Team Narrative

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 Narrative" for me. The skill itself orchestrates the narrative team for story content, world lore or a narrative-driven level; with no argument it prints usage and exits without spawning any agent. It first resolves review_mode, automation and team.size by running the template's hooks/yaml-helper.sh, outside this skill's folder, reads the canon before Phase 1 (the narrative bible or tone guide, the character and faction files under design/narrative/, and the world rules — it never tells an agent to invent canon, and asks the user before any drafting when no canon exists), and announces the active set: at the default team.size individual only the writer runs, with the narrative-director invoked only on an explicit pillar conflict; at small the narrative-director and writer run, plus the localization-lead and world-builder when review_mode is full; at studio all six composition agents run. Phase 1 delegates the narrative brief to the narrative-director. Phase 2 spawns the world-builder (lore entries cross-checked against existing lore, with canon levels), the writer (dialogue under 120 characters per line, named placeholders, localization-ready) and the art-director (character visual design and environmental storytelling) in parallel, behind a gate. Phase 3 delegates level narrative integration to the level-designer (triggers, dialogue zones, discovery points, pacing). Phase 4 is this pipeline's own consistency review, ND-CONSISTENCY, run through the narrative-director with the template's director-gate file in every review mode — review_mode never skips it: APPROVE continues, CONCERNS are shown and the user chooses revision or acceptance, REJECT stops Phase 5, and NOT ASSESSED is carried into the report as such, never read as APPROVE; at team.size individual the gate is not spawned and the writer self-checks, and the report must say so by name. Phase 5 spawns the writer (final self-review: dialogue constraints, string keys, placeholder consistency), the localization-lead (i18n validation, including expansion headroom for languages such as German and Finnish) and the world-builder (final canon levels) in parallel. Drafts are written by sub-agents under production/narrative/[content-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/narrative/ are outside that exception — the orchestrator lists them, asks once, and writes them on approval, and the localization review stays in production/. Its frontmatter pins model: sonnet. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/team-narrative/ 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-narrative/ 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 66b923ff3dd13b9e633d3ba05885bb5f53b1294c5765ab3a891205dbd8dea8c3 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 and team.size, follows .claude/docs/automation-modes.md, config-resolution.md, director-gates.md and the ND-CONSISTENCY gate file, reads my project's narrative bible, character, faction and world files under design/narrative/, and spawns template agents (writer at every size; narrative-director, world-builder, art-director, level-designer and localization-lead at wider sizes or for the consistency gate) — 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; the file also names seven other template consumers that read design/narrative/, which is why the final documents must land there. - At use time its sub-agents write draft artifacts under production/narrative/[content-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 documents under design/narrative/ are written by the orchestrator itself only after one "May I write" ask for the set, and the localization review stays in production/. No third-party service, account or credential is named in the file. - Do not draft any narrative content, 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-narrative folder into the agent's skills directory, in a folder named exactly "team-narrative", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: team-narrative), 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/narrative/ canon files and spawns its narrative team agents), and that at use time its sub-agents write drafts under production/narrative/ under a documented bounded exception, and the final design/narrative/ documents only after the orchestrator's single write ask for the set). 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.