データ・AIのスキル

后端开发角色。关键词：后端/FastAPI/Python/API接口/数据库/PostgreSQL/业务逻辑/认证/SSE。激活后读技术架构.md，按四层架构实现，写完任何DB函数必须立即集成测试。

日本語の概要は準備中です。原文の説明を表示しています。

AI工程师角色。关键词：AI/LLM/智能体/Prompt/上下文工程/多智能体/工作流/RAG/Function Call/效果评测。激活后设计提示词、构建智能体调用链、评测输出质量。

日本語の概要は準備中です。原文の説明を表示しています。

根据当前科研数字分身状态，生成结构化提示词，供用户提交给 ChatGPT 等带记忆功能的 AI，从中提取与画像构建相关的信息。不询问用户使用哪个 AI 工具，提示词对所有平台通用。

日本語の概要は準備中です。原文の説明を表示しています。

Use this skill whenever the user asks to run Stata commands, estimate econometric models, work with .dta files, run a .do file, generate Stata output, or do any statistical analysis where Stata is involved. Also trigger when the user mentions Stata variables, Stata syntax, or econometric tasks where Stata is the natural tool, including regressions, IV estimation, diff-in-diff, RDD, panel data, clustering, summary statistics, and margins. Stata runs through pystata on StataNow 19.5 BE; configure once with stata_setup, then drive everything with stata.run() and exchange data directly with pandas. Prefer this skill over subprocess calls or .do-file shelling for Stata work, including cases where the user does not say pystata.

日本語の概要は準備中です。原文の説明を表示しています。

Connect to and query WRDS (Wharton Research Data Services) from any research project. Use this skill whenever the user needs to download, query, or explore data from WRDS — including Compustat, CRSP, FactSet, I/B/E/S, or any other WRDS-hosted database. Also trigger when the user mentions WRDS tables, WRDS libraries, or wants to look up variable definitions or coverage in WRDS datasets. Do NOT trigger for general SQL or database questions unrelated to WRDS.

日本語の概要は準備中です。原文の説明を表示しています。

Style every matplotlib figure like the Stata 18/19 default (stcolor) scheme — Arial embedded as TrueType, white background, recessive light-gray grid below the data, no top/right spines, unframed legends, and the validated blue/red/gray palette. Use whenever a task generates or restyles charts, plots, or figures for papers, reports, or slides, even if the user doesn't mention Stata — this is the house style for all publication figures. Also use when asked to make figures "look like Stata", match the stcolor scheme, or restyle existing matplotlib output.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow despite demeaner_backend="cupy64" and an idle GPU. Use when: (1) a script looping dozens of pf.feols models on a 100k+ row panel takes ~1 min/model, (2) process inspection shows ~1-1.5 cores busy and nvidia-smi shows ~0% GPU utilization with a resident cupy context, (3) planning any worker prompt that will run a model grid (robustness variants x FE structures x domains). Root cause: per-model CPU-side single-threaded fixed costs (formulaic model-matrix build, interaction construction, singleton detection, cluster vcov) dominate wall time; GPU demeaning is a small slice. Fix: shard the model grid across OS processes and/or use pyfixest multiple-estimation syntax; mandate this IN THE WORKER PROMPT.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND before spending on prompt revision or model changes. Use when: (1) a scoring pipeline over-predicts a label (precision low, recall high) and a prompt clarification is proposed to tighten it, (2) a pilot/validation gate fails and the fix candidates are prompt edits, (3) inter-rater agreement on the weak label was already low (κ < ~0.6). Core check: if gold POSITIVES share the exact feature the revision would exclude, no prompt can pass a gold-scored gate — recall craters while precision barely moves. Also documents the verified surgical-pilot design (single-section diff, tune/holdout split, pre-registered gate, perturbation check on untouched sections).

日本語の概要は準備中です。原文の説明を表示しています。

Gate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat, gpt-*-latest, gemini-*-preview, any provider alias without a pinned version). Use when: (1) resuming a paused or credit-exhausted scoring run days after its last chunk, (2) topping up credits to finish a campaign, (3) extending a cached scoring pipeline with new items. Prevents silently splicing two model versions or serving revisions into one measure. Verified 2026-07-16: for $0.30 caught a serving-revision drift WITHIN DeepSeek v4-flash (same alias, same family, litigation scores systematically shifted across a 2-day gap) before an $83 resume spend.

日本語の概要は準備中です。原文の説明を表示しています。

Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.

日本語の概要は準備中です。原文の説明を表示しています。

Build human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to rule on cases an LLM classifier or rater panel judged, (2) a labeler reports "there is no information to label from" or cells look empty in Excel, (3) excerpt columns cluster at one exact length (e.g. all 1,500 chars — a hard truncation cap). Covers: full rating-basis recovery, Excel 32,767-char cell cap, multi-line CSV mangling, ruling dropdowns, companion text files.

日本語の概要は準備中です。原文の説明を表示しています。

Create a Software Design Document (SDD) defining component architecture, data contracts, API schemas, and platform compatibility before planning. Use in Tier 3 (Full Pipeline) or when modifying interfaces, hooks, databases, or multi-platform contracts.

日本語の概要は準備中です。原文の説明を表示しています。

Get detailed data about a shader asset in the Unity project. Returns shader properties, subshaders, passes, compilation errors, and supported status. Use 'assets-find' tool with filter 't:Shader' to find shaders, or 'assets-shader-list-all' tool to list all shader names.

日本語の概要は準備中です。原文の説明を表示しています。

Modify asset file in the project. Use 'assets-get-data' tool first to inspect the asset structure before modifying. Not allowed to modify asset file in 'Packages/' folder. Please modify it in 'Assets/' folder.

日本語の概要は準備中です。原文の説明を表示しています。

Get asset data from the asset file in the Unity project. It includes all serializable fields and properties of the asset. Use 'assets-find' tool to find asset before using this tool.

日本語の概要は準備中です。原文の説明を表示しています。

Generate ScriptableObject-based systems including data containers, event channels, and runtime sets. Use when creating game data (weapons, enemies, items, abilities), cross-system events, or live object tracking. Triggers on requests like "create weapon data", "add an event system", "make a runtime set", "decouple these systems", "create item database", "add a damage event", "track active enemies", "create a config SO", "add game settings data", or any task involving ScriptableObject data containers, event-driven communication, or runtime object tracking. Reads ProjectConfig.yaml -> architecture_pattern to determine SO-first vs DI-first context.

日本語の概要は準備中です。原文の説明を表示しています。

Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

日本語の概要は準備中です。原文の説明を表示しています。

Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

日本語の概要は準備中です。原文の説明を表示しています。

Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

日本語の概要は準備中です。原文の説明を表示しています。

Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.

日本語の概要は準備中です。原文の説明を表示しています。

Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.

日本語の概要は準備中です。原文の説明を表示しています。

Unity ScriptableObject patterns for data management, configuration, and runtime systems.

日本語の概要は準備中です。原文の説明を表示しています。

Unity 6 physics development guide. Use when working with Rigidbody, colliders, raycasting, triggers, collisions, joints, or physics simulation. Covers PhysX 5 (3D) and Box2D (2D) physics, FixedUpdate timing, layer masks, and contact data. Based on Unity 6.3 LTS documentation.

日本語の概要は準備中です。原文の説明を表示しています。

Unity 6 ECS/DOTS development guide. Use when working with Entity Component System, data-oriented design, Jobs system, or Burst Compiler. Covers Entities, IComponentData, ISystem, EntityManager, baking, Jobs, and Burst. Based on Unity 6.3 LTS documentation.

日本語の概要は準備中です。原文の説明を表示しています。