use Astra's supplied plan,
-requirements, and exact context references. Never substitute a legacy procedure.
-
-Astra owns this workflow and its canonical outputs. Claude only inspects relevant
-inputs and returns factual constraints, missing information, or proposed amendments.
-Do not create a replacement plan/document or sign off as Astra.
-
-Use [task gate commands](../../../nccgs/protocols/task-gates.md) for evidence and
-state transitions. Report outcome, evidence, pending decisions, and next owner.

package/.claude/skills/qa-plan/references/legacy.md

@@ -1,7 +0,0 @@
-# Qa Plan
-
-Read `.nccgs/project.yaml`, `.nccgs/state.md`, and the active context packet when present. Preserve Product Owner authority and unrelated work.
-
-Read policy, context packet, requirements, architecture, affected systems, existing tests, and baseline. Identify risk surfaces and map each criterion to the strongest practical evidence, test owner, environment, data/fixtures, expected result, regression scope, and PO gate. Include failure triage and stopping conditions. Persist in the mapped QA source or `.nccgs/evidence/`. Do not inflate coverage with redundant cases.
-
-Return outcome, evidence, affected records, blockers or decisions, residual risk, and the exact next workflow. Do not claim DONE unless this is the `closure` skill and every configured gate passes.

package/.claude/skills/release/SKILL.md

@@ -1,22 +0,0 @@
----
-name: release
-description: Prepares a reproducible Unity release candidate and coordinates builds, versions, regression, known issues, rollback, and sign-offs. Publishing, deployment, store submission, or production changes require explicit Product Owner authority.
-allowed-tools: Read, Glob, Grep, Write, Edit, Bash, Agent, AskUserQuestion, WebSearch, WebFetch
----
-
-# Release
-
-Resolve execution policy from .nccgs/execution.json before model routing. Missing
-execution.json means compatibility; model profile alone never removes obligations.
-
-- standalone: load the [shared standalone procedure](../../nccgs/protocols/standalone.md)
-  for this workflow, using its intake, mode, bounded domain steps and report rules.
-  Do not load the compatibility branches or inherit their external approval chain.
-- compatibility: read models.profile from .nccgs/project.yaml and load exactly one:
-  astra-claude uses [Astra/Claude procedure](references/astra.md); quality, balanced
-  or inherit uses [Legacy procedure](references/legacy.md). Existing task records
-  retain their original gates even after project execution policy changes.
-
-Unknown execution policies or model profiles are configuration errors. External
-review in standalone is off, advisory or required according to execution policy;
-configured routes do not prove actual provider model or effort.

package/.claude/skills/release/references/astra.md

@@ -1,30 +0,0 @@
-# Release — astra-claude
-
-Read [the pipeline protocol](../../../nccgs/protocols/astra-claude.md) and
-[generated routing](../../../nccgs/routing.generated.md). Use Astra's supplied plan,
-requirements, and exact context references. Never substitute a legacy procedure.
-
-Domain objective: Prepares a reproducible Unity release candidate and coordinates builds, versions, regression, known issues, rollback, and sign-offs. Publishing, deployment, store submission, or production changes require explicit Product Owner authority.
-
-Work only inside the supplied plan and assigned write set. Activate an optional
-specialist with the agents command only when its domain is required. Keep one writer
-per path and use official Unity Skills for Editor/assets/runtime operations.
-
-For code changes: task init with Astra's plan and --risk FAST|STANDARD|CONTROLLED
-(default STANDARD), bind the session, and use the recorded implementation route.
-Keep one accountable implementer; use the scout only for missing facts. Implement,
-run relevant checks, and run task check --id ID --target review before requesting
-independent Fable review. Keep only one Fable review in flight for the task. Fix actionable findings
-within scope and re-review only within the remaining task budget. Re-recording
-implementation does not reset that budget. Exhaustion without a usable PASS means
-stop with evidence for an explicit external decision, never automatic approval.
-After task check --target report passes, write and record the report for Astra.
-Stop at AWAITING_ASTRA_CHECK. Astra checking and explicit Product Owner acceptance
-happen outside the Claude implementation session. FAST uses concise plan/report
-artifacts and keeps the full acceptance chain.
-
-Publication and other external release actions still require explicit Product Owner
-authority; successful local verification grants no publication permission.
-
-Use [task gate commands](../../../nccgs/protocols/task-gates.md) for evidence and
-state transitions. Report outcome, evidence, pending decisions, and next owner.

package/.claude/skills/release/references/legacy.md

@@ -1,11 +0,0 @@
-# Release
-
-Treat release work as CONTROLLED when it changes platform configuration, signing, dependencies/services, compatibility, or production state.
-
-Read release policy, candidate scope, closures, known issues, migrations, versioning, repository state, build matrix, and rollback requirements. Run `/release-readiness` before producing a candidate.
-
-Compose release lead, release engineer, Unity build specialist, QA, performance, security, localization, and content roles only where the target requires them. Use official Unity Skills for build operations.
-
-Produce local artifacts, logs, manifests, checksums, evidence, and rollback notes. Fix authorized technical failures but never waive gates or change scope silently. Immediately before upload, publication, store submission, deployment, signing changes, or production configuration, obtain explicit Product Owner authority.
-
-Report candidate identity, source revision, targets, tests/builds, artifact paths, known issues, waivers, pending gates, rollback, and external actions intentionally not performed.