文件

Guide for writing and improving Claude Code skills. Use when creating new skills, debugging why skills aren't activating, or improving skill descriptions and structure.

This skill should be used when the user wants to create a new looplia workflow, generate a workflow definition file, or compose workflow steps from skill recommendations. Use when someone says "create a looplia workflow", "generate workflow.md", "compose workflow steps", "build me an automation pipeline", or "/build" (final step). Final step in looplia workflow building: transforms skill recommendations into valid v0.7.0 workflow YAML/Markdown files. Each step uses skill: + mission: syntax, following the one workflow step → one skill-executor → multiple skills architecture. v0.7.0: Generates explicit `skills:` declaration for selective plugin loading. v0.6.3: Supports input-less workflows using input-less capable skills (e.g., search).

为大文件生成目录概要。当入库的 Markdown 文件超过阈值（默认30KB）时，提取标题结构创建导航文件。触发条件：Markdown 文件大小 >= 30KB。

Sveltia CMS Git-backed content management (Decap/Netlify CMS successor). 5x smaller bundle (300 KB), GraphQL performance, solves 260+ issues. Use for static sites (Hugo, Jekyll, 11ty, Gatsby, Astro, Next.js), blogs, docs, i18n, or encountering OAuth errors, TOML/YAML issues, CORS problems, content listing errors.

TDD workflow and test strategy patterns including test pyramid, coverage strategies, mocking approaches, and anti-patterns. Load when writing tests, designing test strategies, or reviewing test coverage.

Python coding conventions and best practices. Use when writing, reviewing, or refactoring Python code, or when working with Python scripts and projects.

Notion URLが会話に登場した時、またはNotionのコンテンツを検索・取得する必要がある時に使用してください。

Write technical Q&A responses as markdown files to Claude Overflow. Use for programming questions, code explanations, debugging help, API usage. The response becomes a permanent archived answer viewable in a web UI.

Set up GPU sandboxes for interpretability research. Use when writing setup.py scripts with Sandbox, SandboxConfig, ModelConfig, or create_notebook_session. Provides the exact API for Modal GPU environments - MUST read before writing any sandbox setup code.

Hugo static site generator with Tailwind v4, headless CMS (Sveltia/Tina), Cloudflare deployment. Use for blogs, docs sites, or encountering theme installation, frontmatter, baseURL errors.

Export and upload the current chat conversation as a markdown file attachment to a JIRA ticket for later review and documentation.

Comprehensive Wardley mapping toolkit that transforms any input (structured data, unstructured text, business descriptions, technical architectures, competitive landscapes, or abstract concepts) into strategic Wardley maps. Creates visual maps showing component evolution and value chains for strategic decision-making.

Summarize web content including YouTube videos with semantic topic links for Logseq and Obsidian. Uses Z.AI service (port 9600) for cost-effective summarization. Supports markdown, plain text, and note-taking formats.

Refactor and finalize code after parallel phases complete, addressing technical debt. Use in cleanup phase to polish code before merge.

Threads API Documentation

Use this skill when the user wants to plan a new project or feature implementation. This skill helps gather requirements through an iterative question-and-answer process, tracking decisions in a markdown file until a comprehensive specification is ready.

Expert PRD (Product Requirements Document) writer for the AI era. Use when users want to create PRDs, spec documents, product specifications, feature specs, or technical requirements documents. Also use when users ask to review/improve existing PRDs, want PRD templates, need guidance on product documentation, or mention writing product specs. Handles both traditional and AI-specific product features with emphasis on decision-making over documentation.

Apply brand voice, tone, and style guidelines to written content across platforms. Use this skill when writing or editing content that needs to reflect a specific brand identity, adapting content for LinkedIn, Substack, X (Twitter), or other platforms while maintaining brand consistency. Triggers include requests to write on-brand content, apply brand voice, adapt content for platforms, or review content for brand alignment.

Documentation. Use when writing docs or reviewing documentation.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first