Agent skills for Claude Code

Configure Adobe local development with App Builder CLI, Runtime actions,

Execute major Adobe re-architecture: migrating from legacy Adobe APIs

Implement Adobe-specific lint rules, CI policy checks, and runtime guardrails

Execute Adobe production deployment checklist covering credential management,

Implement Adobe reference architecture for production integrations covering

Implement reliability patterns for Adobe APIs: circuit breakers for

Manages the lifecycle of Architecture Decision Records (ADRs) to document technical choices and design rationale in Simplified Chinese.

Creates new Architecture Decision Record (ADR) documents for significant architectural changes using a consistent template and…

Build or rebuild the ADR index + dependency graph by running scripts/import.mjs (handles v3-style and plugin-style ADR formats; one Bash…

Action-Domain-Responder pattern knowledge base.

Reconcile the ADR index against a DELETED ADR file or relation line by dropping and rebuilding adr-patterns + adr-edges from scratch…

Review an Architectural Decision Record (ADR) using a team of six specialist reviewer subagents and produce a consolidated report as both…

Research, spy on, and analyze ads across Meta (Facebook & Instagram), Google (Ads Transparency Center + paid search results), TikTok (Ads…

Advanced architecture stress analysis methodology for designing systems that survive unknown stresses.

Equips Claude with 25 specialized engineering capabilities for complex architecture, system automation, and platform operations.

When to activate: pytest plugins, conftest, custom markers, test architecture, fixtures design, pytest-xdist, coverage strategies

When to activate: design patterns in Python, dependency injection, factory pattern, observer, command, strategy

Master high-performance rendering for large datasets with Datashader.

Cross-vendor adversarial code review of the current branch.

Multi-model adversarial review of a high-stakes or contested question.

Adversarial Quarto vs Beamer QA. Critic finds issues, fixer applies fixes, loops until APPROVED (max 5 rounds).