Team Combat

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — INTEGRATED SYSTEM FIRST: this skill is one piece of the complete "Claude Code Game Studios" template (49 agents, 74 skills, studio templates and a studio CLAUDE.md, per the repository README). Each skill assumes that template is installed, with its conventions, its project.yaml / project.local.yaml configuration, its .claude/docs/ mode documents, its hooks (for example hooks/yaml-helper.sh, outside this skill's folder) and its .claude/scripts/ helpers. Installing this listing alone copies only this skill's folder, without the rest of the system: the skill may reference template agents, files, hooks or scripts that are absent outside the full template, and it may not run as designed on its own. No account, no key and no payment are needed to copy the files, and nothing is run during installation. Install "Team Combat" for me. The skill itself orchestrates the combat team for one combat feature, design through implementation and validation; with no feature description it prints usage and stops immediately, without spawning any subagent or reading any file. It first resolves review_mode, automation, team.size and workflow by running the template's hooks/yaml-helper.sh, outside this skill's folder — workflow sizes the design document the way /design-system does — and announces the active set before Phase 1: at the default team.size individual the gameplay-programmer runs the pipeline alone (the ai-programmer is escalated only if the feature flags AI work), at small the full composition below runs, and at studio engine sub-specialists and an adversarial QA pass are added. Phase 1 delegates the design to the game-designer, who drafts the GDD to production/combat/[feature]-gdd-draft.md; the orchestrator writes the final design/gdd/[feature].md itself, only after its own "May I write" ask, because design/ is outside the bounded write exception. Phase 2 delegates the architecture sketch to the gameplay-programmer (with the ai-programmer if AI is involved) and spawns the primary engine specialist to validate it for the pinned engine — skipped, and recorded as NOT ASSESSED, when no engine is configured — then gates on an explicit proceed / revise / stop question. Phase 3 spawns the gameplay-programmer, ai-programmer, technical-artist and sound-designer in parallel: the sound-designer writes its audio event list to production/combat/[feature]-audio-events.md under the bounded exception, while code, VFX and shader files under the code root and assets/ are outside that exception and are written only after one ask for the whole set. Phase 4 integrates the pieces behind a gate, and Phase 5 delegates validation to the qa-tester, who writes test cases to production/qa/test-cases/[feature]-cases.md and bug reports to production/qa/bugs/BUG-[NNNN].md. Phase 6 is a spoken sign-off report (COMPLETE, NEEDS WORK or BLOCKED; a skipped engine validation is named in the verdict, never a plain COMPLETE). Its frontmatter pins model: sonnet. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/team-combat/ folder at the pinned commit: 1 file in total) Pinned version: install the code at commit 05ad7c8a5b8aa2aa86bbd3439ae7cf7295cac418 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/Donchitos/Claude-Code-Game-Studios into a temporary folder, check out commit 05ad7c8a5b8aa2aa86bbd3439ae7cf7295cac418, and copy the .claude/skills/team-combat/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 2bea102f0344c9387f281b59cf3ad9905523e8fe084f63d12091594eb3fd7eb9 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 1 file: SKILL.md only. Nothing in the folder is a program; it is instructions the agent follows at use time. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit, and no project of mine is audited, read or modified. - Integrated-system reality, from the file: at use time the skill runs the template's hooks/yaml-helper.sh to resolve review_mode, automation, team.size and workflow, follows .claude/docs/automation-modes.md, config-resolution.md and error-recovery-protocol.md and the GDD template, reads my project's design and code files locally, and spawns template agents (game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, the primary engine specialist and qa-tester, scoped by team.size) — agents, docs, templates and project files that live outside this skill's folder and are absent in a standalone install, so it cannot run as designed on its own. - At use time its sub-agents write drafts, sketches and QA artifacts under production/, docs/ or tests/ without a per-write prompt, but only inside the bounded exception the file documents (orchestrator-named path, new artifact, phase gated by an AskUserQuestion); the file itself notes that its two docs/architecture/ sketch files are read by nothing in the repo and are records, not gate inputs. Implementation files (Phase 3 code, VFX, shaders and Phase 4 integration edits) are written only after one ask for the whole set, and the design document design/gdd/[feature].md is written by the orchestrator itself only after its own "May I write" ask. No third-party service, account or credential is named in the file. - Do not design or implement any combat feature, do not spawn any team agent, do not run any template hook, and do not use the skill in any way during this install: using it is a separate step that only starts when I ask for it later. 3. When I say "yes, install", install it as a skill: copy the whole team-combat folder into the agent's skills directory, in a folder named exactly "team-combat", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: team-combat), the 1 file in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that it belongs to the full Claude Code Game Studios template and may not run standalone (it resolves its settings through the template's yaml-helper hook, reads the template's design and code files and spawns its combat team agents), and that at use time its drafts and QA artifacts are written under production/, docs/ or tests/ under a documented bounded exception, implementation files only after one ask for the set, and the GDD only after the orchestrator's own write ask). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.