Decompose (Grade A)Security-tested data-ai skill for Claude AI. Grade A. Phase 3: Dependency decomposition. Only invoke when explicitly requested by the user or by the yoink orchestrator.

— (0)

Reviewed by Daniel Nikulshyn·Updated July 2026

Overview

Decompose is a security-tested data-ai skill for Claude AI, specifically designed for dependency decomposition. It's part of the Yoink project and should only be invoked explicitly by the user or the Yoink orchestrator. The skill relies on a multi-step process that includes seeding a decomposition queue with a target package, evaluating libraries for decomposition, preparing sub-packages, implementing and validating them, and enqueuing new dependencies. The process involves various scripts and agents, such as the decomp-evaluator and decomp-implementer agents, to manage the decomposition loop until the queue is empty.

Key features

Dependency decomposition
Automated evaluation
Sub-package preparation
Implementation and validation
Enqueuing new dependencies

Pricing

Model: Free
Category: Skills
Rating: No reviews yet

Use cases

Automated Dependency Decomposition

Decompose can be used to automate the process of dependency decomposition for a target package, making it easier to manage complex dependencies.

Security Testing

Decompose's security-tested design makes it suitable for use cases where security is a top priority.

Pros & Cons

Pros

Security-tested
Structured approach to dependency decomposition
Utilizes multiple agents for evaluation and implementation
Automates the process of preparing sub-packages and validating their implementation

Cons

Complex multi-step process
Requires explicit invocation
Depends on various scripts and agents
May require manual intervention to fix baseline test failures

Reviews

No reviews yet. Be the first!

Q&A

How does Decompose handle test failures during the baseline verification step?

If the top‑level generated tests fail, the baseline is considered broken; you need to investigate and fix the failures, then rerun the tests until they all pass before the skill proceeds to the next step.

Asked by Julia Steiner · Dec 25, 2025

What prerequisites must be met before running Decompose?

You must first run the /yoink:curate tests to validate the baseline; only then can you seed the decomposition queue with the target package and start the decomposition loop.

Asked by Isabela Almeida · Nov 24, 2025

When can I safely invoke the Decompose skill?

Decompose must only be invoked explicitly by the user or by the Yoink orchestrator, and never automatically; it should be called after the /yoink:curate tests have successfully completed.

Asked by Anya Sokolova · Sep 20, 2025

Ask a question

Skills alternatives

Manage Headers (Grade A)

Skills

Security-tested development skill for Claude AI. Grade A. Inspects and configures the security headers a Power Pages site sends to browsers — Content Security Policy, frame and clickjacking protection

— (0)

Free

Using Git Worktrees (Grade A)

Skills

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

— (0)

Free

Ga4 Bigquery Schema (Grade A)

Skills

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

— (0)

Free

Meta Capi (Grade A)

Skills

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

— (0)

Free

Callees (Grade A)

Skills

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

— (0)

Free

Test Module Name (Grade A)

Skills

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

— (0)

Free

Board Of Directors (Grade A)

Skills

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

— (0)

Free

Advpl Mvc Avancado (Grade A)

Skills

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)

— (0)

Free