.claude/skills/gdd-cnRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
中文游戏系统策划案(GDD)编写。按国内研发流程逐节推进:先对齐定位与竞品,再写规则、公式、配置表结构、边界、依赖、数值可调项、验收标准。数值优先落配置表,落笔前过一遍专家视角自检。触发词:写策划案、做系统策划案、GDD、系统拆解、配置表设计。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/gdd-cnRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/gdd-cnRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/gdd-cnRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @sharinchan233/gdd-cnclawhub inspect @sharinchan233/gdd-cn --version 1.0.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:beffe4b69504ec55a4146ee0546e8b953bb14816546d6e90073f156455f6340breferences/config-table-spec.mdreferences/naming-glossary.mdreferences/review-checklists.mdreferences/section-playbook.mdskill-card.mdSKILL.mdInitial release of gdd-cn: single-system Chinese GDD drafting assistant for domestic game development processes. - Automates eight-section GDD creation: alignment, questioning, drafting, confirmation, and file writing in strict sequence - Enforces “rules in docs, values in config tables”; no stray values in text - Reads project context, dependencies, and prior decisions before starting; prompts user at all decision points - Expert perspective self-check (lean/full/solo review modes), user must confirm/resolve all findings - Supports collaborative, interruption-resilient workflow; progress tracked and restorable - Only writes to files after explicit user confirmation