template-repo

Compact the current conversation into a handoff document for another agent to pick up.

Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

Use when managing Node.js dependencies with pnpm - install packages, configure monorepo workspaces, set up pnpm catalogs, resolve dependency conflicts with overrides, patch third-party packages, and configure CI pipelines for pnpm projects

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Godot 4.x GDScript development. Use when writing GDScript code for this project - class structure, signals, autoloads, scene composition, typed variables, enums, @export annotations, state machines, JSON data loading, Godot 4.2 API, and the project's coding conventions. Also use when modifying scripts/battle/, scripts/cards/, scripts/core/, scripts/enemies/, or scripts/ui/ directories.

Battle system for this project. Use when modifying card execution, enemy AI, turn management, damage calculation, status effects, battle state, or win/lose conditions. Covers BattleController, TurnManager, CardExecutor, EffectResolver, DamageCalculator, StatusManager, EnemyAI, and the EventBus signal flow.

Data-driven design for this project. Use when adding or modifying cards, enemies, game config, JSON data files, or JSON Schema. Covers card effects (damage, block, draw, energy, status, conditional), enemy definitions (intents, moves, regions), data validation schema, and Python validation scripts.

Godot export and pipeline. Use when configuring export_presets.cfg, setting up export profiles (Linux/X11, Web), understanding release workflow, managing builds/ output directory, or modifying release.yml. Covers export presets, build targets, Godot CLI export commands, and release automation.

Testing and CI for this project. Use when running Python validation tests (pytest), modifying validate_json.py, configuring GitHub Actions workflows, adding test cases, or running the Godot headless import check. Covers JSON Schema validation, Python unit tests, CI pipeline (validate.yml), and the smoke test.

代码分析、修改、重构和调试

分析日志文件，聚合错误，精简堆栈，提炼高频问题

技术文档、README、API 文档、代码注释撰写

Use when managing Node.js dependencies with pnpm - install packages, configure monorepo workspaces, set up pnpm catalogs, resolve dependency conflicts with overrides, patch third-party packages, and configure CI pipelines for pnpm projects

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Use when writing unit/integration tests for Vite projects - configure vitest.config.ts, write test suites with describe/it, create mock implementations with vi.fn and vi.mock, set up code coverage thresholds, and run tests in parallel

设计角色。用于主角设定、反派设定、配角设定、角色关系网构建、话风提炼。激活于任何涉及角色创建、细化、关系梳理的小说创作任务。

一致性检查。用于检查章节内容与设定的矛盾、伏笔遗漏、逻辑漏洞、角色行为一致性。激活于任何涉及小说审核、修订、质量检查的任务。

灵感发散。用于获取场景灵感、冲突设计、命名、章节标题。激活于任何涉及卡文、需要创意、缺乏方向的小说创作任务。

润色文笔。用于润色对话、动作描写、心理描写、整体文笔打磨。激活于任何涉及小说文字润色、修改、优化措辞的任务。

切换书籍。用于切换当前激活的小说项目，更新写作上下文。激活于任何涉及切换小说、同时管理多本书的任务。

构建世界观。用于设计力量体系、地理设定、势力派系、世界运行规则、术语词典。激活于任何涉及世界观创建、扩展、细化的小说创作任务。

写小说章节。用于写新章节、续写章节、修改章节内容。激活于任何涉及小说正文创作的任务。

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.