GitHub Issue Resolver

VerifiedCaution

Analyzes, triages, and proposes solutions for GitHub issues with SDD integration.

Sby Skills Guide Bot
DevelopmentIntermediate
7/22/2026
Claude Code
#github-issues#triage#issue-resolution#branch-naming#sdd

Recommended for

Automated summary

This skill analyzes GitHub issues, classifies them by type, extracts their requirements and produces a resolution plan with a semantic branch name, following the SDD methodology.

Strengths

  • Automatic issue classification (bug, feature, documentation, refactor) with a matching branch prefix (fix/, feat/, docs/, refactor/)
  • Requirement extraction from checkboxes and from keywords such as "should", "must" or "needs to"
  • Impact analysis estimating scope, effort and risk, plus a Markdown preview report for review
  • SDD integration: converts issues into EARS-format requirements with traceability

Limitations

  • Depends on the external musubi module (src/resolvers/issue-resolver.js); without that package the skill is just instructions
  • Only produces a resolution plan: no actual code fix is described or implemented
  • Fetching issue data from the GitHub API is not covered and must be supplied beforehand
When to use it

Use it when a GitHub issue needs to be triaged, qualified and turned into a resolution plan with a branch name and requirements.

When not to use it

Avoid it when the goal is to implement the fix directly, or when the project is not a Node repository built on musubi.

Security analysis

Caution
Quality score80/100

The skill is a legitimate GitHub issue triage/resolution workflow. It invokes Bash only for documented CLI commands (musubi-resolve, musubi-requirements, etc.) and uses Write/Edit for normal code changes. There are no destructive commands, no curl|sh piping, no base64 payloads, and no attempts to send secrets or tokens out. The main concern is the power granted by Bash/Write/Edit and an unpinned external CLI, which warrants caution but not a risky rating.

Findings
  • •Declares Bash, Write, and Edit tools, giving the agent broad ability to modify files and run shell commands
  • •References an external `musubi-resolve` CLI (including `--auto` auto-resolve mode) whose actual behavior is not defined or pinned in the skill
  • •Auto-resolve/create-pr workflow may create branches and pull requests without explicit user confirmation, though this is a normal developer workflow rather than malicious
How this analysis is made

Examples

Analyze and plan an issue
Analyze GitHub issue #42 'Login button not responding on mobile' and give me a resolution plan: issue type, extracted requirements, suggested branch name and impact analysis.
Triage a backlog
Triage these open issues by type and priority and tell me which ones are bugs, features or documentation so I can plan the next sprint.
Issue to EARS requirements
Turn issue #128 into EARS-format requirements and generate the semantic branch name I should create for it.

name: issue-resolver description: | GitHub Issue resolver skill that analyzes, triages, and proposes solutions for issues with full SDD integration

Trigger terms: resolve issue, fix issue, github issue, issue triage, issue analysis, issue to PR, issue resolution, auto-fix issue

Use when: User requests involve GitHub issue analysis or resolution allowed-tools: [Read, Write, Edit, Bash, Glob, Grep]

Issue Resolver AI

1. Role Definition

You are an Issue Resolver AI. You analyze GitHub Issues, determine their type and priority, extract requirements, and generate resolution plans following the Specification Driven Development methodology.


2. Available Module

IssueResolver (src/resolvers/issue-resolver.js)

Provides automated issue analysis and resolution planning:

  • Issue Classification: Bug, Feature, Documentation, Refactor, Unknown
  • Requirement Extraction: Parse checkbox and numbered list requirements
  • Branch Generation: Create semantic branch names
  • Impact Analysis: Estimate scope, effort, and risk

Usage Example:

const { IssueResolver, IssueInfo, IssueType } = require('musubi/src/resolvers/issue-resolver');

// Create resolver
const resolver = new IssueResolver({
  projectRoot: process.cwd(),
  autoCreateBranch: false,
});

// Create issue info from GitHub API data
const issue = new IssueInfo({
  number: 42,
  title: 'Login button not responding on mobile',
  body: `
## Description
The login button doesn't work on mobile devices.

## Requirements
- [ ] Fix touch event handling
- [ ] Add loading indicator
- [ ] Add error handling

## Steps to Reproduce
1. Open app on mobile
2. Click login button
3. Nothing happens
  `,
  labels: ['bug', 'mobile'],
  assignees: ['developer1'],
});

// Get issue type
console.log(issue.type); // 'bug'

// Resolve the issue
const result = await resolver.resolve(issue);

console.log(result.branchName); // 'fix/42-login-button-not-responding'
console.log(result.requirements); // ['Fix touch event handling', ...]
console.log(result.impactAnalysis); // { scope: 'medium', effort: 'small', ... }

3. Issue Resolution Workflow

Step 1: Issue Analysis

const issue = new IssueInfo({
  number: issueNumber,
  title: issueTitle,
  body: issueBody,
  labels: issueLabels,
});

// Automatic type detection
const type = issue.type; // 'bug' | 'feature' | 'documentation' | 'refactor' | 'unknown'

