Gsp Implementation Plan
Use when turning an approved game brief into verifiable implementation tasks matched to the chosen build mode.
Install
$ agentstack add skill-mike007jd-game-superpowers-gsp-implementation-plan ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-mike007jd-game-superpowers-gsp-implementation-plan) 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 Implementation Plan
Turn the approved build brief into an execution plan. Use ./shared/templates/task-plan.md.
Outputs
Follow the gsp-orchestrator output strategy:
- inline (default): present implementation plan in conversation.
- minimal or full: write
docs/game-studio/plan.md.
Key rule
Do not use one default task size for all situations. Use the chosen development mode.
Planning bias
- In yolo-super, larger end-to-end tasks are allowed and often preferred.
- In guided-build, keep the plan comprehensible but still fast.
- In refactor-open, plan migrations and replacements explicitly.
- In surgical-live, keep tasks tight and rollbackable.
Execution bias
Unless the user explicitly wants a cheap or minimal pass, assume the plan should support:
- a builder stage
- a reviewer stage
- a verifier stage
For benchmark, showcase, or polished-prototype work, plan with this loop in mind instead of assuming one pass from build to done.
Important
Do not produce fake progress tasks like “set up scaffolding” unless that scaffold immediately enables real implementation. Prefer tasks that end in a stronger running build.
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.