Team Live Ops

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. At use time (never during installation) this skill also designs a live economy on paper — reward tracks with a premium tier, seasonal currency, store rotation contents and prices, and pity timers — and checks that design against the project's ethics policy; it publishes and sends nothing itself. Install "Team Live Ops" for me. The skill itself orchestrates the live-ops team to plan one season or live event; with no season name or event 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, and announces the active set before Phase 1: at the default team.size individual the live-ops-designer and economy-designer run, at small the analytics-engineer and community-manager join, and at studio the writer and narrative-director join too. Phase 1 delegates season scoping (type, duration, theme, content list, retention hook, reuse budget) to the live-ops-designer. Phase 2 delegates the seasonal narrative theme and lore connections to the narrative-director. Phase 3, run in parallel with Phase 4, delegates the economy design to the economy-designer: it reads design/live-ops/economy-rules.md and designs the reward track (free tier and premium tier value), the seasonal currency, store rotation contents and prices, and pity timers, verifying that no pay-to-win item sits in the premium track. Phase 4 delegates success metrics, A/B test design and telemetry event specifications to the analytics-engineer — specifications on paper; the skill instruments and contacts nothing. Phase 5 spawns the narrative-director and the writer in parallel for in-game text and all player-facing copy. Phase 6 delegates the communication plan to the community-manager: launch announcement drafts and a teaser / launch / mid-season / final-week cadence — drafts and a calendar, prepared locally; the skill publishes and sends nothing. Phase 7 reviews the whole plan, including an ethics check of the economy design against design/live-ops/ethics-policy.md: if that file is missing the review is flagged ETHICS REVIEW SKIPPED in the output document, and if a violation is found the verdict is BLOCKED until the user revises the design, overrides with a documented rationale, or cancels. Sub-agents write one working file each under production/live-ops/[season-slug]/ without a per-write prompt, under a bounded exception the file documents (orchestrator-named path, new artifact under production/, docs/ or tests/, phase gated by an AskUserQuestion); the final documents under design/live-ops/seasons/ are outside that exception and are written by the orchestrator itself only after its own "May I write" ask, and the COMPLETE verdict comes only after the user approves the season plan. Its frontmatter pins model: sonnet. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/team-live-ops/ 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-live-ops/ 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 ac1996365db5638b43ae25dd92cba785bdd33333929a43614149c68d0e1a7f03 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, reads my project's economy rules and ethics policy under design/live-ops/, and spawns template agents (live-ops-designer and economy-designer at every size; analytics-engineer and community-manager at small and up; writer and narrative-director at studio) — agents, docs 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 new working artifacts under production/live-ops/[season-slug]/ without a per-write prompt, but only inside the bounded exception the file documents (orchestrator-named path, new artifact under production/, docs/ or tests/, phase gated by an AskUserQuestion); the final season documents under design/live-ops/seasons/ are written by the orchestrator itself only after its own "May I write" ask. The economy it designs (premium tier, store prices, seasonal currency) stays a design document: no payment is processed, no store is contacted, no announcement is published or sent, and no third-party service, account or credential is named in the file. - Do not plan any season or event, 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-live-ops folder into the agent's skills directory, in a folder named exactly "team-live-ops", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: team-live-ops), 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/live-ops/ files and spawns its live-ops team agents), and that at use time its sub-agents write working artifacts under production/live-ops/ under a documented bounded exception, the final season documents only after the orchestrator's own write ask, and its economy and communication outputs stay local design documents — nothing is published, sent or charged). 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.