Loading...
Loading...
Found 24 Skills
Bug-to-test pipeline: reproduce the bug as a failing test first, then fix. The regression test lives forever.
Rojo, Wally, Selene, StyLua, Lune, Aftman, luau-lsp, filesystem workflows, CI pipeline.
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.
GitLab issues, merge requests, repositories, CI pipelines, and code search via the glab CLI. Use when the user mentions GitLab, an MR/issue number, a project on gitlab.com, or a self-hosted GitLab instance.
GitHub Actions and CI/CD patterns for Databricks, including automated testing, deployment, and quality gates.
Interact with GitLab via the glab CLI. Supports five MR workflows — Read (summarize), Review (full code/security/QA review), Fix (review + implement), CI Fix (fix pipeline failures), and Feedback (address review comments). Trigger whenever the user provides a GitLab MR URL or says anything like "อ่าน MR", "ดู MR", "check MR", "review MR", "ช่วย review MR นี้", "ตรวจ MR", "แก้ตาม MR", "fix MR", "fix CI", "fix pipeline", "แก้ pipeline", "แก้ตาม comment", "แก้ตาม feedback", "address feedback", or just pastes a GitLab MR URL. Also supports listing MRs, viewing MR status, checking CI/CD pipelines, approving MRs, and other glab operations. Trigger on "check pipeline", "list open MRs", "pipeline failed", or any GitLab-related task.
[Hyper] Diagnose and fix build failures, CI pipeline errors, and deployment errors across the entire repository or a specific folder. Routes simple build breaks directly; tracks complex multi-system failures via .hypercore/deploy-fix/ JSON flow.
Use when designing tests, writing test cases, or planning test strategy for a module. Covers unit, integration, and e2e layering.
Build Docker images for Python services following team conventions. Use this skill when writing Dockerfiles, authoring CI image build pipelines, or adding a new service — covers mitodl image naming, git short-ref tags, relocatable uv venvs, and shared library handling.
Harness CI (Continuous Integration) for container-native builds with test intelligence, caching, parallelization, and build infrastructure management
Apply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call). Companion to cost-booster-route.