- Home
- Skills
- Workflow Automation
- gh issues
Works with the AI Agents you already use
gh issues
Decompose complex feature requests into atomic, dependency-mapped GitHub issues via the GitHub CLI.
Free
gh issues
Example session with this skill installed
Break down the request 'Implement JWT-based authentication for the API' into GitHub issues for this repo.
- Read your context and instructions
- Compiled the gh issues
I have analyzed the current codebase and verified that JWT utilities are not yet present. I checked gh issue list and found no conflicting tickets.
Proposed Issue Breakdown
| Issue Title | Scope | Dependencies |
|---|---|---|
| Auth: Add JWT library and configuration | Install jsonwebtoken, set up secret management, and create utility helpers. | None |
| Auth: Implement User Login endpoint | Create /api/login route, verify credentials, and return a signed JWT. | JWT library |
| Auth: Create JWT Middleware | Implement passport or custom middleware to protect routes and decode payloads. | JWT library |
| Auth: Secure existing Profile routes | Apply the JWT middleware to /api/profile and update tests. | JWT Middleware |
Acceptance Criteria for Issue #1:
jsonwebtokenadded topackage.json.JWT_SECREThandled via environment variables.- Helper functions created for
signTokenandverifyToken. - Unit tests cover token generation and expiry.
Next steps
- Review the dependency graph above for circular blockers.
- Confirm if I should use the
backendlabel or create a newarea/authlabel. - Type
approveto begin creating these issues on GitHub.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing complex feature requests requires breaking them down into manageable chunks before a single line of code is written. This skill converts high-level goals into a structured graph of atomic, independently mergeable GitHub issues. It prevents scope creep and avoids the noise of poorly defined tickets by enforcing a strict decomposition process.
What it does
- Goal decomposition identifies vertical slices of work that provide value and can be merged independently.
- Dependency mapping builds an acyclic graph to ensure blockers are identified and resolved in the correct topological order.
- Environment auditing checks current repo labels, existing issues, and issue templates to maintain consistency with project standards.
- Codebase survey reads existing data models and architecture to ensure proposed issues do not conflict with the current system.
- Bulk issue creation automates the generation of tickets in the correct order, linking dependencies via GitHub blocked-by relationships.
How it works
- Context gathering uses the GitHub CLI to verify the repo, check for duplicate issues, and fetch active labels.
- Strategy proposal generates a table showing the proposed titles, dependencies, and one-line scopes for user approval.
- Sequence execution creates the blocker issues first to ensure every dependency link points to a valid, existing ticket.
- Relationship management groups large feature sets under a parent issue and records sub-issue relationships without overwriting bodies.
Frameworks & tools
This skill uses the GitHub CLI (gh) for authentication, repository inspection, and issue management. It integrates with project files like .github/ISSUE_TEMPLATE/ and AI_MEMORY.md.
Why this beats prompting it yourself
Writing clear acceptance criteria and manual dependency tracking is tedious and prone to logical errors like circular blockers. This skill automates the repo discovery and CLI commands required to keep tickets in sync with the actual state of the codebase.
Use cases
- Split a large "Add SSO" request into specific auth, UI, and backend tasks.
- Map out the migration of a legacy data importer to a resumable architecture.
- Generate a sequence of PR-ready tasks for a new microservice implementation.
- Audit a messy feature request and organize it into a parent-child issue hierarchy.
Known limitations
Requires a functional GitHub CLI installation and active authentication. It cannot create labels that do not exist without explicit user permission.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 2 days ago
- Free to download with an account