Agent skills for Claude Desktop

Break through stagnation with lateral thinking personas — single or multi-persona debate

First-touch experience for new Ouroboros users

Audit first-party B2B outbound cohorts and calculate channel-correct funnel conversion, leakage, fully loaded CAC, first-year gross…

Transactional outbox pattern for reliable event publishing.

Outbox Pattern knowledge base. Provides patterns, antipatterns, and PHP-specific guidelines for transactional outbox, polling publisher…

Assemble and coordinate the smallest appropriate Many Hats team for a cross-functional product problem.

Transform output-based feature lists into outcome-driven Now/Next/Later roadmaps using the "so what?" technique.

Design a structured outdoor learning sequence embedding curriculum objectives in an available outdoor space.

Search, read, and manage Outline wiki documents.

Configure and understand different output formatting styles for Claude Code responses.

Use when the user explicitly types `ov dream` or `ov recall ` and the request should be routed to the OpenViking sync/recall CLI…

Auto-generate API documentation from code and comments.

Store objects with R2's S3-compatible storage on Cloudflare's edge.

Run Python code in the cloud with serverless containers, GPUs, and autoscaling.

Maintain one documented z-index ladder for overlay tiers (base → sheet → dialog → floating content → toast → blocking alert).

Playwright browser automation (OpenClaw AI snapshots).

Gives the work-selection snapshot for the current Git repository's octa workflow: a read-only Markdown section per active Project plus…

Skill de entrada para qualquer trabalho de integração com a API da Tray.

Apply this skill whenever writing or reviewing code that handles user input, makes external API calls, scrapes websites, stores…

How to use @owlmeans/llm-common — runtime-free serializable contracts for LLM inference and execution (ModelProvider…

For own expert opinion — Section 109 SGG: defines norm, burden of proof and counter-argument; result: test product with risk and next step.