LLM 與 Agent

Update index.json status. Use for: upsert index.json, update status/last_flow/updated_at. Deterministic writes - stable diffs, no creation. Use only in run-prep and *-cleanup agents. Invoke via bash .claude/scripts/demoswarm.sh index upsert-status.

Build tools, CSS architecture, and Git workflows for clemencefouquet.fr WordPress theme. Covers linting, @layer CSS, and sync between Laragon/Git/VPS.

Enables AI agents to use Braintrust for LLM evaluation, logging, and observability.Includes scripts for querying logs with SQL, running evals, and logging data.

Cost Estimation & BOM Generation Agent

プロジェクトの CLAUDE.md を更新する。「CLAUDE.md を更新して」「ルールを追加」「プロジェクトルールを変更」「Claude のルール」「AI ドキュメント更新」「CLAUDE.md に追記」「ルールを編集」などで起動。プロジェクト固有のルールやガイドラインを管理。

Creates video presentations with static AI-generated slides and animated transitions. Auto-trigger when users ask to create presentations, slideshows, video presentations, pitch decks, training videos, or animated slide shows. Supports brand consistency via reference images (logos, colors) from the Reference Images folder. Uses fal.ai APIs (Nano Banana Pro for slides, Eleven Labs for voiceover, Kling 2.6 Pro for transitions) and FFmpeg for assembly.

A simple example skill that demonstrates the basic structure of a Claude Skill, including scripts, references, and best practices. Use this as a learning template when creating new skills.

Utilities and patterns for detecting execution environment (CI/CD vs local, network access, available ports, timeouts). Use when you need to adapt scripts or workflows based on where the agent is running, or when creating helper scripts that need environment-aware behavior.

Manages testing lifecycle including unit tests, integration tests, validation, and quality assurance.

This skill teaches the agent how to implement request validation in the API project. MANDATORY - You MUST read this skill before modifying any validator files.

Query game configuration table schemas and analyze table relationships using HTTP API and CFG syntax. This skill should be used when Claude needs to understand table structures for game development, query configuration data, or analyze foreign key relationships between tables.

Homeostatic sensor validating all requirements have design coverage. Checks for requirements without components, APIs, or data models. Quality gate before Code stage. Use to ensure design completeness.

Responsive layout considerations using CSS and Javascript. When Claude needs to build responsive, fluid layouts.

Design multi-agent workflows with DAGs, state machines, and event-driven patterns

Use for LangGraph agent design and refactors. Prefer explicit state, small nodes, and clear transitions.

Orchestrate OpenAI Codex CLI for parallel task execution. As orchestrator, analyze tasks, inject context, manage sessions, and coordinate parallel instances. Use when delegating coding tasks to Codex or running multi-agent workflows. (user)

Initialize Claude skills in the current project and verify setup. Use when user says '/init-skills', 'setup skills', 'install skills', or 'add Claude skills to this project'. Can also review and verify existing skills installation.

Assists with careful Git commits in any repository. Activates when committing changes, checking .gitignore, or generating commit messages. Ensures proper file exclusion (credentials, MCP configs, personal settings), identifies untracked files, and generates Conventional Commits messages with Japanese explanations.

Generate an end-to-end test for a given feature or user story. Use when the user asks to create E2E tests, automate workflows, test user flows, or convert manual workflows into Playwright tests. Leverages Playwright MCP to perform the workflow interactively before generating test code.

Automate Ideal Direct finance and supply chain SOPs with browser-based workflow guidance. Handles payroll, working hours, purchase orders, and audits using Playwright MCP.