AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.
devrel-strategy
Design a developer relations program's charter—business driver, goals, pillar mix, audience priority, and build-vs-buy decisions.
devtools-pricing-strategy
Design pricing architecture, value metrics, and tier ladders for developer tools.
mapbox-store-locator-patterns
Build store locators and location-based search apps with Mapbox GL JS patterns.
n8n-loops-official
Handle loops, batches, pagination, and rate-limiting in n8n workflows.
sveltekit-structure
SvelteKit structure guidance. Use for routing, layouts, error handling, SSR, or svelte:boundary. Covers file naming, nested layouts, error boundaries, pending UI, and hydration.
oss-launch
Plan and execute an open-source project launch end-to-end, from name clearance through GitHub Trending and post-launch measurement.
openclaw-audit-watchdog
Automated daily security audits for OpenClaw agents with DM delivery and optional email reporting. Runs deep audits, creates or updates a recurring cron job, and sends formatted reports to configured recipients.
wordpress-setup
Connect to WordPress sites via WP-CLI over SSH or REST API with verified access and saved config.
compose-state-authoring
Use when writing or reviewing Jetpack Compose code with bare local var in a @Composable, remember { mutableStateOf(...) }, mutableStateListOf/mutableStateMapOf, or @ReadOnlyComposable.
tailwind-patterns
Tailwind CSS v4 patterns: CSS-first configuration, container queries, and modern design token architecture.
handover
Generate comprehensive handover documentation for AEM Edge Delivery Services projects across multiple audiences.
python-testing
Expert in Python testing with pytest and test-driven development
qdrant-monitoring-debugging
Diagnose Qdrant production issues via metrics and observability—optimizer status, memory, and query latency.
audience-growth-tracker-sms
Track follower growth, identify what drives new audiences, and analyze audience development trends.
caveman
Token-saving terse mode — no filler, no narration, just results
planetscale-safe-orchestrator
Master orchestrator for complete PlanetScale safety assessment—inventory, engine review, Insights, Traffic Control, webhooks, schema, instrumentation, and agent model—with unified recommendations and
n8n-extending-mcp-official
Expose n8n workflows as callable MCP tools to fill API gaps or invoke custom business logic.
developer-quickstart-guide
Write or audit developer quickstarts that get readers from zero to verified success in minimal time.
llm-app-patterns
Production-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best practices.
full-output-enforcement
Enforce complete, unabridged code generation without placeholders or truncation.
huashu-proofreading
三遍审校降低AI检测率，让文章更有人味。当用户提到"AI味太重"、"像AI写的"、"降低AI检测率"、"审校"、"自然一些"时使用。
postmortem
Blameless 5-Whys analysis to extract learning from failures and build a change register.
wcag-accessibility-audit
Comprehensive WCAG 2.1/2.2 accessibility audit across POUR principles with A/AA/AAA conformance levels.
day3-clarify
Learn to clarify vague requirements, build custom skills, and submit your first GitHub PR.
literature-review
Conduct a systematic literature review on an academic topic. Use when the user asks for a literature review, survey, or systematic overview of a research area.
planetscale-autonomous-execution-mode
Execute approved PlanetScale changes end-to-end autonomously when operator explicitly acknowledges risk.
experiment-code
Generate and iteratively improve ML experiment code for research papers with training pipelines, debugging, and result optimization.
rag-retrieval
Production RAG patterns: embeddings, hybrid search, reranking, HyDE, agentic retrieval, and pgvector indexing.
ionic-design
Build beautiful native-looking mobile apps with Ionic Framework components and Capacitor.
pp-hackernews
Hacker News from your terminal — with a local SQLite store, snapshot history, and agent-native output no other HN tool has. Trigger phrases: `check hacker news`, `search hn`, `what is hn saying about`, `diff the hn front page`, `pulse on hn`, `look up hn user`, `hn who is hiring`, `hn top stories`, `use hackernews`, `run hackernews`.