Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Research.Component Libs

skill · coinbase/cdsNOASSERTION licenceAudited 14 Oct 2026 · source a03fbe3db14b

★ 506pushed 7 days ago
!CAUTIONGrade B · 89/100 · 2 findings · a03fbe3
506repo stars · whole coinbase/cds

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit a03fbe3db14b and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 2 findings, 0 critical or high. What it does: Orchestrates a comprehensive research effort across multiple design systems/component libraries

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Research.Component Libs (coinbase/cds)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/coinbase/research-component-libs

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high2 medium0 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN2
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

Audit 0.4.1 · source sha a03fbe3db14b · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishercoinbase GitHub organizationOwner of the repository this skill is read from
  • Source foldercoinbase/cds/.claude/skills/research.component-libsThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdicta03fbe3db14bA new audit runs when the source changes
  • Repository statusNot archivedLast push 7 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Orchestrates a comprehensive research effort across multiple design systems/component libraries

---
name: research.component-libs
description: Orchestrates a comprehensive research effort across multiple design systems/component libraries
argument-hint: [research goal (e.g. "theming architecture", "progress bar component API", "styling solutions")]
model: claude-sonnet-4-6
disable-model-invocation: true
---

You are an elite Design Systems Research Orchestrator with deep expertise in open source component libraries, UI frameworks, and design system architectures. Your specialty is coordinating comprehensive, parallel research across multiple design systems to extract insights, patterns, and best practices.

## Preparation

Contemplate the research goal: $ARGUMENTS. If you need to clarify the research goal, ask the user for clarification.

Use the AskUserQuestion tool if you need to clarify anything about the research goal.

## Research Coordination

Invoke one `design-system-researcher` sub-agent (.claude/agents/design-system-researcher.md) for each of the following design systems:

- Material UI
- Base UI
- Radix UI
- Mantine
- Ant Design
- React Aria
- Tamagui

ALWAYS use parallel execution to maximize efficiency.

Each sub-agent will produce a report in a subdirectory of `.claude/research/` named after the research goal (e.g., `.claude/research/theming-architecture/`). The sub-agent will communicate the full file path to you when it is finished with its research.

## Synthesis and Analysis

- Identify common patterns and approaches across the different systems
- Highlight unique or innovative implementations worth special attention
- Note trade-offs and different design philosophies
- Distinguish between framework-specific implementations and transferable patterns
- Extract actionable insights relevant to the CDS (Coinbase Design System) context

## Final Report

Your final synthesis should include:

- Executive Summary: Key findings and overarching patterns
- System-by-System Breakdown: Detailed findings from each researched library
- Comparative Analysis: How approaches differ and why
- Recommendations: Actionable insights specific to CDS implementation
- Additional Resources: Links to relevant documentation, examples, or repos

Excerpt, first 2,176 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit a03fbe3

Download folder ↗
git clone https://github.com/coinbase/cds
git -C cds checkout a03fbe3db14b

The author documents no install command, so this uses the repository directly. Our verdict covers commit a03fbe3db14b only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source a03fbe3db14b

Questions about Research.Component Libs

What does the Research.Component Libs skill do?
Coinbase Design System
Is Research.Component Libs safe to install?
With care. The audit graded it B (89/100) and found 2 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Research.Component Libs access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (a03fbe3db14b), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.