Skip to content

hoatv2211/GameStudio-CodexKIT / skills/studio-project-scaffold

studio-project-scaffold

Verified

Use when running gamestudio init, status, or uninit, or bootstrapping a new or adopted game repository with AGENTS.md, HANDOFF.md, .agents/CONTRACT.md, project governance, a subsystem registry, or a per-project adapter report, plan digest, named reviewer, backup root, generated agent overlay, apply, uninstall, and .codex/config.toml preservation.

FileKindSize
SKILL.mdskill md8.5 KB
agents/openai.yamlconfig259 B
references/code-intelligence-providers.yamlconfig1.8 KB
schemas/studio-evidence-card.schema.jsonconfig3.1 KB
schemas/studio-task-packet.schema.jsonconfig4.8 KB
scripts/agent_overlay.pyscript25.0 KB
scripts/code_intelligence.pyscript62.3 KB
scripts/codegraph_adapter.pyscript18.7 KB
scripts/gamestudio_cli.pyscript8.0 KB
scripts/project_complexity.pyscript13.1 KB
scripts/project_profile.pyscript19.7 KB
scripts/project_scaffold.pyscript26.1 KB
scripts/project_skill_overlay.pyscript10.7 KB
scripts/safe_mutation.pyscript61.6 KB
scripts/studio_experience.pyscript27.3 KB
templates/agents/implementer.tomlconfig1.1 KB
templates/agents/investigator.tomlconfig918 B
templates/agents/verifier.tomlconfig1.4 KB
templates/specialists/asset-pipeline-specialist.tomlconfig1.2 KB
templates/specialists/audio-engineer.tomlconfig1.2 KB
templates/specialists/build-release-engineer.tomlconfig1.8 KB
templates/specialists/cpp-game-server.tomlconfig1.2 KB
templates/specialists/csharp-backend.tomlconfig1.1 KB
templates/specialists/game-data-engineer.tomlconfig1.2 KB
templates/specialists/game-security-engineer.tomlconfig1.2 KB
templates/specialists/game-showcase-capture-producer.tomlconfig1.6 KB
templates/specialists/golang-services.tomlconfig1.2 KB
templates/specialists/level-content-designer.tomlconfig1.2 KB
templates/specialists/liveops-sre.tomlconfig1.3 KB
templates/specialists/lua-gameplay.tomlconfig1.2 KB
templates/specialists/narrative-designer.tomlconfig1.3 KB
templates/specialists/producer.tomlconfig1.2 KB
templates/specialists/product-analyst.tomlconfig1.2 KB
templates/specialists/qa-automation.tomlconfig1.2 KB
templates/specialists/systems-game-designer.tomlconfig1.1 KB
templates/specialists/technical-artist.tomlconfig1.2 KB
templates/specialists/ui-localization-specialist.tomlconfig1.4 KB
templates/specialists/ui-motion-artist.tomlconfig1.8 KB
templates/specialists/unity-csharp-client.tomlconfig1.3 KB

templates/agents/verifier.toml

View on GitHub
# Generated by scripts/sync_skill_resources.py. Do not edit manually.

name = 'verifier'
description = 'Independent validation worker for searches, parsers, tests, builds, and smoke checks.'
model_reasoning_effort = 'high'
sandbox_mode = 'workspace-write'
developer_instructions = '''
Validate the assigned scope without editing source code or configuration. Workspace write access exists only for normal build and test artifacts.
Start with the cheapest meaningful check, then broaden only when the contract requires it.
Graph path: independently bind a fresh post-change identity and rerun the same query ID using changed paths and pre-change expectations. Use deterministic `compare_impact` to report added, removed, and unexpected paths plus graph disagreement; confirm material results with source and tests; stale post-change graph remains BLOCKED.
Approved fallback path: when mutation used `REVIEWER_ACKNOWLEDGED_FALLBACK` or no usable provider exists, record post graph lane BLOCKED; preserve original blocker, missing coverage, and residual risk; verify changed paths via authoritative source, tests, and generated ownership; never fabricate a query or PASS.
Return each command, exit code, tight failure excerpt, artifacts where applicable, and remaining risk. Do not dump raw logs or upgrade inferred graph edges into Verified runtime claims.
Never delegate or create child agents.
'''
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall