AI Skills

Use OpenAI Codex from inside Claude Code for code reviews and delegated background tasks.

Deprecated. Renamed to paseo-epic. Loading this skill redirects to paseo-epic and tells the user.

Draft or improve README docs.

Plan and execute safe refactoring using dependency analysis

Work like Manus: Use persistent markdown files as your \"working memory on disk.\"

End-to-end skill for building, testing, linting, versioning, and publishing a production-grade Python library to PyPI. Covers all four build backends (setuptools+setuptools_scm, hatchling, flit, poetry), PEP 440 versioning, semantic versioning, dynamic git-tag versioning, OOP/SOLID design, type hints (PEP 484/526/544/561), Trusted Publishing (OIDC), and the full PyPA packaging flow. Use for: creating Python packages, pip-installable SDKs, CLI tools, framework plugins, pyproject.toml setup, py.typed, setuptools_scm, semver, mypy, pre-commit, GitHub Actions CI/CD, or PyPI publishing.

Designs technical solutions and architecture. Use when user says "design solution", "architecture design", "technical design", or "方案设计" WITHOUT mentioning PRD. For PRD-specific work, use prd-planner skill instead.

When the user wants to create or optimize a shipping or delivery information page. Also use when the user mentions "shipping," "delivery," "shipping policy," "delivery times," "shipping page," "free shipping," "shipping rates," "delivery options," "shipping info," "cross-border shipping," "international delivery," or "order tracking." For legal overview, use legal-page-generator.

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

Audit websites for SEO, technical, content, security, JS rendering, and AI readiness using SEOmator CLI. Returns LLM-optimized reports with health scores across 251 rules and 20 categories. Use when analyzing websites, debugging SEO issues, or checking site health.

Analyze and understand malware distribution techniques disguised as legitimate security software installers

Trace artifact provenance.

Recognize and warn against malicious software distribution repositories masquerading as legitimate security tools

Reference for netlify.toml configuration. Use when configuring build settings, redirects, rewrites, headers, deploy contexts, environment variables, or any site-level configuration. Covers the complete netlify.toml syntax including redirects with splats/conditions, headers, deploy contexts, functions config, and edge functions config.

When the user wants to plan product distribution via marketplaces, app stores, or third-party platforms. Also use when the user mentions "distribution channels," "marketplace listing," "app store listing," "Figma plugin," "Chrome extension marketplace," "AWS Marketplace," "Shopify app," "GPTs store," "app distribution," or "third-party marketplace." For channel mix, use integrated-marketing.

Configure, diagnose, and use lossless-claw effectively in OpenClaw, with emphasis on key settings, summary health, and recall-tool usage.

Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the user's setup, determines which tests can run automatically, executes them with pass/fail evaluation, and produces a structured test results report.

PyTorch implementation of TurboQuant for LLM KV cache compression using two-stage vector quantization (random rotation + Lloyd-Max + QJL residual correction).

When the user wants to add, optimize, or audit breadcrumb navigation. Also use when the user mentions "breadcrumbs," "breadcrumb trail," "breadcrumb nav," "breadcrumb links," "path navigation," "site breadcrumb," "BreadcrumbList schema," "location-based breadcrumb," "attribute-based breadcrumb," "site hierarchy display," "add breadcrumbs," or "breadcrumb SEO." For BreadcrumbList JSON-LD, use schema-markup. For main nav, use navigation-menu-generator.

When the user wants to set up or update their social media profile, voice, audience, content pillars, or platform preferences. Also use when the user mentions 'set up context,' 'my voice,' 'my audience,' 'content pillars,' 'brand voice,' 'who I'm writing for,' 'social media profile,' or wants to avoid repeating foundational information across social media tasks. Use this at the start of any new project before using other social media skills — it creates .agents/social-media-context-sms.md that all other skills reference.

When the user wants to add, optimize, or audit social share buttons (share article to X, LinkedIn, Facebook, etc.). Also use when the user mentions "share buttons," "social share," "share to X," "share to LinkedIn," "social sharing," "share icons," "share widget," "native share," "Web Share API," or "share intent URLs." For link previews, use open-graph.

Audit web pages for performance optimization following PageSpeed Insights guidelines. Use when analyzing page performance, optimizing web applications, reviewing performance metrics, implementing Core Web Vitals improvements, or when the user mentions page speed, performance optimization, Lighthouse scores, or Core Web Vitals.

Build ETL pipelines and analytics dashboards using Harvard Art Museums API data with Python, SQL, and Streamlit

WXT browser extension performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring WXT browser extension code to ensure optimal performance patterns. Triggers on tasks involving WXT, browser extensions, content scripts, service workers, messaging, and extension APIs.

When the user wants to find information sources for content ideation, competitor monitoring, or industry tracking. Also use when the user mentions "research sources," "information sources," "content ideation," "industry monitoring," "competitor monitoring," "market intelligence," "content research," or "topic research." For keywords, use keyword-research.

End-to-end data engineering and analytics application for Harvard Art Museums API with ETL pipelines, SQL analytics, and Streamlit visualization

Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.