Unvetted agent skills can hide prompt injection, credential theft, persistence, or unsafe dependencies. This skill combines offline scanning with guided semantic review.

GitHub Actions workflows can expose credentials, repositories, and releases through subtle configuration errors. This skill applies a structured security review and proposes concrete fixes.

Manual feature testing can miss edge cases and leave evidence scattered. This skill plans browser scenarios, captures results, uploads media, and creates a structured Alan report.

Pull request reviews often miss context or produce vague feedback. This skill gathers GitHub evidence and posts focused, line-specific findings through Alan MCP tools.

Complex software changes need plans grounded in the existing codebase. This skill clarifies requirements, drafts visual plans, and stores versioned artifacts in Alan.

Server-side Supabase authentication and client setup can be easy to misconfigure. This skill provides current patterns for secure handlers, webhooks, adapters, and migrations.

Slow queries and schema drift can make Postgres apps hard to scale. This skill gives AI agents Supabase-backed rules for indexes, RLS, pooling, and diagnostics.

Supabase projects change quickly, and outdated guidance can create database or auth defects. This skill directs Claude, Codex, and Claude Code to verify docs, use safe workflows, and check Supabase security concerns.

Sharing pages and documents securely can require several tools and manual steps. This skill publishes content and manages ShareOne links from one workflow.

Teams need clear requirements before assigning work to AI coding agents. This skill turns feature ideas into structured PRDs with user stories and quality gates for ralph-tui workflows.

Teams often need a clean task file before ralph-tui can execute a PRD. This skill converts requirements into structured user stories with dependencies and quality gates.

Large PRDs are difficult to turn into executable ralph-tui work. This skill converts PRD stories into beads with dependencies and quality gates.

PRDs can be hard to turn into small, executable agent tasks. This skill converts a PRD into ralph-tui bead plans with quality gates and dependencies.

Stripe version changes can break API responses, webhooks, and SDK clients. This skill gives structured guidance for planning, testing, and completing upgrades.

Developers often need databases, auth, hosting, and API credentials without leaving their coding workflow. This skill guides Claude, Codex, and Claude Code through Stripe Projects CLI provisioning steps.

China market launches can fail when public claims exceed verified product evidence. This skill creates localized Chinese messaging and a launch plan that keeps claims, channels, and buyer expectations aligned.

Long sources make key information difficult to review. This skill uses the Summarize CLI to extract or condense URLs, documents, transcripts, audio, and video.

Dynamic websites often fail with simple fetch tools. This skill guides Claude, Codex, and Claude Code to use Steel cloud browsers for scraping, navigation, screenshots, PDFs, and sessions.

Tokenized asset workflows combine multiple APIs, wallets, chains, signatures, and jurisdiction rules. This skill organizes Treasures Finance discovery, portfolio, quote, trade, bridge, and troubleshooting steps.

Multi-agent coding tasks can lose ownership, status, and completion signals. This skill guides Claude, Codex, and Claude Code through Orca orchestration commands for supervised dispatch, gates, and worker completion.