efficient-coding

report-coaching 和 plan-coaching 共享的访谈引擎。当这两个 skill 要求遵循访谈规则时加载，一般不单独使用。

规划教练。通过访谈引导用户形成能被批准和推行的规划材料，或对已有规划稿做评审与拷问。当用户要写规划、Roadmap、立项或方向提案，或要求 review 规划文档时使用。

通过访谈从零梳理一份规划材料。

评审并拷问已有的规划稿。

汇报教练。通过访谈引导用户产出高质量汇报材料，或按听众测试清单审阅已有汇报稿。当用户要准备汇报、周报/月报、述职材料，或要求 review 汇报文档、整理汇报思路时使用。

通过访谈从零梳理一份汇报材料。

按听众测试清单审阅已有汇报稿并引导补足。

Create professional SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Supports light (default) and dark themes. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.

Create, modify, evaluate, and package portable Agent Skills for coding agents. Use this skill when users want to create a skill from scratch, turn a workflow into a reusable skill, improve an existing skill, set up evals, compare skill behavior against a baseline, or optimize skill trigger descriptions across agent environments.

Use this skill whenever the user wants to work with the Memos REST API for memos, attachments, or activities, including creating, reading, querying, updating, deleting memos, managing memo comments/reactions/relations/attachments, listing and inspecting activities, or creating memos with hashtag-based tagging after checking existing tags from a Memos instance.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Search a user's Cubox collection deeply by topic, theme, or question. Use this whenever the user asks to search Cubox, saved articles, archived reads, or collected pages for a subject, wants multiple keyword variations tried, wants full-text search across Cubox, or needs article details exported from Cubox HTML into local Markdown with downloaded images for later analysis.

Build a topic-centered research memo from the user's Readwise Reader documents and Readwise highlights. Use this whenever the user asks what they have already read, saved, highlighted, or been reading about a topic, wants a reading brief or research memo from their own library, wants evidence and tensions synthesized across Reader and Readwise, or wants topic-based shortlist/later/archive or tag suggestions. Use it even when the user does not say "Readwise" explicitly and instead says things like "I've been reading a lot about X" or "help me organize what I've read on Y." Prefer this skill over inbox-style triage when the task is organized around a theme, argument, project, or decision rather than chronology. Default to analysis first and only modify Reader after explicit user confirmation.

Transform any code project into one optimized for AI agent collaboration through harness engineering. Scans the codebase to detect structure, patterns, and tooling, extracts implicit engineering knowledge through guided choice-based questions, and generates minimal structured context documents plus engineering changes (lint rules, structural tests, CI checks). Use this skill when the user wants to make their codebase agent-ready, mentions harness engineering, wants to set up AGENTS.md or agent context, wants to improve AI coding agent productivity on their project, or asks to establish constraints, guardrails, or feedback loops for AI agents. Also trigger when users say "prepare my repo for agents", "harness my project", "improve agent workflow", or want their project to work better with Claude Code, Codex, Cursor, or similar AI coding tools. Even if the user doesn't use the word "harness", if they're asking about making a codebase more agent-friendly or productive for AI-assisted development, use this skill.

S.EE (SEE) platform API integration for short URL management, text sharing, and file sharing.

Product thinking tool that helps shape vague ideas into clear, structured design decisions before and during development. Use this skill whenever the user invokes /shape, or asks to "think through" a product idea, "plan out" what to build, "define requirements", "spec out" a feature, "shape" an idea, or wants help deciding what to build before writing code. Also trigger when users say things like "I want to build X but haven't figured out the details", "help me think through this", "what should I consider before building", or "let me scope this out". This skill is about product-level thinking (what to build and why), not implementation planning (how to build it) — the latter is handled by plan mode.

Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API key needed.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Use only when the user explicitly asks to do brainstorming (e.g., says 'brainstorm'/'头脑风暴' or invokes $brainstorming). Do not auto-trigger based on general creative work.

Manage Git worktrees. Use when asked to create/switch/list/merge/remove worktrees, to keep multiple branches in parallel directories, or to clean up worktrees safely during development.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when you have a spec or requirements for a multi-step task, before touching code