Navigating Design Jira Process logo

Navigating Design Jira Process

Organization
bitwarden
navigating-design-jira-process

Move design work through Bitwarden's Product and Design Jira workflow — final designs attached to tickets, the 30/60/90 critique cadence tracked in Figma, status transitions on engineering epics and stories, and the one-off engineering story flow.

Overview

Publisherbitwarden
Repositoryai-plugins
Skill namenavigating-design-jira-process
Stars
149
Forks
19
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bitwarden on GitHub. Read the source before you install it.

Installation

Install the Navigating Design Jira Process AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bitwarden/ai-plugins.git /tmp/ai-plugins
mkdir -p .claude/skills
cp -r /tmp/ai-plugins/plugins/bitwarden-design-tools/skills/navigating-design-jira-process .claude/skills/navigating-design-jira-process
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Navigating Design Jira Process in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Navigating Design Jira Process on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Navigating Design Jira Process is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Navigating the Product and Design Jira Process

This skill grounds Jira moves in the design team's current practice for plugging into engineering's Jira workflow. The goal: keep design decisions visible alongside the engineering work — without maintaining a parallel design tracker. Designs are attached directly to the engineering tickets they belong to, and everything substantive (30/60/90 critique iterations, copy, annotations) lives in Figma.

A note on status names below. Jira status labels appear here in the same casing Jira uses them — IN DESIGN, IN PROGRESS, DONE, DESIGN NEEDED, Ready for Dev. Copy them verbatim when transitioning tickets.

The structural rule

Designs are attached directly to tickets. The Figma file lives in the engineering Epic's "Design" field (or, for one-off engineering stories, in the story's "Design" field). There is no parallel design project, no parallel design Kanban, and no per-stage design tasks.

That's the design-team-Jira insight in one sentence. Everything else is choreography around this rule.

Epic-driven flow

Initial setup

  • A PM creates at least one Epic to accompany every Product Initiative document they're working on.
  • PM assigns the Epic to the designated designer.

In Design

  • Designer (or PM) moves the Epic to IN DESIGN.
  • Designer runs the 30/60/90 critique cadence in Figma — no separate Jira tasks per stage. Stage iterations, attached materials (stakeholder presentations, research), and cross-iteration feedback all live in the Figma file alongside the work.

Design Done

  • In Figma, group final designs on a single page with named Sections for each story-level surface.
  • Designer links the Figma file in the Epic's "Design" field.
  • Designer marks Figma sections as "Ready for Dev".
  • EM moves the Epic to Ready for Dev to signal engineering can pick the work up. (Some teams have automation that handles this; treat it as the EM's responsibility for now.)

Engineering technical breakdown

  • When engineering creates stories during technical breakdown, designer + PM + the engineer doing the breakdown together review the stories.
  • For each story, ensure the correct Figma section is linked and that the section's content is only about that story. One-to-one mapping.

In Progress (and dev support)

  • PM or EM moves the Epic to IN PROGRESS when development starts.
  • PM/EM creates a dev-support task titled [project name] - dev support, assigns it to the project's designer, and links it as "relates to" all engineering stories needing design support. (This convention persists for now even as other separate-design-task work has retired.)
  • The task lets the designer know when their project enters development and represents the misc support needed throughout.
  • When the last engineering task is done, the dev-support task is also marked DONE.

One-off engineering stories

Some stories aren't tied to an epic — common on the UI Foundation team. The flow is shorter:

  • An engineering story is created outside an epic; PM or EM realizes design support is needed. (Or: a designer working on a component improvement for UIF creates the story themselves.)
  • PM or EM moves the story to DESIGN NEEDED and assigns it to the feature team's designer.
  • Designer does the design work in Figma. No separate design task is created.
  • When the design is complete, the designer:
    1. Links the Figma file to the story's "Design" field.
    2. Unassigns themselves from the story.
    3. Adds a comment in the ticket noting the design is ready to be picked up.

The three closing steps — link, unassign, comment — are explicit. Skipping any of them leaves the story stuck in someone's queue or visible-but-not-discoverable.

Composing with other skills

  • preparing-design-handoff. The transitions at the end of In Design (Figma linked, sections marked Ready for Dev, EM moves Epic) are the pre-handoff side of the handoff process. The handoff skill is the gate / checklist; this skill is the canonical lifecycle.
  • evolving-design-system-components. Component Library work generates Jira issues on the Component Library board. Those follow the same rule (designs attached to tickets), but feature-team-owned recipes generate stories in the feature team's project rather than the Component Library project. Surface the difference explicitly to the designer.

Common mistakes to catch

  • Forgetting to mark Figma sections "Ready for Dev." Engineering can't find what's final. This is part of Design Done, not optional.
  • Sections not aligned to stories. When engineering creates stories, each story should map to a Figma section whose content is only that story. Mismatch creates ambiguity at review time.
  • One-off engineering story left unfinished at the design end. All three closing steps must happen — link Figma to the story's "Design" field, unassign self, comment that the design is ready. Missing any one of them leaves the ticket in an ambiguous state.
  • PM creating the dev-support task too late or not at all. When dev support isn't visible on the Epic, dev support requests come at the designer without warning. Surface this gap when reviewing a project's Jira state.

Output format

When asked to set up or move work through the Jira process:

  1. Project shape — is this an epic-driven project or a one-off engineering story?
  2. Current state — what Jira entities exist (Epic, story, dev-support task) and their current statuses.
  3. Moves to make — the specific status transitions and Figma links to apply, named by responsibility (designer, PM, EM).
  4. Figma links — what to attach where (Epic "Design" field, story "Design" field).
  5. Watch-outs — the common mistakes above that apply to this specific project.

Frequently asked questions

What does the Navigating Design Jira Process AI skill do?

Move design work through Bitwarden's Product and Design Jira workflow — final designs attached to tickets, the 30/60/90 critique cadence tracked in Figma, status transitions on engineering epics and stories, and the one-off engineering story flow.

Why use Navigating Design Jira Process on TypingMind?

Because you install it once and use it with any model. Navigating Design Jira Process is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Navigating Design Jira Process in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitwarden/ai-plugins/tree/main/plugins/bitwarden-design-tools/skills/navigating-design-jira-process. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Navigating Design Jira Process?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Navigating Design Jira Process?

As many as you like. As long as a model supports skills, you can use Navigating Design Jira Process with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Navigating Design Jira Process AI skill free?

It is published on GitHub by bitwarden. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