Loading...
Loading...
Found 51 Skills
File-based knowledge persistence patterns: when to store discoveries, when to recall past solutions, and how to organize project memory. Activate when starting tasks, encountering errors, making decisions, or when context may be lost between sessions.
Concurrent investigation of independent failures. Use when multiple unrelated issues need parallel resolution.
Learn how to manage conversation context in AMCP to avoid LLM API errors from exceeding context windows. This skill covers SmartCompactor strategies, token estimation, configuration, and best practices.
Set up a complete book writing workspace with AI agents, instructions, prompts, and scripts. Use when users want to create a new book/technical writing project with Markdown + Re:VIEW + PDF output workflow. Triggers on "book writing workspace", "technical book project", "執筆ワークスペース", or similar project setup requests.
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
A 10-step methodology for building software with AI collaboration - from north star through automated Ralph loop execution with zero human-in-the-loop code writing
Uses persistent markdown files for general planning, progress tracking, and knowledge storage (Manus-style workflow). Use for multi-step tasks, research projects, or general organization WITHOUT mentioning PRD. For PRD-specific work, use prd-planner skill instead.
Define the design rules (Skill Laws) that all Skills must follow, including core principles such as AI-first, human-centric, and ready-to-use. When to use: When users create a new Skill, optimize an existing Skill, ask about Skill design specifications, or need to evaluate Skill quality.
Monitors context window health throughout a session and rides peak context quality for maximum output fidelity. Activates automatically after plan-interview and intent-framed-agent. Stays active through execution and hands off cleanly to simplify-and-harden and self-improvement when the wave completes naturally or exits via handoff. Use this skill whenever a multi-step agent task is underway and session continuity or context drift is a concern. Especially important for long-running tasks, complex refactors, or any work where degraded context would silently corrupt the output. Trigger even if the user doesn't say "context surfing" — if an agent task is running across multiple steps with intent and a plan already established, this skill is live.
Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.
PUA Loop — Autonomous Iterative Development with PUA Pressure. Runs continuously until the task is completed, no user interaction required. Combines the Ralph Loop iteration mechanism with PUA quality enforcement. Triggered by: '/pua loop', '/pua:loop', 'automatic loop', 'loop mode', 'keep running', 'automatic iteration'.
[Trigger] When PPT workflow needs SVG slide quality review via Gemini. [Output] Structured review assessment with scores, pass/fail, and fix suggestions. [Skip] For content authoring or SVG generation tasks (those are handled by Claude). [Ask] No user input needed; invoked by review-core agent. [Resource Usage] Use references/, scripts/ (`scripts/invoke-gemini-ppt.ts`).