Explorar skills

Comprehensive reference for LINE Login (OAuth 2.1) — authorization code flow, PKCE, token management, ID token JWT verification, user profiles, bot linking, and login button design. This skill should be used when the user asks to "implement LINE Login", "add Log in with LINE", "set up OAuth authorization flow", "verify an ID token", "refresh an access token", "link a bot to login", "design a login

Consumer audience research and insights using GWI (Global Web Index) data via the gwi_spark_ai MCP server. Use when the user asks about audience demographics, consumer behaviors, media consumption, social media usage, purchase drivers, brand perception, market sizing, audience profiling, competitive audience analysis, trend identification, or any consumer/market research question that can be answe

根據結構化的 AI coding 實作文件（.md）逐步實作程式碼。讀取 prompt.md 大綱， 依序參考技術規格、後端實作指示、前端實作指示，逐步確認後實作後端與前端程式碼。 使用時機：當使用者要求根據已產出的實作文件開始寫程式、實作功能、按照文件 coding、 依文件實作、開始開發時觸發。關鍵字：md to code、根據文件實作、開始寫程式、 按文件 coding、依文件開發、實作程式碼、開始實作、to code、toCode、implement, implementation, 寫程式, coding, 依規格實作, 按規格開發, 從文件產生程式碼, generate code, code generation, 開始開發。

Synthesize user interviews, JTBD analysis, and qualitative data into actionable product insights. Use this skill when a team has raw qualitative data and needs structured insights.

Develop product positioning and messaging that resonates with target segments. Use this skill when a team needs to define how to talk about the product to specific audiences.

Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup

Use this skill whenever the user wants to build, train, evaluate, or iterate on a supervised machine learning or deep learning model. Triggers include: any mention of training or fitting a model with labeled data, dataset preparation, hyperparameter tuning, cross-validation, model checkpointing, experiment tracking, overfitting, loss curves, metrics, or prediction visualization. Also trigger when

Trigger on "quickly: X", "quickly recall X", "what did I say about X", "what did they say about X", "find the quote on X", "remind me -- X", "did [name] mention X", "what was the number for X", "what date did I commit to X". Use when the user needs a one-breath answer mid-call or mid-pitch. NOT for exploration (use timeln-find) or planning (use timeln-plan).

Iterative Five Whys root cause analysis drilling from symptoms to fundamentals

Facilitate RFP process for new nlink-jp projects. Collects requirements through interactive Q&A, validates completeness against CONVENTIONS.md Phase 1, and generates a structured RFP document.

Use this skill for any task related to long-term project health: technical debt management, dependency updates, refactoring, performance optimization, quarterly reviews, codebase health assessments, legacy code modernization, or sustaining engineering. Triggers on: "tech debt", "refactor", "clean up the codebase", "update dependencies", "quarterly review", "codebase health", "legacy code", "modern

Identify and optimize conversion bottlenecks and reinforce compounding growth loops. Use this skill when a team needs to improve conversion rates in a flow or strengthen a growth loop.