Explore skills

Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\"

Coordinator that executes a plan in parallel groups via background subagents. Spawns implementers, then dedicated test-runner / static-analyse subagents, then routes failures back to the original implementer (SendMessage) or a fresh fixer. Fully autonomous — no human-in-loop.

Use only when the user explicitly asks to save, note, record, or preserve one learning from the current conversation as a raw developer note.

Use when Pulse planning or discovery needs graph-based architecture context, execution-flow tracing, symbol relationships, or blast-radius analysis beyond plain file search.

Update the docs/architecture .md spec files after adding a new feature, without re-running the full ms-spec. Detects what changed via git diff, maps changes to the right spec sections, grills the developer for missing context, and patches only the affected .md files. Use when a feature is done and the user wants to keep AI agent context up to date, or says "update spec", "sync spec", "ms-spec-upda

Dynamically discover all git repositories under a parent folder, checkout master/main, and pull latest code. Use when user wants to update all microservices, sync all repos, or says "update-all" or "pull all repos".

Create structured GitHub issues via gh CLI using type-specific templates (bug, feat, refactor, doc, perf, security). Use when filing bugs, requesting features, tracking work, opening tickets, or any intent to create a GitHub issue — even implicit phrases like "track this" or "file this".

Use when packaging, publishing, or updating a public agent-skill repository so it can be installed across machines, repos, Codex, Claude Code, and local skill directories.

Manually-triggered comprehensive codebase health audit covering security, architecture, documentation drift, dead code, and test coverage gaps. Produces a ranked markdown report, files prioritized GitHub issues, and proposes (but never autonomously opens) auto-fix PRs for trivial safe changes. Use when the user wants to audit, scan, review the health of, do a security check on, find dead code in,

Use when the user wants to prevent broken code from being pushed, block git push when tests fail, run tests before push, set up push protection, or add a safety net against pushing untested code. Covers any request to gate pushes on test results — whether they mention "hook", "pre-push", or just describe wanting to stop bad code from reaching the remote. Also handles auto-fix/auto-repair of test f

Audits a working feature for the gap between "happy path passes" and "production-ready" — edge cases, error handling, loading/empty/error states, a11y, responsive, i18n, observability, ops hooks. Use when a feature works but needs polish, for "완성도 높여줘", "production ready로", "edge case 검토", "polish this feature", "is this ready to ship?", "엣지 케이스 다 챙겼나", "PR 전 점검", "빠진 상태 없나", or before shipping an

SAP ABAP RESTful Application Programming Model (RAP) development skill. End-to-end scope: business objects (BO), CDS data model, behavior definitions and implementations, service definitions / bindings, file uploads/downloads, metadata extensions, value helps, and RAP testing. Use when the user asks to: build a RAP BO (managed or unmanaged), model CDS view entities / table entities / projection vi