MCP App StoreMCP App StoreThis skill maps the Koru language toolchain: where to find the tutorial and reference artifacts, how the compiler (koruc) runs, and how the test suite is the authoritative spec. It distills gotchas about parser modes, subflows vs procs, punning, and the four-stage compile/runtime pipeline so agents and developers can quickly orient and run tests.
Use this skill when opening a Koru repo, compiling Koru sources (.kz/.k), running regression tests, diagnosing test failures, or when you need to understand why a given behavior is enforced by the test suite. Start here before editing code or writing new tests.
koru-tutorial.md, koru-by-example.md, and CLAUDE.md for deeper mental modelsBest for agents with shell access able to run local test harnesses and compilers (CI bots, developer assistants, local build agents).
Koru-toolchain is an orientation skill for developers working with the Koru language and its compiler koruc. The SKILL.md is well-written with clear structure: quick orientation, artifact references, mental model gotchas, file forms, and test-running instructions. No scripts are bundled — it's purely a reference/guidance skill. The content is thorough and unambiguous for its niche audience.
Clean skill — no security concerns, no scripts, no network calls, no destructive commands. Well-structured SKILL.md with proper frontmatter and clear progressive disclosure. Low usefulness score reflects the extremely niche audience (Koru language developers), not quality issues.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Blender Build-Go (bgo)
Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
EventKit Integration (iOS/macOS)
Expert EventKit patterns for iOS/macOS: permissions, bidirectional sync, zero-width identity signatures, batch operations, and zombie-task handling.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr