RCS launches require complete evidence, correct routing, and coordinated approval. This skill builds a reviewable checklist and guides controlled readiness tests.

CPaaS migrations often fail when provider concepts are copied without translation. This skill maps those differences into a phased Sent v3 cutover plan.

AI coding histories can retain credentials after they were shared with a model provider. This skill finds affected records while keeping reported secrets masked.

Browser demonstrations can be difficult to script, narrate, and record consistently. This skill builds and verifies ScreenCI scripts, then records and uploads finished videos.

Manual browser inspection makes reliable automation scripts difficult to author. This skill uses Playwright CLI to navigate pages, capture snapshots, and verify selectors.

Manual web research and scraping can be slow and inconsistent. This skill guides Claude, Codex, and Claude Code through ScrapeGraph CLI workflows.

Notes lose value when projects, responsibilities, and references mix together. This skill classifies Obsidian notes into PARA categories and proposes safe routing, metadata, reviews, and archiving.

Using many AI providers requires separate integrations, keys, and billing workflows. SandBase offers one MCP interface for inference, media, search, scraping, and structured APIs.

Go error paths often lose context, duplicate logs, or expose internals. This skill gives Claude, Codex, and Claude Code concrete rules for safer Go errors.

Go code can pass formatting checks while still being hard to read. This skill guides Claude, Codex, and Claude Code toward clearer style choices.

Code and agent outputs can regress without clear signals. This skill documents Ruflo verification guards, truth scores, reports, and rollback workflows for Claude, Codex, and Claude Code.

Mascot concepts often become detailed illustrations that fail at small sizes. This skill creates simple, product-relevant logo directions with consistent generation constraints.

Complex software work often lacks a consistent path from requirements to completion. This skill applies SPARC phases, specialized modes, and coordinated development workflows.

Agents often lose useful lessons from prior tasks. This skill shows how to store, judge, retrieve, and distill reasoning patterns with AgentDB-backed ReasoningBank.

Manual hook setup can be inconsistent across Claude Code projects. This skill guides automated hook configuration for tasks, sessions, memory, and Git workflows.

Manual releases can miss version, validation, artifact, and communication steps. This skill guides release planning, testing, publishing, deployment, monitoring, and rollback with reusable workflows.

Multi-repository changes are difficult to coordinate and validate consistently. This skill guides discovery, synchronization, testing, architecture standards, and pull request workflows.

Manual pull request review can miss security, performance, and architecture issues. This skill coordinates GitHub CLI workflows and ruv-swarm agents for structured review feedback.

Flow Nexus workflows span many tools and operational domains. This skill provides one guide for accounts, sandboxes, deployments, billing, storage, and monitoring.

Concurrent AI agents can create conflicting changes and repeat failed workflows. This skill documents Agentic Jujutsu methods for coordination, trajectory learning, and integrity checks.