github-issue-enhancer

Files (2)

• README.md
• SKILL.md

SKILL.md (first lines)

# GitHub Issue Enhancer Workflow

Transform raw GitHub issues into agent-ready specifications by detecting gaps, clarifying requirements, and adding structure through interactive questioning.

## When to Use

Trigger this skill when the user wants to:

- Enhance a GitHub issue with missing details
- Prepare an issue for autonomous agent processing
- Add acceptance criteria and technical context
- Structure an unstructured issue description
- Fill information gaps before handing off to an agent

## Step 1 — Retrieve the Issue

Get the issue content from the user or GitHub API:

**If issue number provided:**

```bash
gh issue view <issue-number> --json title,body,labels,assignees,comments
```

**If issue content provided directly:**
Parse the markdown content to extract:

- Title
- Description/Body
- Labels
- Any existing comments or context

Store the original issue content for comparison.

## Step 2 — Initial Analysis

Analyze the issue for completeness using these criteria:

### Required Elements Checklist

- [ ] Clear title describing the work
- [ ] Problem statement or goal description
- [ ] Expected behavior/outcome
- [ ] Acceptance criteria (explicit or implicit)
- [ ] Technical context or constraints
- [ ] Priority or urgency indication
- [ ] Related issues or dependencies
- [ ] Definition of "done"

### Gap Detection

For each missing element, note:

- What information is absent
- Why it matters for agent execution
- What questions need to be asked

### Quality Assessment

Rate the issue on:

- **Clarity**: Is the goal unambiguous?
- **Completeness**: Can an agent execute without guessing?
- **Actionability**: Are next steps clear?
- **Testability**: Can success be measured?

## Step 3 — Interactive Q&A Session

Based on detected gaps, ask targeted questions to gather missing information. Use `ask_user_question` for structured choices when applicable.

### Common Question Categories

#### 1. Problem Understanding

```text
Question: "What specific problem does this issue address?"
Options:
- Bug fix (unexpected behavior)
- Feature request (new capability)
- Technical debt (refactoring/improvement)
- Documentation (missing or unclear docs)
- Infrastructure (devops, deployment, config)
```

#### 2. Scope Definition

```text
Question: "What should be in scope for this work?"
Options:
- Minimal viable fix only
- Core functionality + basic edge cases
- Full implementation with error handling
- Complete solution with tests and docs
```

#### 3. Technical Constraints

```text
Question: "Are there technical constraints to consider?"
Options:
- Must maintain backward compatibility
- Performance requirements exist
- Security/compliance requirements
- Integration with existing systems
- No constraints, full flexibility
```

#### 4. Success Criteria

```text
Question: "How should success be measured?"
Options:
- All existing tests pass
- New tests added and passing
- Manual verification steps defined
- Performance benchmarks met
- User acceptance criteria satisfied
```

From woernfl/ai-lab, MIT.

More from woernfl/ai-lab