issue-enricher

Transforms rough requirements into well-structured GitHub issues. Use when the user provides a vague idea, feature request, or problem description and wants to create a GitHub issue. Analyzes codebase, explores solution approaches, researches relevant libraries, and generates actionable issues using `gh` CLI.

465 stars

byphodal

View on GitHub Installation ↓

Best use case

issue-enricher is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using issue-enricher should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/issue-enricher/SKILL.md --create-dirs "https://raw.githubusercontent.com/phodal/routa/main/.claude/skills/issue-enricher/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/issue-enricher/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How issue-enricher Compares

Feature / Agent	issue-enricher	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

## Process

### 1. Understand the Requirement

Extract from user input:
- **Core problem/goal**: What needs to be solved?
- **Mentioned constraints**: Tech stack, performance, compatibility
- **Referenced files/APIs**: `@file.yaml`, existing code paths
- **Related issues**: Links to parent or related issues

If the task is enriching an existing GitHub issue rather than creating a new one:
- Treat `docs/issues/` as the local issue knowledge base when it is available
- Search for mirrored GitHub issues and prior local issue reports before proposing a new direction
- Call out duplicate or related issues explicitly in the output

### 2. Codebase Analysis

Search the codebase to understand context:
```
- Existing patterns for similar features
- Related modules and their architecture
- Relevant configuration files
- Test patterns used in the project
- Existing local issue files under docs/issues/ that provide historical context
```

### 3. Solution Exploration

For each potential approach, research:
- **Libraries/Tools**: Search npm, crates.io, PyPI for relevant packages
- **Trade-offs**: Performance, complexity, maintenance burden
- **Integration effort**: How it fits with existing architecture

Generate 2-3 distinct approaches when multiple solutions exist.

If one requirement actually contains multiple distinct features:
- Split it into multiple issue proposals instead of forcing one umbrella issue
- Keep each issue independently implementable and testable
- Explicitly explain why you split or why you kept items together
- Do not emit search narration or work logs; output final issue drafts only

### 4. Create GitHub Issue

Use `gh issue create` with structured content:

```bash
gh issue create \
  --repo {owner}/{repo} \
  --title "Brief, action-oriented title" \
  --body "$(cat <<'EOF'
# Problem

[1-2 sentences describing the core problem]

## Context

- Current behavior: ...
- Desired behavior: ...
- Related: #issue-number (if applicable)

## Proposed Approaches

### Approach 1: [Name]

**Libraries**: `package-name` (v1.x) - [brief description]

**Pros**:
- ...

**Cons**:
- ...

**Estimated effort**: Small/Medium/Large

### Approach 2: [Name]

...

## Recommendation

[Which approach to start with and why]

## Out of Scope

- [Explicitly excluded items]

## Labels

`enhancement`, `area:...`
EOF
)"
```

## Issue Quality Checklist

- [ ] Title is specific and action-oriented
- [ ] Problem statement is clear without implementation details
- [ ] Each approach has concrete library/tool recommendations
- [ ] Trade-offs are honest (not just pros)
- [ ] Effort estimates are realistic
- [ ] Out of scope is defined to prevent scope creep
- [ ] Links to related issues/PRs included
- [ ] Related History section cites prior issues or explicitly says none were found

## Tips

- **Don't over-specify**: Focus on the problem, not implementation steps
- **Research libraries**: Use web search to find current, maintained options
- **Reference existing code**: Point to patterns already in the codebase
- **Keep it scannable**: Use headers, bullets, and code blocks
- **Label thoughtfully**: Match project's existing label conventions

## Output

Each issue draft must include:
- A `Related History` section citing concrete prior issues or `None found after searching docs/issues/`
- A `Recommendation` section choosing one approach
- An `Out of Scope` section
- Final drafts only, no chain-of-thought or search transcript

After creating the issue:
1. Confirm the issue URL
2. Summarize what was created
3. Note any assumptions made that user should verify

Related Skills

issue-garbage-collector

465

from phodal/routa

Two-phase cleanup of duplicate and outdated issue files in docs/issues/. Phase 1 uses Python script for fast pattern matching. Phase 2 uses claude -p for semantic analysis on suspects only.

spreadsheets

465

from phodal/routa

Use this skill for spreadsheet creation, editing, analysis, formatting, formula modeling, charting, or workbook review. Triggers include requests to create or modify an .xlsx file, build a model or tracker, format a workbook, add formulas or charts, or prepare a shareable spreadsheet deliverable.

slide

465

from phodal/routa

Use this skill as reference material when creating or editing presentation slide decks.

pdf

465

from phodal/routa

Use this skill for PDF generation, conversion, inspection, extraction, editing, form filling, OCR, redaction, or render comparison. Triggers include requests to create a PDF, convert Markdown or HTML or LaTeX or DOCX or PPTX to PDF, extract text or tables or images, fill or inspect forms, OCR scans, compare revisions, or redact content.

docx

465

from phodal/routa

Use this skill for creating, editing, and reviewing DOCX files, including generation, formatting, content controls, tracked changes, comments, accessibility checks, redaction, rendering, and diff-based QA workflows.

pr-verify

465

from phodal/routa

Comprehensive PR verification skill. Analyzes PR body requirements, reviews comments, checks CI status, and performs E2E testing. Use when a PR is ready for final verification before merge.

playwright-cli

465

from phodal/routa

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

evolution-architecture-review

465

from phodal/routa

Multi-agent architecture evolvability review for this repository. Use when the user wants to analyze current architecture quality, evolvability, fitness functions, coupling, boundary clarity, delivery flow, or phased evolution strategy. Designed to be invoked from Claude Code with prompts like `/evolution-architecture-review analyze the current architecture evolvability`.

slack

465

from phodal/routa

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

electron

465

from phodal/routa

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

dogfood

465

from phodal/routa

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

agent-browser

465

from phodal/routa

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.