Joe Jiang
Community@J0Jng · 中国
Nice to meet you. AI Agent developer · Math student @ GDUT · LangGraph / FastAPI / Docker
Agent Skills by Joe Jiang
Showing 17 vetted skills indexed across 1 GitHub repositories.
improve-codebase-architecture
Scan a codebase for shallow modules and present deepening refactors as a visual HTML report.
research
Investigate questions against primary sources and save cited findings as Markdown files.
domain-modeling
Build and maintain project domain glossaries and architectural decision records.
wayfinder
Plans large efforts as decision tickets on an issue tracker and resolves them incrementally.
setup-matt-pocock-skills
Configures a repository's issue tracker, triage labels, and domain doc layout for engineering skills.
diagnosing-bugs
Diagnose hard bugs and performance regressions through a structured six-phase feedback-loop workflow.
code-review
Reviews a git diff against coding standards and the originating spec in parallel sub-agents.
to-tickets
Breaks plans and specs into tracer-bullet tickets with declared blocking edges.
ask-matt
Routes engineering situations to the appropriate skill or workflow in this repository.
to-spec
Synthesizes conversation context into a structured spec published to the project issue tracker.
codebase-design
Designs deep modules with small interfaces, clean seams, and testable adapters.
triage
Move GitHub issues and external PRs through a triage state machine with agent-ready briefs.
prototype
Build throwaway terminal or UI prototypes to answer design questions.
resolving-merge-conflicts
Resolve in-progress git merge and rebase conflicts while preserving both change intents.
grill-with-docs
Interrogates a plan or design while generating ADRs and a glossary.
implement
Implement work from a spec or tickets using TDD and code review.
tdd
Guides test-driven development through red-green cycles with seam-based test design.
Frequently Asked Questions About Joe Jiang
FAQPage SchemaWhat tasks can I accomplish with J0Jng's skills?▼
You can diagnose hard bugs and performance regressions, review branches against coding standards and specs, build domain models and ubiquitous language, resolve git merge conflicts, prototype design ideas, run test-driven development, and convert conversations into specs or tracker tickets.
Who are these skills designed for?▼
Software engineers and AI-agent developers managing non-trivial codebases. The set suits practitioners who plan multi-session work on issue trackers, enforce documented coding standards, maintain ADRs and glossaries, and want structured diagnosis loops for failing or slow code.
How do I set up and start using these skills?▼
Run setup-matt-pocock-skills once first: it configures the repo's issue tracker, triage label vocabulary, and domain doc layout. After that, invoke individual skills directly, or use ask-matt, a router that recommends which skill or flow fits your current situation.
How do the planning and ticket skills work together?▼
Wayfinder maps oversized work as decision tickets resolved one at a time; to-spec turns a conversation into a published spec; to-tickets splits plans into tracer-bullet tickets with blocking edges; triage moves issues through categorise-verify-grill states; implement then executes against specs or tickets.
What prerequisites or dependencies do these skills require?▼
A repository with a configured issue tracker, established via the one-time setup skill. Several skills are marked disable-model-invocation, meaning they run as explicit user-invoked procedures rather than automatic model triggers. No external services beyond the tracker are specified in the manifest.