typst-grammar-authoring

Use when authoring or validating Typst documents from canonical grammar examples, especially when you need compile, HTML, or SVG-based validation workflows.

install-pymllm

Install the pymllm Python package. Asks the user whether to do a full build (with CMake C++ compilation) or a fast install (Python-only, skip CMake). Use when the user asks to install, set up, or reinstall pymllm.

building

Use when building knowhere from source, configuring build options (CPU/GPU/DISKANN/ASAN), or troubleshooting compilation errors

cuda-kernels

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.

compiler-switching

Safely switch between NAG, gfortran, and Intel compilers when building MAPL

benchmark-translate

Run a quality benchmark of the /translate skill by selecting stratified test keys, capturing ground truth, translating, judging with sub-agents, and compiling a regression report. Invoke with /benchmark-translate.

rationalize-deps

Analyze Cargo.toml dependencies and attempt to remove unused features to reduce compile times and binary size

build-frontend

Builds the Fake Survey Generator React frontend with Vite and TypeScript. Use this skill when frontend code changes need to be compiled and validated for TypeScript errors. This skill orchestrates the npm build command and reports build errors.

pyfoma-codebase

Rapidly onboard to pyfoma core internals (regex compiler + FST algorithms), make safe code changes, and avoid common semantic and performance regressions in fst.py, regexparse.py, atomic.py, algorithms.py, paradigm.py, and partition_refinement.py.

project-overview

Overview of the torch-spyre repository, Spyre device architecture, compilation pipeline, and codebase structure. Use when asking about how torch-spyre works, the repo layout, Spyre hardware, the Inductor backend, or getting oriented in the codebase.

agnostic-prompt-standard

The reference framework to generate, compile, and lint greenfield prompts that conform to the Agnostic Prompt Standard (APS) v1.0.

deepslide-openclaw

Installs and deploys DeepSlide, and enables Docker-based TeX compilation. Invoke when setting up DeepSlide, starting/stopping services, or compiling LaTeX without local TeX.

fict-best-practices

Fict compiler and runtime engineering guide for correctness and reliability. Use when implementing or reviewing Fict compiler transforms, runtime reactivity behavior, SSR/resume flow, devtools/playground integration, or release CI gates in Fict repositories.

Com.Axiomatic Ai/Prover

Lean 4 MCP server: compile, prove theorems, and formalize math with Mathlib.

debugging-dbt-errors

Debugs and fixes dbt errors systematically. Use when working with dbt errors for: (1) Task mentions "fix", "error", "broken", "failing", "debug", "wrong", or "not working" (2) Compilation Error, Database Error, or test failures occur (3) Model produces incorrect output or unexpected results (4) Need to troubleshoot why a dbt command failed Reads full error, checks upstream first, runs dbt build (not just compile) to verify fix.

ontology-catalog-import

Import customer or external RDF/OWL into this repo's catalogue format. Use when user drops an RDF/OWL file and wants it catalogue-ready (metadata, category, validation, compile).

author-code

Conventions for authoring Rust code in the Dada compiler. Use when writing or modifying Rust code, adding functions, or making implementation changes.

java-lsp-tools

Compiler-accurate Java code intelligence tools powered by the Java Language Server. ALWAYS load this skill when the workspace contains Java, Maven (pom.xml), or Gradle (build.gradle) projects. Use these tools to find symbol definitions, get type/call hierarchies, resolve types, inspect file outlines, and check imports in Java source files. Prefer over grep_search or read_file for any Java code navigation, understanding, debugging, or refactoring task.

xcdocs

Use when an agent is writing, debugging, or updating code against Apple frameworks and needs local Xcode documentation to resolve compile errors, discover the right symbols, check API shape or availability, confirm usage patterns, or inspect related articles and topics for newly released SDK features.

update-upstream-sdk

Update the hs-temporal-sdk project against the upstream Rust core SDK (temporalio/sdk-core). Covers revision bumps, Rust compilation, C header regeneration via bindgen, Haskell FFI bridge updates, protobuf regeneration, SDK module propagation, and nix build verification across GHC versions. Use when updating, bumping, syncing, or upgrading the upstream Temporal SDK dependency.

ClaudeInk — Knowledge Vault

Save, search, and compile valuable knowledge from your Claude conversations.

kessoku-di

Kessoku compile-time DI with parallel initialization for Go. Use when writing or debugging kessoku providers/injectors, enabling async dependencies, migrating from google/wire, or fixing go:generate/codegen issues in Go services.

sync-with-swift

Guide for syncing with upstream Swift compiler demangling changes

iz-tolk-mcp — Tolk Compiler for TON

Tolk smart contract compiler for TON — compile, check, and deploy from AI assistants

fast-mlx

Optimize MLX code for performance and memory. Use when asked to implement or speed up MLX models or algorithms, reduce latency/throughput bottlenecks, tune lazy evaluation, type promotion, fast ops, compilation, memory use, or profiling.

