Model Training
Model training is the process of teaching machine learning models to
Model Optimization
Model optimization is process of improving machine learning models for
Label Studio Setup
'Label Studio is an open-source data labeling platform that provides
Distributed Training
'This skill covers **when and how** to scale training beyond a single
Data Preprocessing
Data preprocessing is a critical step in machine learning pipelines that
Algorithmic Self Discovery
Algorithmic Self-Discovery is the God-Mode protocol that enables AI agents
Technical Debt Management
Technical debt is the implied cost of additional rework caused by choosing
System Thinking
System thinking is a holistic approach to understanding complex systems
Swarm Collaboration
Swarm Collaboration enables multiple AI agents with different personas
Skill Router
The Skill Router is the cognitive orchestrator that dynamically loads
Skill Generator
The Meta-Skill Generator is the foundational cognitive engine that instructs
Self Validation Cicd
Self-Validation CI/CD provides an automated pipeline for testing AI-generated
Risk Assessment
Risk assessment is a systematic process of identifying, analyzing, and
Problem Framing
Problem framing is the critical first step before any implementation,
Intelligence Router
The Intelligence Router implements the "Twin-Engine" Intelligence Architecture
Decision Records
Architecture Decision Records (ADRs) are lightweight documents that capture
Architectural Reviews
Architectural Reviews is a critical process for evaluating system designs
explore-test
>-
code-review
>-
address-findings
>-
internalize
>-
commit
Creates a git commit with proper message formatting. Use when committing staged changes with a descriptive commit message.
prompt-doctor
>-
pr
Creates or updates a GitHub pull request for the current branch. Use when ready to submit code changes for review.
plan-ticket
>-
weekly-report-generator
从Git提交记录生成专业工作周报。支持单周/多周批量生成、多项目汇总、自定义模板（Markdown/Word）。自动将技术术语转换为业务语言，补充下周计划/本周总结/问题和风险章节。使用场景：(1) 从Git日志生成本周工作汇报 (2) 将多个项目的提交记录汇总为一份周报 (3) 基于自定义Word模板生成领导要求的格式 (4) 批量生成一个月或多周的周报
multi-agent-creator
通用多子智能体系统创建器。基于主子交互模式快速搭建任意业务的多智能体系统。分析业务流程、推荐智能体类型、生成提示词模板。使用场景：(1) 用户说'创建多子智能体系统'或'搭建multi-agent系统'时触发 (2) 需要主子架构的自动化流程 (3) 数据处理流水线、内容生成、代码审查等场景 (4) 需要并行/串行编排多个子任务
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
worktree-manager
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.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
shape
>
brainstorming
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.
codex-skill-creator
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.
cubox-research
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.
dev-browser
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.
exa-web-search
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.
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
harness
>
memos
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.
readwise-research
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.
see
S.EE (SEE) platform API integration for short URL management, text sharing, and file sharing.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
frontend-design-extractor
Extract reusable UI/UX design systems from frontend codebases: design tokens, global styles, components, interaction patterns, and page templates. Use when analyzing any frontend repo (React/Vue/Angular/Next/Vite/etc.) to document or migrate UI/UX for reuse across projects. Focus on UI/UX only; explicitly ignore business logic and domain workflows.
google-gemini-media
Use the Gemini API (Nano Banana image generation, Veo video, Gemini TTS speech and audio understanding) to deliver end-to-end multimodal media workflows and code templates for "generation + understanding".
dns-troubleshooter
It's not DNS / There's no way it's DNS / It was DNS. Diagnose and troubleshoot DNS issues including delegation verification, record conflicts, authoritative vs local DNS comparison, and SPF validation. Use when encountering NXDOMAIN errors for URLs that should exist, verifying DNS delegation is correct, checking for conflicting DNS records, comparing what authoritative nameservers say vs local resolvers, or validating SPF records for email deliverability.
code-review
Perform thorough code reviews on pull requests, diffs, or code changes. Use when asked to review code, check a PR, or provide feedback on changes.
react-development
React patterns, anti-patterns, and performance optimization. Use when writing React components, reviewing React code, or debugging React issues.
solid-development
SolidJS patterns, reactivity model, and best practices. Use when writing Solid components, reviewing Solid code, or debugging Solid issues.
image-gen
Generate compelling cover images and in-article illustrations for technical articles using the imagen CLI tool. Use when asked to "generate images", "create cover image", "make article illustrations", "create visual assets", or "add images to article". Handles both high-impact conceptual cover images and technical diagrams/illustrations for specific concepts. Includes prompt engineering best practices and SEO-friendly image integration.
Page 1368 of 1713 · 85639 results
