Install
$ agentstack add skill-avelrl-skills-design-system ✓ 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
Purpose: Write or update one game-system GDD from the approved systems map.
Use when:
- a system already exists in
design/gdd/systems-index.md - the project needs one implementable GDD for that specific system
Do not use for:
- creating the overall systems index
- inventing the game concept
- broad stage or project health analysis
Inputs / Required Context:
- required:
design/gdd/game-concept.mdanddesign/gdd/systems-index.md - optional:
design/gdd/game-pillars.md, existingdesign/gdd/[system-name].md, upstream or downstream system docs, relevant prototype reports inprototypes/*/REPORT.md,gamedev/standards/design-docs.md
Outputs / Owned Artifacts:
- owns
design/gdd/[system-name].md - updates the matching row in
design/gdd/systems-index.md - uses
gamedev/templates/game-design-document.md - updates the GDD status block and acceptance criteria so the document matches the strongest confirmed project state
Modes or Arguments:
- ``: normalized to kebab-case for the target GDD path
Execution Rules:
- Parse the system name and validate that the concept and systems index exist.
- Stop and route to
map-systemsifdesign/gdd/systems-index.mdis missing. - Stop and refresh the systems index if the requested system is not present there.
- Summarize the system's layer, priority, dependencies, interfaces, formulas, assumptions, and existing evidence.
- Create or update
design/gdd/[system-name].mdusing the canonical GDD template and shared design-doc rules. - Preserve the project's working or documentation language and player-facing terminology policy when it is already fixed in the concept or technical-preferences docs. Do not mix languages inside the system GDD unless the project language policy explicitly requires it.
- Keep the system contract platform-agnostic unless a runtime capability, input mode, hardware limit, or delivery constraint is genuinely part of the design.
- Ensure the
Scope Boundariessection clearly separates:
In MVPIn Vertical SliceDeferred / Later
- If a relevant prototype report exists, keep an explicit
Evidence / Prototype Inputssection that:
- references the report path or paths
- extracts up to 4 key findings
- records adopted baseline values or
None adopted yet - records remaining open questions or evidence gaps
- If no relevant prototype exists, keep the section and explicitly mark
None yetinstead of implying certainty. - Update the matching row in
design/gdd/systems-index.mdso status reflects the strongest confirmed state. - When syncing status:
- use
designedwhen the GDD exists but prototype findings are not yet folded into it - use
informed-by-prototypewhen prototype findings and baseline decisions are reflected in the GDD - never downgrade
implementedorintegrated
- Sync the GDD
## Statusblock to the same strongest confirmed state you are relying on:
- keep
Document StatusasDraftonly while implementation blockers remain - use
Approvedwhen the document is implementation-ready - use
Implementedwhen production code already exists for the system - use
Integratedwhen the system is already verified inside the main playable loop
- If acceptance criteria are already satisfied by the current repository state, check them or rewrite them so the document does not pretend the repo is less complete than it really is.
- If prototype or playtest evidence changes scope or assumptions, rewrite the affected sections so the document stays internally consistent instead of appending contradictory notes.
- When the GDD is implementation-ready and the scaffold already exists, end with a handoff to
implement-system; otherwise hand off to anotherdesign-systemorprototype.
Failure / Stop Conditions:
- stop if the game concept is missing
- stop if the requested system is outside the current systems index
- record unknowns as assumptions or open questions instead of inventing detail
Return Format:
- GDD path
- systems-index status update and rationale
- scope boundaries captured
- key rules or decisions captured
- evidence adopted from prototype reports, if any
- open questions that still block implementation
- next recommended skill:
design-system,prototype, orimplement-system
Example Invocation:
/design-system combat-loop
Related Skills / Boundary:
- use
map-systemsto define the system list before writing GDDs - use
prototypewhen one mechanic is still too risky to spec confidently - use
implement-systemonce the GDD is stable and a runnable project scaffold exists
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: avelrl
- Source: avelrl/skills
- 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.