Install
$ agentstack add skill-mike007jd-game-superpowers-gsp-super-build ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Game Super Build
Lead game-production workflow. Choose the right strategy for project state and quality target instead of just producing the smallest thing that runs.
Outputs
Follow the gsp-orchestrator output strategy:
- inline (default): keep all findings, plans, and decisions in conversation. Do not create
docs/files. - minimal: write only
docs/game-studio/plan.mdanddocs/game-studio/quality-target.mdfor cross-session continuity. - full: create or update the relevant
docs/game-studio/records for project state, concept, requirements, scope, build strategy, backend, UX, feedback, architecture, plan, quality, and release safety.
Phase map
- Classify
- Detect build, audit, or both.
- Existing repo inspection routes to
gsp-project-auditfirst. - Assess project state with
gsp-project-state-assessment.
- Lock the brief
- Use
gsp-concept-brainstormwhen the request is vague, weakly differentiated, archetype-ambiguous, or a one-prompt showcase build. - Use
gsp-requirements-brainstorm. - Use
gsp-scope-profile. - Use
gsp-build-strategy.
- Choose implementation route
- Use
gsp-backend-selector. - Route explicit Douyin H5 delivery through
gsp-douyin-h5before deeper browser specialization. - Route chosen web 2D or browser 3D profiles to the matching specialist skill.
- Design the product
- Use
gsp-ux-flow-designer,gsp-feedback-design, andgsp-mechanics-systems-design. - Use
gsp-production-codewhen the quality target needs product-grade implementation standards.
- Execute and verify
- Use
gsp-implementation-plan. - If subagents are available and the target is above throwaway-spike quality, prefer
gsp-subagent-build-loop. - Review and verify with
gsp-build-review,gsp-playability-verifier, andgsp-screenshot-critic.
- Escalate only when justified
- Use compare or rolling-supervisor modes only when the task size or uncertainty warrants them.
Important
For browser games, stack-neutral does not mean implementation-vague. Do not confuse fewer questions with better workflow.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mike007jd
- Source: mike007jd/game-superpowers
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.