mirror of https://github.com/Donchitos/Claude-Code-Game-Studios.git synced 2026-10-16 01:37:05 +00:00

Files

T

DonchitosandClaude Opus 5.5 be8993bbc5 Release 1.1.3 — long skills keep their later steps

Fix release for 1.1.2: the 14 longest skills keep their later phases
after a compaction, a question nobody answered is never taken as an
answer, settings read the same from a subfolder, the commit check works
for a project in a subfolder of a larger repository, every skill opens
with a title, and the shipped allow rules no longer approve deleting a
branch or writing files without asking. Details in CHANGELOG.md; upgrade
steps in UPGRADING.md (v1.1.2 → v1.1.3).

Refs #83
Refs #133

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0185en4t76fPn7315q4c3nko

2026-10-08 17:52:48 +11:00

5.4 KiB

Raw Blame History

Vertical Slice Report: [Concept Name]

Date: [YYYY-MM-DD] Slice Duration: [N days] Target Scope: 3–5 minutes of polished, continuous gameplay Source GDD: design/gdd/game-concept.md (or design/game-brief.md)

Validation Question

[The full game loop question this build was proving — both experience AND feasibility: "Does a player, starting from nothing, experience [core fantasy] within [N] minutes, without developer guidance — and can we build one such loop in [X] days at representative quality?"]

Scope Built

[Systems implemented, art quality level, what was intentionally omitted.]

Systems included:

[System 1]
[System 2]
[...]

Art/audio quality level: [Placeholder / Representative / Near-shipping] Shortcuts taken deliberately: [List] What was cut from original scope: [List]

Build Velocity Log

[Day-by-day record of what was completed. This is your real production rate data — use it in sprint planning.]

Day	Completed
Day 1	[What was built]
Day 2	[What was built]
Day 3	[What was built]
...	...

Total elapsed: [N days] for [scope summary] Velocity estimate: [N hours per equivalent scope unit — e.g., "1 day per combat encounter, 0.5 days per UI screen"]

Playtest Results

Attribute	Value
Total sessions	[N]
Internal testers	[N]
External testers	[N — people who had not seen the game, if available]
Avg session length	[N minutes (target: [N] minutes)]
Time to first meaningful action	[N seconds (target: [N] seconds)]

Observations

[Specific, non-opinion observations from playtest sessions. Quote testers where useful.]

Where testers succeeded without guidance:

[...]

Where testers were confused or stuck:

[...]

Emotional reactions observed:

[...]

Metrics

Metric	Target	Actual
Time to first meaningful action	[N sec]	[N sec]
Session length	[N min]	[N min]
Critical fun blockers found	0	[N]
Pipeline blockers found	0	[N]
Architecture surprises	0	[N]

Feel assessment: [Specific — "combat feedback weak; no impact sound on hit" not "felt rough"]

Recommendation: [PROCEED / PIVOT / KILL / NOT ASSESSED — the slice was built but nobody has played it]

[One paragraph with evidence — reference the validation question directly. Did a player experience the core fantasy within the target time, without developer guidance? Can the team build at this quality on the projected schedule?]

Creative Director review (CD-PLAYTEST): [APPROVE / CONCERNS / REJECT / NOT ASSESSED — the director's reason; or "not run — [review mode]"]

If Proceeding

Production requirements (what must change from slice to production):

[e.g., "Replace placeholder art with shipped assets"]
[e.g., "Combat system needs 2 more weapon types"]

Architecture adjustments needed:

[ADR to update or create]

Sprint velocity estimate based on slice data:

[e.g., "1 day per enemy type, 2 days per level section, 0.5 days per UI screen"]

Scope adjustments from original design:

[What the slice revealed about the true production scope]

Performance targets: [Confirmed / Revised — list changes if revised]

Playtest note: Run /playtest-report to structure additional session data before running /gate-check production.

Next steps:

/create-epics layer:foundation — plan Foundation layer epics
/create-epics layer:core — plan Core layer epics
/create-stories [epic-slug] — break each epic into stories
/sprint-plan — use velocity data from this report in the estimate
/gate-check production — formally advance to Production

If Not Assessed

[The slice was built but nobody has played it through, so there is no evidence for PROCEED, PIVOT or KILL yet.]

Next step: play the slice unguided (at least one documented session), then re-run /vertical-slice — it resumes from the checkpoint in production/session-state/active.md.

If Pivoting

[Which GDDs need revision and why — be specific about the failure mode observed.]

Systems requiring GDD revision: [List] Architecture decisions to revisit: [List — use /architecture-decision to update] Core loop change needed: [What specifically to change]