发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
sci-hub
Use when downloading academic papers, journal articles, or research papers by title, DOI, or URL. Downloads via Sci-Hub (sci-hub.st) using curl, with browser fallback if curl is blocked.
research-agent
Use when the user needs a trade-off, risk, or evidence analysis before committing. Trigger phrases: "should I use X or Y", "what are the risks of Z", "compare these approaches", "is there consensus on X", "what do experts recommend for Y", "I've heard conflicting things about X", "what are the known failure modes", "evaluate this library for my use case", "deep dive on topic X", "investigate whether Z is a good idea". Searches across sources, weighs evidence, flags contradictions, and returns a structured report. Works for coding and non-coding topics. Do NOT use when the user wants the exact API/syntax of a library (use docs-agent) or understanding of the current codebase (use codebase-explainer).
markdown-codeblock
Use when the user wants to highlight code in markdown files, including inline code highlighting with {lang} prefix syntax, code blocks with language fences and titles, and transformer marks for diffs, highlights, focus, errors, and warnings. Always read this skill file when inserting code blocks or inline code in markdown.
perfect-design
Premium UI design engineering skill for creating, redesigning, polishing, and judging product-specific interfaces with senior-level craft. Use when Codex works on frontend design, UX/UI, design systems, dashboards, SaaS apps, landing pages, commerce, portfolios, visual polish, interaction quality, or wants output in the spirit of Vercel, Linear, Raycast, Awwwards, and high-end product teams. Composes with no-slop as the anti-generic gate.
us-stock-researcher
US Stock Investment Research Assistant. Supports Gemini Deep Research or Claude Native Deep Research (7-Phase + GoT). Use when analyzing 10-K/10-Q reports or generating investment research reports.
exa-research
Exa.ai deep research and answer generation with citations. Use when building research automation, implementing the Answer API for Q&A with sources, creating research reports, or using deep search with summaries. Triggers on: Exa Answer, answer endpoint, exa.answer, deep search, research API, Exa Research, async research, research report, citation extraction, summarization with sources, fact verification, streaming answers, research tasks.
Senior Project Manager
Converts specs to tasks and remembers previous projects. Focused on realistic scope, no background processes, exact spec requirements
sources-section
Appends a Sources/References section using only web sources from the sources pool.
deploy
Deploy the mobile app using EAS Build and Submit. Use when building for app stores, creating preview builds, or managing releases. Invoked by: "deploy", "build", "release", "eas", "app store", "publish".
octave-compression
Specialized workflow for transforming verbose natural language into semantic OCTAVE structures. REQUIRES octave-literacy to be loaded first
octave-ultra-mythic
Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity.
build-feature
Use when creating or developing a feature, this contains a focused instructions for building features.
spec-writer
Spec Driven Development (SDD) agent. Converts a PRD user story into a formal technical spec: exact function signatures, types, interfaces, API contracts, and DB schema — before any code is written. Use between architect and Ralph. Triggered by: 'write specs', 'create technical spec', 'SDD', '/spec', 'spec for USxxx', 'define the interface for'.
Mental Health Assessment
Generates mental health screening questionnaires and assessment tools with scoring guidelines
Multi-turn Dialogue Manager
Manages multi-turn dialogues with context tracking, slot filling, and conversation state management
OWASP Compliance Checker
Checks web applications against OWASP Top 10 vulnerabilities with remediation guidance
deployment-incident-responder
Respond to deployment incidents by triaging failure signals, isolating root cause, executing safe rollback or forward-fix, and documenting incident outcomes. Use when deploys fail, production errors spike after release, or service health regresses immediately after changes.
amama-session-memory
Use when restoring user context, tracking decisions, or managing availability states. Trigger with session start or preference changes.
codebase-health-auditor
Unified dead code detection, AST-based duplicate detection, and cleanup tool combining Legacy Tech Remover + Comprehensive Auditor + Architectural Cleanup with Knip, depcheck, TypeScript, Vue-specific analysis, file size/token limit detection, and AST-powered refactoring suggestions. Use for dead code, duplicates, oversized files, and architectural issues.
code-review-mean
Code review for MEAN stack apps. Use when reviewing backend (Express + MongoDB) and frontend (React) code for quality, security, architecture compliance, performance, and best practices.
arweave-standards
GitHub repository skill for ArweaveTeam/arweave-standards
conductor
Comprehensive assistance with Conductor
update-docs
Sync documentation from source-of-truth files
elysia
Elysia.js server patterns for error handling, status responses, and plugin composition. Use when writing Elysia route handlers, returning HTTP errors, creating plugins, or working with Eden Treaty type safety.