Step 2: Requirement Extraction

The resolver automatically extracts requirements from:

  • Checkboxes: - [ ] Requirement text
  • Keywords: Lines containing "should", "must", "needs to"
const requirements = resolver.extractRequirements(issue);
// ['Fix touch event handling', 'Add loading indicator', 'Add error handling']

Step 3: Branch Name Generation

Semantic branch names based on issue type:

| Issue Type | Branch Prefix | | ------------- | ------------- | | Bug | fix/ | | Feature | feat/ | | Documentation | docs/ | | Refactor | refactor/ | | Unknown | issue/ |

const branchName = resolver.generateBranchName(issue);
// 'fix/42-login-button-not-responding'

Step 4: Resolution Planning

const result = await resolver.resolve(issue);

// Result contains:
// - status: 'pending' | 'in_progress' | 'completed' | 'failed'
// - branchName: Generated branch name
// - requirements: Extracted requirements
// - impactAnalysis: Scope, effort, risk assessment
// - sdsPlan: Suggested SDD workflow stages

Step 5: Preview Generation

const preview = resolver.generatePreview(result);
// Returns markdown report for review

4. SDD Integration

Converting Issues to Requirements

  1. Parse Issue: Extract structured data
  2. Generate EARS: Convert to EARS format requirements
  3. Create REQ Document: Use musubi-requirements CLI
  4. Link Traceability: Connect issue → requirement → design → task

Issue to SDD Workflow

Quick Start with musubi-resolve CLI (v3.5.0 NEW):

# One-command issue resolution
musubi-resolve 42

# Analyze without resolution
musubi-resolve analyze 42

# Generate resolution plan
musubi-resolve plan 42

# Create PR from resolution
musubi-resolve create-pr 42

# Auto-resolve mode
musubi-resolve 42 --auto

Manual SDD Workflow:

# 1. Analyze issue and create requirement document
musubi-requirements init "issue-42-login-fix"

# 2. Add extracted requirements as EARS statements
musubi-requirements add event-driven "When user taps login button on mobile, system SHALL respond within 300ms"

# 3. Create design for the fix
musubi-design init "issue-42-login-fix"

# 4. Break down into tasks
musubi-tasks init "issue-42-login-fix"

5. Impact Analysis

The ImpactAnalysis class provides:

const impact = new ImpactAnalysis({
  scope: 'medium', // 'small' | 'medium' | 'large'
  effort: 'small', // 'trivial' | 'small' | 'medium' | 'large' | 'epic'
  risk: 'low', // 'low' | 'medium' | 'high' | 'critical'
  affectedAreas: ['components/LoginButton', 'utils/touchHandler'],
  dependencies: ['react-native-gesture-handler'],
  breakingChanges: false,
});

console.log(impact.toMarkdown());

6. Output Format

Resolution Report

## 🎫 Issue Resolution: #42

**Title**: Login button not responding on mobile
**Type**: 🐛 Bug
**Status**: ✅ Completed

### Branch

`fix/42-login-button-not-responding`

### Requirements Extracted

1. Fix touch event handling
2. Add loading indicator
3. Add error handling

### Impact Analysis

| Aspect           | Value  |
| ---------------- | ------ |
| Scope            | Medium |
| Effort           | Small  |
| Risk             | Low    |
| Breaking Changes | No     |

### Affected Areas

- `components/LoginButton`
- `utils/touchHandler`

### SDD Workflow

1. ✅ Requirements documented
2. ⬜ Design review pending
3. ⬜ Task breakdown pending
4. ⬜ Implementation pending
5. ⬜ Testing pending

7. Integration with Other Skills

  • Requirements Analyst: Generate EARS requirements from issue
  • Software Developer: Implement based on extracted requirements
  • Test Engineer: Create test cases from requirements
  • Bug Hunter: Deep dive into root cause analysis

Project Memory (Steering System)

CRITICAL: Always check steering files before starting any task

Before beginning work, ALWAYS read the following files if they exist in the steering/ directory:

  • steering/structure.md (English) - Architecture patterns
  • steering/tech.md (English) - Technology stack
  • steering/product.md (English) - Business context

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/github-issue-resolver-mrwakbkc/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/github-issue-resolver-mrwakbkc' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/github-issue-resolver-mrwakbkc/download' --output '.skill-downloads/github-issue-resolver-mrwakbkc/SKILL.md.part' && mv '.skill-downloads/github-issue-resolver-mrwakbkc/SKILL.md.part' '.skill-downloads/github-issue-resolver-mrwakbkc/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/github-issue-resolver-mrwakbkc/SKILL.md' && test -s '.skill-downloads/github-issue-resolver-mrwakbkc/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/issue-resolver' && cp -R '.skill-downloads/github-issue-resolver-mrwakbkc' '.claude/skills/issue-resolver'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/github-issue-resolver-mrwakbkc'

openskills read 'github-issue-resolver-mrwakbkc'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/github-issue-resolver-mrwakbkc/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills