notque/vexjoy-agent / skills/game/game-dev
game-dev
FlaggedGame development: design, asset pipelines, Phaser, Unity CLI and builds, vanilla JS frontend, GM mode, match booking.
references/capabilities/57-game-dev-first-steps.md
View on GitHub# game-dev-first-steps
## Purpose
Sequence early work toward a playable decision proof. This packet is a repository-aware operating procedure, not a label to apply to a design.
## Evidence intake
Inspect repository evidence before requesting context: concept, team, tools, market constraints. Then inspect these capability-specific signals: target player, core action, technical risk, art direction, test cadence, funding constraint. Ask only for external evidence, confidential player research, decision authority, or constraints unavailable in the repository.
Mark every claim as `observed`, `documented`, `measured`, or `inferred`. Give each inference a confidence level and a disproof route.
## Method
1. Sequence concept framing, playable core proof, technical risk spike, visual direction proof, player test, and decision cadence.
2. Choose the next step by the uncertainty that could invalidate the project, not by discipline preference.
3. Delay production scale until a player-facing proof and delivery assumptions exist.
## Capability matrix
| Lens | Repository question | Player or delivery consequence |
|---|---|---|
| target player | What evidence shows how this changes the reviewed moment? | Record the effect, confidence, and repair test. |
| core action | What evidence shows how this changes the reviewed moment? | Record the effect, confidence, and repair test. |
| technical risk | What evidence shows how this changes the reviewed moment? | Record the effect, confidence, and repair test. |
| art direction | What evidence shows how this changes the reviewed moment? | Record the effect, confidence, and repair test. |
| test cadence | What evidence shows how this changes the reviewed moment? | Record the effect, confidence, and repair test. |
| funding constraint | What evidence shows how this changes the reviewed moment? | Record the effect, confidence, and repair test. |
## Diagnostic questions
- What exact player moment or delivery decision is under review?
- Which capability lens above has the strongest evidence and which is only an inference?
- Which competing explanation would produce the same visible symptom?
- What is the smallest change or test that would separate them?
## Output schema
Return all of the following, not a generic summary:
- first-steps roadmap
- proof order
- owner map
- exit criteria
- first-week actions
## Failure modes
- Do not start with a full GDD or content backlog.
- Do not scale a team around an untested loop.
- Do not scale production before a player-facing proof.
## Example application
When a team needs to sequence early work toward a playable decision proof, begin with the available build path and the capability matrix above. Apply the named method to the affected moment, not an abstract feature description. If direct player evidence is absent, publish an evidence gap rather than a false conclusion; label the result as inferred and use the validation below to move it toward measured evidence.
## Decision procedure
1. Use `target player` as the first discriminating lens, because it is closest to the stated capability.
2. Compare it against `funding constraint` before selecting a fix; this prevents a single-dimension conclusion.
3. Convert the result into `first-steps sequence` with an owner, a quality guard, and a stop rule.
## Validation
A first phase passes when it resolves a go/no-go decision, not when it looks polished.
## Full-diagnostic disposition
In a complete repository diagnostic, run this packet and record `assessed`, `evidence gap`, or `not applicable` with a game-specific reason. A missing artifact is a finding; it never permits silent omission.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |