packmind: Skill for Claude Code

.claude/skills/working-with-pm-design-kit/SKILL.md

working-with-pm-design-kit is a skill for Claude Code from PackmindHub/packmind. It costs 91 tokens per session (2,932 once invoked), scanned A, original, Apache-2.0.

A guide to Packmind’s user-interface component library, @packmind/ui, which provides reusable visual building blocks on top of Chakra UI. Chakra UI is a separate library for building web interfaces.

In plain words
What is it for?
Use it when building or modifying Packmind screens, choosing components, styling layouts, or handling inputs and user feedback.
Why use it?
It helps frontend changes follow the application’s existing components, theme, and layout conventions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is PackmindHub/packmind's own configuration. It tells Claude Code how to work on packmind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything packmind configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PackmindHub/packmind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PackmindHub/packmind/main/.claude/skills/working-with-pm-design-kit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PackmindHub/packmind

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for working-with-pm-design-kit

README.md
[![agentmods](https://agentmods.dev/badge/skills/packmindhub/packmind/working-with-pm-design-kit.svg)](https://agentmods.dev/skills/packmindhub/packmind/working-with-pm-design-kit)
Your own site
<a href="https://agentmods.dev/skills/packmindhub/packmind/working-with-pm-design-kit"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/working-with-pm-design-kit.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,932 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.02932
Opus 5 $0.00046 $0.01466
Sonnet 5 $0.00018 $0.00586
Haiku 4.5 $0.00009 $0.00293

Measured 8d ago against content hash 1bde0e3e4672, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

working-with-pm-design-kit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/working-with-pm-design-kit/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working With the PM Design Kit

Overview

The Packmind design kit (@packmind/ui) is a component library built on top of Chakra UI v3. All components are prefixed with PM and provide a consistent, themed API across the application. The source lives in packages/ui/.

Import pattern: Always import from @packmind/ui, never from Chakra UI directly.

import { PMButton, PMBox, PMHeading, PMText } from '@packmind/ui';

Component Selection Guide

Before reaching for a raw <div> or Chakra primitive, check if a PM component exists. Consult references/component-catalog.md for the full inventory organized by category.

Decision Flow

  1. Need a layout container? Use PMBox, PMVStack, PMHStack, PMFlex, or PMGrid.
  2. Need text? Use PMHeading (with level prop for semantic h1–h6) or PMText (with variant and color).
  3. Need a button? Use PMButton with the appropriate variant: primary for main actions, secondary/ghost for secondary, danger for destructive.
  4. Need user input? Use PMInput, PMTextArea, PMSelect, PMCheckbox, PMSwitch, or PMRadioGroup.
  5. Need feedback? Use pmToaster for transient messages, PMAlert for inline messages, PMConfirmationModal for destructive confirmations.
  6. Need an overlay? Use PMDialog for modals, PMPopover for contextual info, PMDrawer for side panels.
  7. Need to show nothing? Use PMEmptyState with title, description, icon, and an action button.
  8. Need loading placeholders? Use PMSkeleton for content areas, PMSpinner for inline indicators.
  9. Need a color indicator? Use PMColorSwatch to display a color sample.
  10. No PM wrapper exists? Check Chakra UI v3 docs, then ask the user before using a raw Chakra component.

Compound Component Patterns

Several PM components use Chakra's compound pattern with dot notation. Always use the compound API — do not try to reconstruct these with standalone elements.

// Dialog
<PMDialog.Root open={isOpen} onOpenChange={setIsOpen}>
  <PMDialog.Backdrop />
  <PMDialog.Positioner>
    <PMDialog.Content>
      <PMDialog.Header>
        <PMDialog.Title>Title</PMDialog.Title>
        <PMDialog.CloseTrigger />
      </PMDialog.Header>
      {/* body */}
    </PMDialog.Content>
  </PMDialog.Positioner>
</PMDialog.Root>

// Accordion
<PMAccordion.Root>
  <PMAccordion.Item value="section-1">
    <PMAccordion.ItemTrigger>Section 1</PMAccordion.ItemTrigger>
    <PMAccordion.ItemContent>Content here</PMAccordion.ItemContent>
  </PMAccordion.Item>
</PMAccordion.Root>

// Timeline
<PMTimeline.Root>
  <PMTimeline.Item>
    <PMTimeline.Separator>
      <PMTimeline.Indicator />
      <PMTimeline.Connector />
    </PMTimeline.Separator>
    <PMTimeline.Content>
      <PMTimeline.Title>Event</PMTimeline.Title>
      <PMTimeline.Description>Details</PMTimeline.Description>
    </PMTimeline.Content>
  </PMTimeline.Item>
</PMTimeline.Root>

// Tabs (compound pattern — preferred for flexible tab layouts)
<PMTabsCompound.Root defaultValue="tab1">
  <PMTabsCompound.List>
    <PMTabsCompound.Trigger value="tab1">First Tab</PMTabsCompound.Trigger>
    <PMTabsCompound.Trigger value="tab2">Second Tab</PMTabsCompound.Trigger>
  </PMTabsCompound.List>
  <PMTabsCompound.Content value="tab1">First content</PMTabsCompound.Content>
  <PMTabsCompound.Content value="tab2">Second content</PMTabsCompound.Content>
</PMTabsCompound.Root>

Read the full file on GitHub · 341 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 341 lines · 91 tokens per session scan A 1bde0e3e4672

Subscribe to this mod's changes

working-with-pm-design-kit is a skill published in the GitHub repository PackmindHub/packmind (309 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 2,932 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.