Skip to content
TrustedSkillsbeta
Back to all skills

Co Design

Checked
am-will·vlatest·frontend

Collaboratively brainstorms and refines design concepts with users, iteratively improving ideas based on feedback.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add am-will/swarms --skill co-design -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

am-will

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned am-will/swarms at 110268148a.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
110268148a
Manifest
skills/co-design/SKILL.md
Scanned
1 file, 246 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill, Co-Design, orchestrates parallel subagents to execute tasks defined in a markdown plan file. It intelligently routes tasks based on their nature – design or standard – using different execution methods. Design tasks (those involving UI/UX elements) are handled by a Claude instance with CLI capabilities, while other tasks utilize standard Task tool subagents. This allows for collaborative brainstorming and iterative refinement of design concepts.

When to use it

  • Frontend development: When you need to build or modify user interfaces, including styling, layout, and component creation.
  • Design system implementation: To manage and implement design tokens, themes, and UI components consistently.
  • Iterative design refinement: When collaborating with users to improve design concepts through feedback loops.
  • Complex projects with mixed tasks: When a project involves both frontend design and backend logic, ensuring the design aspects are handled appropriately.

Key capabilities

  • Plan file parsing: Reads and parses markdown plan files containing task definitions.
  • Task classification: Automatically classifies tasks as either "design" or "standard" based on predefined criteria (CSS, HTML, React/Vue/Svelte/Angular components, etc.).
  • Parallel execution: Executes multiple tasks concurrently using parallel subagents.
  • Dependency management: Handles task dependencies specified within the plan file (depends_on).
  • Design Task Routing: Launches design-related tasks via claude -p with CLI access and specific allowed tools.
  • Standard Task Routing: Executes standard tasks using the "Task" tool subagent.

Example prompts

  • “Run the plan file ‘design_plan.md’.”
  • “Execute tasks T1 through T3 from the plan file ‘project_plan.md’."
  • "Process 'website_layout.md' and focus on improving the card component design.”

Tips & gotchas

  • Plan File Format: The skill requires a markdown plan file with clearly defined task sections (e.g., ### T1: Task Name:).
  • Design vs. Standard Classification: If a task mixes design and standard elements, it should be classified as a "design" task to ensure appropriate handling.
  • CLI Access for Design Tasks: The Claude instance used for design tasks has limited CLI access via --allowedTools.