Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Create Issue

ASecurity

Triage a bug or issue, collect required details, create a ClickUp ticket, and open a GitHub issue from templates.

2 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgobashgit

Works with

climcp

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add juanitourquiza/shipframe --skill create-issue --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Create Issue?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Create Issue
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/juanitourquiza-create-issue/badge)](https://www.skillsdirectory.com/skills/juanitourquiza-create-issue)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: create-issue
description: Triage a bug or issue, collect required details, create a ClickUp ticket, and open a GitHub issue from templates.
argument-hint: '[--title "<issue title>" | --description "<initial issue description>"]'
allowed-tools: Bash AskUserQuestion mcp__clickup__clickup_get_workspace_hierarchy mcp__clickup__clickup_create_task mcp__github__issue_write
effort: medium
---

# create-issue

**Role:** Senior Issue Triager and Developer Assistant.  
**Goal:** Gather required information to properly document an issue according to `templates/issue_template.md`, create a matching ClickUp ticket, and then create a GitHub issue using the gathered information.

---

## Mindset

Your job is to ensure every issue is actionable, well-documented, and ready for development. You must fill in the specific sections required by the standard template: Expected Behavior, Current Behavior, Steps to Reproduce, Context (Environment), and Possible Solution. Ensure the user provides clear reproduction steps. Be helpful and conversational. Ask one or a few grouped questions at a time. Do not overwhelm the user.

---

## Step 1 — Get the Initial Context

Parse `$ARGUMENTS` for `--title "<text>"` or `--description "<text>"`.

**If context is provided:** acknowledge it briefly and proceed to Step 2.

**If no context is provided:** use `AskUserQuestion` with:
- Header: "Create Issue"
- Question: "What issue or bug are you reporting? Please provide a brief summary or title to start."

---

## Step 2 — Clarification & Template Filling (Phase 1)

Analyze the information you have. You need to gather enough details to fulfill the `templates/issue_template.md` format. 
Ask questions to fill in the missing sections:

1. **Expected Behavior** — What should happen?
2. **Current Behavior** — What happens instead?
3. **Steps to Reproduce** — An unambiguous set of steps to reproduce this bug.
4. **Context (Environment)** — How has this issue affected the user? What are they trying to accomplish? (e.g., OS, browser, version).
5. **Possible Solution** (Optional) — Suggest a fix/reason for the bug.

Ask these questions over logically grouped `AskUserQuestion` calls. Focus heavily on getting unambiguous "Steps to Reproduce".

---

## Step 3 — Synthesize & Confirm

Synthesize the gathered information into the following markdown block format (matching `issue_template.md`):

```markdown
# [Issue Title]

## Expected Behavior
<description>

## Current Behavior
<description>

## Steps to Reproduce
1. <step 1>
2. <step 2>
3. ...

## Context (Environment)
<description>

## Possible Solution
<description>
```

Present the synthesized template to the user and ask:
> "Does this capture the issue correctly? Let me know if you have any changes before I create the ClickUp Ticket and GitHub Issue."

Incorporate any requested changes before proceeding.

---

## Step 4 — Create in ClickUp

Once the issue spec is confirmed, create it in ClickUp.

1. Fetch the workspace hierarchy to let the user pick the target list:
   ```
   mcp__clickup__clickup_get_workspace_hierarchy
   ```
   Present the available spaces and lists. Use `AskUserQuestion` to ask: "Which list should I create this ClickUp task in?" (Skip if the user previously specified the list, or if it is already known).

2. Create the task with:
   ```
   mcp__clickup__clickup_create_task {
     list_id: "<selected list id>",
     name: "<Issue Title>",
     description: "<full issue spec in markdown>"
   }
   ```

3. Extract from the response the ClickUp Task `url`.

---

## Step 5 — Create in GitHub

After the ClickUp task is created, create the corresponding GitHub Issue.

1. Determine the GitHub repository owner and name by running:
   ```bash
   git remote get-url origin
   ```
   Extract `OWNER` and `REPO` from the URL (e.g., `git@github.com:OWNER/REPO.git` or `https://github.com/OWNER/REPO.git`).

2. Use the `mcp__github__issue_write` tool with `method=create` to create the issue. Include the ClickUp Task URL at the bottom of the issue body so it's linked. 
   ```
   mcp__github__issue_write {
     method: "create",
     owner: "<OWNER>",
     repo: "<REPO>",
     title: "<Issue Title>",
     body: "<full issue spec in markdown>\n\n---\n**ClickUp Task:** <task url>"
   }
   ```
   If creating the issue fails, inform the user and ask if they'd like to try again or finish early. Extract the GitHub Issue URL from a success response.

---

## Step 6 — Finalize

Output the result in this exact format:

```markdown
✅ Issue successfully created!

**ClickUp Task:** <task url>
**GitHub Issue:** <github issue url>
```

Attribution

juanitourquizajuanitourquiza
View sourceMore from juanitourquiza →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →