Loading...
Loading...
Found 11,542 Skills
Systematic Learning Material Generator. Given a new field/technology/concept, AI conducts independent research, builds a knowledge system, and generates HTML learning materials (including framework/cases/engineering/controversies + blind spots). Triggered when the user says "I want to learn X / Help me systematically break down X / I want to master the field of X / Help me organize the full picture of X / Conduct in-depth research on X and explain it systematically / Master X thoroughly". Not applicable for "Is X feasible / Why Y" (use long-research), "What interesting cases are there in X" (use case-radar for scattered cases), "Organize these materials into HTML" (use readable-output to process existing materials), article writing (use writing-assistant), design drafts (use design-exploration).
Converge vague requirements into a goal contract (scope / non-goals / success criteria / verification / stop conditions) that another AI can execute autonomously and be accepted. This skill only writes goal contracts, **never executes tasks for users**. Hard trigger condition: This goal is to be handed over to others for execution — subagent, Codex, another AI session, or another person. It is used to write goals, optimize goals, revise handoff prompts, or turn requests like "finish today, optimize as much as possible, help me research and execute" into task contracts that the executor won't guess randomly or overstep boundaries. Not applicable to: internal team requirement management and version breakdown (use issue-pool — it produces tasks for humans to start working on, not contracts for AI), interface design exploration (use design-exploration), PRD/acceptance criteria/test case documents (use prd-test-writer), framework planning and version roadmaps (use issue-pool), and situations where the user actually wants you to **do the task directly** — just do it directly instead of using this skill to turn the task into a document.
Push projects to GitHub with three automatically determined modes: **First-time Push** (large file scanning → generate .gitignore → git init → create repo via gh → push), **Daily Update** (commit + push), **Version Release** (tag + create Release, optional attached download files). Core principle: Safety First: Must scan for large files and sensitive files before pushing, better to ask one more question than push something that shouldn't be pushed. Triggered when users say "push to GitHub", "git push", "upload to GitHub", "commit and push", "release version", "create release", "create tag", "/git-push". Not applicable for: Planning which features go into which version number (use issue-pool—this skill only handles tagging pre-determined version numbers), complex git operations like rebase/cherry-pick/resolving conflicts/modifying history/rolling back (use git commands directly, this skill does not cover these), self-testing and acceptance before code is completed.
Explain the Ralph Loop plugin, how it works, and available skills. Use when the user asks for help with ralph loop, wants to understand the technique, or needs usage examples.
Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers via the Cursor SDK, and collect structured handoffs; do not invoke autonomously.
Screen US stocks for Stockbee-style selling-exhaustion hammer setups using prior momentum, pullback depth, undercut/reclaim, long lower-wick geometry, close-location, volume confirmation, quality/liquidity gates, and risk-distance scoring. Use when the user asks for Stockbee, Pradeep Bonde, exhaustion setup, selling exhaustion, hammer reversal, undercut reclaim, near-close reversal candidates, or pullback entries in high-quality funds-owned stocks.
Cria templates visuais padronizados para canais digitais. Use para Instagram, LinkedIn, cabeçalhos de email, thumbnails e banners do YouTube.
Use when the user asks to file, open, or create a PR (pull request), or says "file and babysit".
Primary entry point for topic audience identification in Eva Audience Finder 2.2.8. Only use this when the user explicitly calls /eva-audience-finder, mentions "Topic Audience Identifier", or clearly asks questions like "Who is the audience behind this topic, who does it really resonate with, who is this topic for, who cares about it". Break down topics, buzzwords, titles, phenomena or comments into specific audiences, cognitive gaps, user problems and subsequent content entry points. Do not take over general topic discussion requests such as "I have an idea for a topic", "Help me look at this topic", "Want to chat"; these should still be handled by eva-think. Do not directly generate complete title proposals or full drafts.
Eva Learn 2.2.8 Independent Learning Project Entry. Use this when users explicitly say /eva-learn, eva-learn, Eva Learn, or clearly request in natural language such as "walk me through mastering", "guide me through systematic learning", "walk me through reading", "thematic reading", or "continue my previous learning". All Learn tasks must first establish or restore traceable archives before starting teaching in the same round; do not handle ordinary explanations, creation, revision, title drafting, commercial draft finalization, or converting materials into short videos/articles. Trigger methods: /eva-learn, eva-learn, Eva Learn, enter Eva Learn mode, walk me through mastering, guide me through systematic learning, walk me through reading, conduct question-based learning, conduct thematic reading, continue Eva Learn learning project, continue previous learning project, continue the guided reading from last time.
Eva Preflight 2.2.8 Pre-publication Review Entry. It is used to review the basically finalized, unpublished natural language content drafts of users themselves or their teams when users explicitly request "pre-publication check, final draft check, can this be published, full review before publication, what are the critical flaws in this draft"; it reads only existing titles, openings, logic, facts, expression assets, and Brief truth sources according to scenarios such as short videos, articles, general social media, or commercial orders, and provides three levels of publication judgments and one next-step action. Do not use it when only topics, materials, or outlines are provided; submit published content to eva-review; do not use it for action plans, code, product releases, and deployment acceptance.
Configure and optimize gw-tools for different project types and team needs. Use this skill when setting up gw for new projects, configuring auto-copy files, troubleshooting configuration issues, or customizing gw for Next.js, Node.js APIs, monorepos, or React SPAs. Triggers on tasks involving .gw/config.json, auto-copy patterns, environment files, or gw init commands.