Install
$ agentstack add skill-avelrl-skills-map-systems ✓ 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.
About
Purpose: Turn a game concept into a systems index and a clear design order.
Use when:
design/gdd/game-concept.mdexists and the project needs a system map- you need the next
design-systemtarget from the current MVP surface
Do not use for:
- inventing the game concept itself
- writing individual system GDDs
- broad production-stage readiness assessment
Inputs / Required Context:
- required:
design/gdd/game-concept.md - optional:
design/gdd/game-pillars.md, existingdesign/gdd/systems-index.md, existing system docs indesign/gdd/*.md, relevant prototype reports inprototypes/*/REPORT.md
Outputs / Owned Artifacts:
- owns
design/gdd/systems-index.md - creates
design/gdd/if it does not exist - uses
gamedev/templates/systems-index.md - maintains a
High-Risk Systemssection insidedesign/gdd/systems-index.md
Modes or Arguments:
- no argument: create or refresh
design/gdd/systems-index.md next: recommend the highest-priority nextdesign-systemtarget
Execution Rules:
- Stop immediately if
design/gdd/game-concept.mddoes not exist. - Enumerate explicit systems, required inferred systems, and clearly out-of-scope ideas.
- Build dependency order across foundation, core, feature, presentation, and meta layers.
- Assign priority tiers with a bias toward MVP and vertical-slice usefulness.
- Use a fixed status vocabulary for systems and keep updates forward-only:
identified,designed,prototyped,informed-by-prototype,implemented,integrated. - Apply the status meanings consistently:
identified: the system is only mapped in the systems indexdesigned: the canonical GDD existsprototyped: a relevant prototype report exists, but its findings are not fully folded into the canonical design docsinformed-by-prototype: prototype findings and baseline decisions are reflected in the GDD or indeximplemented: production code exists for the systemintegrated: the implementation is wired into the main playable loop or production flow
- Never downgrade a row when refreshing the index; keep the strongest confirmed status already evidenced.
- Always include a compact
High-Risk Systemssection indesign/gdd/systems-index.mdwith up to 5 real MVP risks, and do not pad the list with weak filler. Use:
SystemRisk TypeWhy It Is RiskyMitigationPrototype CandidateEvidence Needed
- For each high-risk row, name a real closure path:
Prototype Candidateshould name a concrete prototype route, or explicitly say why downstream evidence is expected to close the risk without a prototype.Evidence Neededshould name the exact proof that will close the row, not a vague aspiration.
- If prototype reports or durable downstream evidence already exist, use them to update relevant system statuses, risk notes, and
High-risk systems without evidence coverageinstead of treating the index as a fresh document. - Create or update
design/gdd/systems-index.mdusing the canonical template. - Preserve the project's working or documentation language and player-facing terminology policy when it is already captured in the concept or technical-preferences docs; do not let the systems index drift into a different default language without an explicit reason.
- In
nextmode, refresh the index first if it is missing or stale, then recommend the next highest-leverage move. - In
nextmode, prefer a target that either:
- unlocks multiple downstream systems, or
- reduces a high-risk uncertainty that blocks confident design.
- In
nextmode, if the highest-leverage move is evidence gathering rather than spec writing, recommendprototypebeforedesign-system.
Failure / Stop Conditions:
- stop if the concept is too vague to separate MVP systems from wish-list ideas
- do not write system GDDs or silently invent missing concept intent
Return Format:
- systems index path
- top MVP systems
- high-risk systems
- unresolved high-risk systems without evidence coverage
- any system statuses updated from existing evidence
- next recommended move:
design-systemorprototype - rationale for that recommendation
Example Invocation:
/map-systems next
Related Skills / Boundary:
- hand off to
design-systemfor one system at a time - hand off to
prototypewhen a high-risk system needs validation before deeper design
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.