cascade-post-design-questions-to-jira

cascade-post-design-questions-to-jira is a skill for Claude Code from bitovi/cascade-mcp. It costs 64 tokens per session (596 once invoked), scanned A, original, MIT.

A Jira comment formatter that posts design-behavior questions grouped by Figma frame. Jira is a work-tracking tool, and Figma is a collaborative design tool.

In plain words
What is it for?
Use it after generating questions when you want to add one structured comment with links to the relevant design frames.
Why use it?
It keeps review questions in the source Jira issue instead of leaving them in a separate discussion.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cascade-mcp plugin — 13 skills shipped together

Good fit Use it after generating questions when you want to add one structured comment with links to the relevant design frames.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bitovi/cascade-mcp/cascade-post-design-questions-to-jira
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add bitovi/cascade-mcp --skill cascade-post-design-questions-to-jira
Clone the repo
git clone --depth 1 https://github.com/bitovi/cascade-mcp

Made for: Claude Code.

Or install cascade-mcp, the plugin that ships this one along with the rest of its 13 skills.

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 cascade-post-design-questions-to-jira

README.md
[![agentmods](https://agentmods.dev/badge/skills/bitovi/cascade-mcp/cascade-post-design-questions-to-jira/github.svg)](https://agentmods.dev/skills/bitovi/cascade-mcp/cascade-post-design-questions-to-jira)
Your own site
<a href="https://agentmods.dev/skills/bitovi/cascade-mcp/cascade-post-design-questions-to-jira"><img src="https://agentmods.dev/badge/skills/bitovi/cascade-mcp/cascade-post-design-questions-to-jira/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cascade-post-design-questions-to-jira

Your own site · 80×15
<a href="https://agentmods.dev/skills/bitovi/cascade-mcp/cascade-post-design-questions-to-jira"><img src="https://agentmods.dev/badge/skills/bitovi/cascade-mcp/cascade-post-design-questions-to-jira.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 596 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 $0.00064 $0.00596
Opus 5 $0.00032 $0.00298
Sonnet 5 $0.00013 $0.00119
Haiku 4.5 $0.00006 $0.00060

Measured 12d ago against content hash 29710a39a2ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cascade-post-design-questions-to-jira 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 12d 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.

plugins/cascade-mcp/skills/cascade-post-design-questions-to-jira/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post Questions to Jira

Post behavior questions as a structured comment on the source Jira issue. All questions are combined into a single comment, organized by Figma frame with links.

When to Use

Use after generate-behavior-questions has produced frame-specific questions and the user confirms they want to post them to Jira.

Typical trigger: User says "post to Jira" or "yes, add to PROJ-123" after reviewing generated questions.

Required Input

  • Questions organized by Figma frame (output from generate-behavior-questions)
  • Jira issue key (e.g., PROJ-123) — the issue to comment on

Procedure

1. Format questions as markdown

Combine all frame-specific questions into a single markdown comment:

## Behavior Questions

### [Login Screen](https://www.figma.com/design/abc123?node-id=1-234)

1. ❓ Should the "Remember me" checkbox be checked by default?
2. ❓ What error message appears for invalid credentials?

### [Dashboard](https://www.figma.com/design/abc123?node-id=5-678)

1. ❓ Is the widget layout user-configurable?

---
_Generated by Cascade feature review_

Formatting rules:

  • Top-level ## Behavior Questions heading
  • Each frame as ### [Frame Name](figma-url) — clickable link in Jira
  • Numbered questions under each frame
  • Footer separator with generation attribution

2. Post the comment

Call MCP tool atlassian-add-comment with:

  • issueKey: The Jira issue key (e.g., PROJ-123)
  • markdownText: The formatted markdown comment

The tool handles markdown → ADF (Atlassian Document Format) conversion automatically.

3. Report results

Confirm to the user:

  • Which issue received the comment
  • Total number of questions posted
  • Link to the Jira issue for verification

Important Notes

  • Single comment — all questions go in ONE Jira comment, not one per frame or per question
  • Markdown input — the atlassian-add-comment tool accepts markdown and converts to ADF internally
  • Frame links are clickable — Figma URLs in markdown become clickable links in the Jira comment
  • No duplicate posting — if the user runs this again, it posts a NEW comment (doesn't update the old one). Warn the user if they're about to post duplicate questions.

Read the full file on GitHub · 70 lines

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. 12d ago First seen · 70 lines · 64 tokens per session scan A 29710a39a2ff

Subscribe to this mod's changes

cascade-post-design-questions-to-jira is a skill published in the GitHub repository bitovi/cascade-mcp (24 stars, last pushed 23d ago), licensed MIT. It adds 64 tokens to every session and 596 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

huashu-keynote-black

OpenDesign's all-hands: the year in review, the three priorities, and what every team owns next quarter. Built as a decision-grade corporate strategy deck for whole company.

nexu-io/open-design · 43 tokens

kanban-board

A Kanban board is a visual task list with columns for stages such as To do, In progress, In review, and Done. It can show filters, labels, due dates, assignees, comments, and swimlanes that group cards.

nexu-io/html-anything · 26 tokens

acid-blue-business

A visual presentation style for modern business topics, using electric blue with black, white, and grey, directional layouts, and clear spacing. It is intended for business content rather than traditional data dashboards.

arcsin1/oh-my-ppt · 0 tokens

design-inventory

Use to run the Claude Design to ClosedLoop pipeline against the current web-ui. Stage A inventories a design export zip into schema-validated findings (typed design units - screens, regions like nav bars, standalone components like a chat dialog; UX and behavioral changes; Storybook component reuse mapping; token…

closedloop-ai/claude-plugins · 173 tokens

visual-dashboard

Start a browser-based dashboard that visualizes architecture, implementation plans, and project status. Persists artifacts in .bigpowers/dashboard/. Reads specs/state.yaml, release-plan.yaml, epics, and planning-status via HTTP API or opencode panel.

danielvm-git/bigpowers · 52 tokens

contribution-workflow

Create or document a contribution workflow for a design system — the multi-stage process for evaluating, accepting, and shepherding new contributions through to publication. Trigger when someone says: how should someone contribute, contribution process, adding a new component, contribution guidelines, what's the…

murphytrueman/design-system-ops · 99 tokens