AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Adaptive Skills

skill-furkantokkan-agent-foundry-adaptive-skills · by furkantokkan

Use when a task may span multiple personal skills and Codex should choose the smallest relevant skill set across Unity, Unity performance, Clean OOP, Firebase backend, JavaScript tooling, game design/UX, tracked task lifecycle, Steam launch, code review, and web/SaaS work.

— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-furkantokkan-agent-foundry-adaptive-skills

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-furkantokkan-agent-foundry-adaptive-skills)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● yesterday

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Adaptive Skills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Adaptive Skills

Use this skill when the best skill choice is not obvious or the task crosses multiple game-development domains.

Selection Rules

Choose the smallest relevant skill set:

  • Unity implementation, debugging, refactoring, setup, or tests:

use unity-game-dev.

  • Unity profiling, optimization, CPU/GPU/GC bottlenecks, hot paths, UI/physics/

rendering/loading/memory performance, or mobile thermal/battery constraints: use unity-optimization.

  • Unity specialist workflows: use the exact skill from the separately installed

official unity@unity-agent-plugin when its trigger matches. In Claude Code invoke /unity:; in Codex select unity:. Examples include 2d-pixel-perfect, audio-setup-mixers, build-live-game, generate-editor-search-query, implement-in-app-purchases, initialize-ai-navigation, levelplay-unity-integration, localization, manage-sprite-atlas, migrate-birp-to-urp, new-unity-project, optimize-audio, optimize-text-mesh-pro, optimize-web, physics-3d-collision, setup-multiplayer-services, setup-vivox-voice-chat, shader-graph-create-custom-node, sprite/tilemap skills, ui plus its framework skills, unity-cli, unity-package-management, urp-postprocessing, or validate-urp-render-graph-renderer-feature. Agent Foundry retains its unity-cli operating contract for project identity and authorization. If the official plugin is absent, install it from Unity-Technologies/unity-agent-plugin before invoking a specialist skill.

  • SOLID, Clean Code, naming, dependency boundaries, DI, ServiceLocator, Onity,

or testability: use clean-oop-architecture.

  • Firebase Auth, Firestore, Realtime Database, Functions Gen2, Express.js game

APIs, App Check, rules, emulators, or Unity request/response clients: use firebase-game-backend.

  • JavaScript/TypeScript tooling, Node scripts, Cloud Functions, dashboards,

packages, linting, tests, or browser tooling: use javascript-game-tools.

  • Code or architecture review: use game-code-review.
  • Game design, GDDs, systems, core loops, economy, pacing, UX, or acceptance

criteria: use game-design-studio.

  • Steam Coming Soon/store page, wishlist campaign, press/creator CRM, festival

planning, Steam Next Fest, announcement posts, or indie launch marketing: use steam-store-launch.

  • Read-only readiness check before Unity Editor work: use unity-preflight.
  • Full system GDD authoring: use design-system; small tuning/mechanic specs:

use quick-design; GDD validation: use design-review.

  • Screens, HUD, flows, onboarding, feedback, accessibility: use ux-design or

ux-review.

  • Game feel, juice, impact feedback, screen shake, hitstop, punch tweens, hit

flash, damage numbers, toasts, SFX banks, or CRT screen looks for a menu, HUD, or hit: use game-feel-polish. For Liquid UI-style Unity widgets, follow its Unity system and UI Toolkit references; Godot excerpts are source references, not the Unity implementation route.

  • Tracked task lifecycle: use create-task, implement-task, task-status,

task-bug, task-cycle, task-done, or daily-handoff; several ready tasks: use game-studio-orchestration.

  • Web/SaaS work: use the installed web stack (React/Next.js, NestJS/ASP.NET

Core, Supabase, shadcn/Radix, Playwright/webapp-testing, security, Vercel/Render deploy) as indexed in the global instructions.

This list is a common-route summary, not the authority. The Personal Skill Index in the global AGENTS.md/CLAUDE.md owns the full domain map: when the task matches an installed skill not listed above, route to that skill instead of declaring that no skill applies.

Combine skills only when the request actually spans domains. Do not force a skill when repository instructions and global rules are enough.

Baseline Defaults

  • Follow repository-local instructions first.
  • Apply SOLID, Clean Code, testability, clear English naming, and simple method

verbs by default.

  • Keep Unity MonoBehaviours thin and domain logic testable.
  • Use an existing ServiceLocator before adding dependencies; otherwise prefer

Onity for new Unity DI/reactive/events work.

  • Add focused unit tests for new or changed expected behavior.
  • For Firebase game APIs, prefer Functions Gen2 with JavaScript and Express.js

routes plus typed Unity request/response DTOs.

  • For Unity tasks that need extra pattern, performance, UI/widget, testing,

handoff, or refactoring context, start from the local PDF-derived index: optional local reference library (not included; skip if unavailable). Search it with rg and load only relevant sections.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.