Issue logo

Issue

Organization
skilluse
issue

Create and manage local Issue specs (specs/issues/) - individual work items with testable acceptance criteria. Use for "create issue", "new task", "list issues", "check issues", "pick issue". NOTE - For GitHub issues, use `gh issue` command directly.

Overview

Publisherskilluse
Repositoryskilluse
Skill nameissue
Stars
55
Forks
3
Bundled files
2
LicenseMIT
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Issue 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.
    https://github.com/skilluse/skilluse/tree/main/.claude/skills/issue
  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/skilluse/skilluse.git /tmp/skilluse
mkdir -p .claude/skills
cp -r /tmp/skilluse/.claude/skills/issue .claude/skills/issue
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Issue 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 Issue 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 Issue 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.

Issue - Issue Manager

Create and manage Issues with testable acceptance criteria.

Directory Structure

project/
└── specs/
    ├── epics/
    │   └── epic-name/
    │       ├── epic.md
    │       └── progress.md
    └── issues/
        ├── 20250115-task01-auth-setup/
        │   ├── issue.md                  # Issue requirements
        │   └── feature.json              # Testable acceptance criteria
        └── 20250116-web01-landing-page/
            ├── issue.md
            └── feature.json

What is an Issue?

An Issue is a single work item with testable acceptance criteria.

Components:

  • issue.md - Requirements and technical details
  • feature.json - Tracking work progress with pass/fail status

Naming convention: YYYYMMDD-issueID-short-description/

  • Date prefix: YYYYMMDD
  • Issue ID: taskNN, webNN, cfgNN, bugNN, etc.
  • Short description: auth-setup, landing-page, etc.

When to Use

  • User says "create issue", "new task", "plan feature"
  • Breaking down an Epic into work items
  • Adding a bug fix or enhancement task
  • Updating issue requirements or status

IMPORTANT: Epic Context

Before creating or updating any Issue, you MUST:

  1. Read Epic Context First

    bash
    # Read the related Epic's files
    cat specs/epics/EPIC_NAME/epic.md        # Understand goals and existing issues
    cat specs/epics/EPIC_NAME/progress.md    # Check current sprint status
    ls specs/epics/EPIC_NAME/references/     # Review design docs and specs
  2. After Creating/Updating Issue

    • Update epic.md - Add new issue to "Related Issues" table
    • Update progress.md - Log the action taken
    • Ensure issue aligns with Epic goals and references

This ensures Issues are consistent with Epic's design and requirements.


Creating an Issue

Step 1: Read Epic Context

bash
# Identify the related Epic and read its context
cat specs/epics/EPIC_NAME/epic.md           # Goals, existing issues
cat specs/epics/EPIC_NAME/progress.md       # Current sprint status
cat specs/epics/EPIC_NAME/references/*.md   # Design specs, requirements

Step 2: Create Issue Directory

bash
mkdir -p specs/issues/YYYYMMDD-issueID-short-description

Step 3: Create issue.md

markdown
# [Issue Title]

## Overview
Brief description of what this issue accomplishes.

## Requirements
- Requirement 1
- Requirement 2
- Requirement 3

## Technical Details

### API Endpoints
| Method | Path | Description |
|--------|------|-------------|
| POST | /api/xxx | Description |

### Data Models

Model { field1: type field2: type }


### Dependencies
- Library/package dependencies
- External service dependencies

## Acceptance Criteria
See `feature.json` for testable criteria.

## Issue Dependencies
- [ ] issueNN-xxx (must be completed first)

## Out of Scope
- What this issue does NOT include

Step 4: Create feature.json

json
{
  "issue": "task01-auth-setup",
  "title": "Authentication System Setup",
  "epic": "cli",
  "priority": 1,
  "status": "pending",
  "created_at": "2025-01-15",
  "completed_at": null,
  "dependencies": [],
  "parallelizable": true,
  "features": [
    {
      "id": "F001",
      "category": "functional",
      "description": "User can register with email and password",
      "steps": [
        "Step 1: Navigate to /register",
        "Step 2: Fill in email and password",
        "Step 3: Submit the form",
        "Step 4: Verify success message"
      ],
      "passes": false,
      "notes": ""
    }
  ],
  "metadata": {
    "estimated_sessions": 1,
    "actual_sessions": 0,
    "blockers": []
  }
}

Step 5: Update Epic Context

This step is mandatory. Update the Epic to reflect the new issue:

  1. Update epic.md - Add to "Related Issues" table:

    markdown
    | Issue | Title | Status |
    |-------|-------|--------|
    | task01-auth-setup | Authentication Setup | pending |
  2. Update progress.md - Log the creation:

    markdown
    [YYYY-MM-DD HH:MM] Created issue task01-auth-setup: Authentication Setup

Step 6: Git Commit

bash
git add specs/issues/YYYYMMDD-issueID-*/ specs/epics/EPIC_NAME/
git commit -m "feat: create issue task01-auth-setup"

Updating an Issue

Step 1: Read Epic Context First

bash
# Always read Epic context before making changes
cat specs/epics/EPIC_NAME/epic.md
cat specs/epics/EPIC_NAME/progress.md

Step 2: Update issue.md

Add an "Updates" section to document changes:

markdown
## Updates (YYYY-MM-DD)

### Issue: [Brief description]
- **Problem**: What was wrong
- **Solution**: How it was fixed
- **Files**: Which files were modified

Step 3: Update feature.json

Mark completed features:

json
{
  "id": "F001",
  "description": "Feature description",
  "passes": true,
  "notes": "Fixed YYYY-MM-DD: Brief explanation"
}

Update issue status:

json
{
  "status": "in-progress",
  "completed_at": "2025-01-15"
}

Step 4: Update Epic Context

This step is mandatory. Update both Epic files:

  1. Update epic.md - Change issue status if needed:

    markdown
    | task01-auth-setup | Authentication Setup | completed |
  2. Update progress.md - Log the changes:

    markdown
    [YYYY-MM-DD HH:MM] Updated issue-name: brief description

Issue Sizing Guidelines

SizeFeaturesSessionsExample
Small2-41Add logout button
Medium5-81-2User authentication
Large8+Split it!-

If an issue has more than 8 features, split it into smaller issues.


Parallel Execution

The parallelizable field indicates if an issue can be worked on by a background AI agent.

Set parallelizable: true when:

  • No pending dependencies
  • Work is isolated
  • Clear requirements
  • No frequent human decisions needed

Set parallelizable: false when:

  • Has dependencies on incomplete issues
  • Core architectural changes
  • Requires interactive feedback
  • Will conflict with other work

Rules

  • Each Issue MUST have both issue.md and feature.json
  • All features start with "passes": false
  • Priority 1 = highest priority
  • Dependencies reference other issue IDs
  • Always update the Epic when issue status changes

References

Template files:

  • references/feature.template.json
  • references/issue.template.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Issue AI skill do?

Create and manage local Issue specs (specs/issues/) - individual work items with testable acceptance criteria. Use for "create issue", "new task", "list issues", "check issues", "pick issue". NOTE - For GitHub issues, use `gh issue` command directly.

Why use Issue on TypingMind?

Because you install it once and use it with any model. Issue 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 Issue in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/skilluse/skilluse/tree/main/.claude/skills/issue. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Issue?

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 Issue?

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

Is the Issue AI skill free?

Yes. It is published on GitHub by skilluse under the MIT license. 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 👇