Unity Agent Harness for Claude Code — auto-compile, test pipelines, cross-model review, out of the box.

Compare the current branch against develop and generate two review documents: architecture change diagram + PR review checklist.

Raya Language Expert

Comprehensive knowledge of the Raya programming language, its architecture, and development practices

xcode-build

Build and run iOS/macOS apps using xcodebuild and xcrun simctl directly. Use when building Xcode projects, running iOS simulators, managing devices, compiling Swift code, running UI tests, or automating iOS app interactions. Replaces XcodeBuildMCP with native CLI tools.

wiki-manager

LLM-compiled knowledge base manager for Codex. Use it to initialize, ingest, compile, query, lint, research, and generate outputs from topic-scoped wikis. Activates when the user mentions wiki workflows, knowledge-base management, ingestion, compilation, querying, linting, research, or uses /wiki-style shorthand in a repo with .wiki/, ~/wiki/, or a configured hub path.

byob

Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3) compile and run a BYOB benchmark, (4) containerize a benchmark, or (5) use LLM-as-Judge evaluation. Triggers on mentions of BYOB, custom benchmark, bring your own benchmark, scorer, or benchmark compilation.

Orionbelt Semantic Layer

API-first semantic layer MCP server compiling YAML models into dialect-specific SQL

fastexcel-to-fesod

Migrates a Java project from FastExcel 1.3 (cn.idev.excel:fastexcel:1.3.0) to Apache Fesod (org.apache.fesod:fesod-sheet:2.0.1-incubating). Invoke this skill when asked to "migrate FastExcel to Fesod", "upgrade to Apache Fesod", or "replace cn.idev.excel". FastExcel 1.3 is the direct predecessor of Apache Fesod. Supports both legacy namespaces seen in real projects: cn.idev.excel.* and org.apache.fesod.excel.*. The entry classes FastExcel and FastExcelFactory are kept as @Deprecated aliases in Fesod, so call-site renames are strongly recommended but NOT required for compilation. The only breaking change is the Java package prefix.

Beamer Slide Workflow

Universal skill for academic Beamer presentations. Full lifecycle: create → compile → review → polish → verify.

build-and-compile

Building, compiling, and resolving dependency issues across languages

Io.Github.SepineTam/Latex Mcp

Enable AI agents to compile TeX files with LaTeX inside a Docker container.

chatcrystal-debug-recall

Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.

AINL for Hermes Agent

**AINL** is an AI-native language that compiles **deterministic graphs**. In Hermes Agent, use it to import workflows, compile them, run them, and expose **`ainl-mcp`** tools to the agent for safe, repeatable execution.

Mcp Server

Kotlin compile-time SQL library. Docs, code validation, and SQLite execution tools.

unity

Execute Unity Editor commands (run tests, compile, get logs, refresh assets, play/pause/step) via file-based bridge. Auto-activates for Unity-related tasks. Requires com.mxr.claude-bridge package installed in Unity project.

coverage-investigation

Investigate and improve code coverage for the wado-compiler crate. Use when asked to analyze coverage gaps, find dead code, or plan coverage improvement.

canonical-markdown-authoring

Convert plain markdown contract drafts into OpenAgreements' canonical `template.md` authoring format. The canonical form is a single lawyer-editable file that compiles to a validated JSON contract spec plus a rendered DOCX via the shared template renderer.

compiler_plugin_dev

Designs, models, and implements Kotlin compiler extensions using K2/FIR and IR. Guides modifications to SpektGenerator (IR), ProxyGenerator (IR), and InspektChecker (FIR). Handles synthetic declaration generation, FIR status/supertype transformations, and IR backend lowerings. Use when implementing reflection features, fixing plugin bugs, or engineering compiler diagnostics.

LLM Wiki — Compounding Knowledge Base

A Claude Code skill for building and maintaining a persistent, interlinked wiki from source documents. Knowledge is compiled once and kept current, not re-derived on every query.

ingesting-spec

Guide for ingesting the latest OpenAI TypeSpec specification into the openai-dotnet SDK. Use this when asked to update or ingest OpenAI API specs, copy base TypeSpec files from upstream, fix client TSP compile errors, or run code generation for new API areas.

compiler-and-fourslash-tests

How to write, run, and debug compiler tests and fourslash (LSP) tests in the typescript-go repository. Covers test file formats, directives, markers, baseline management, and the fourslash verification API.

magpie-engineer

Comprehensive guide for writing Magpie (.mp) programs, debugging compiler errors, and using the Magpie CLI. Designed for agents who have never seen Magpie before.

checkpoint

Save session progress by committing changes, pushing to remote, creating or updating a pull request, persisting decisions and patterns to memory layers, compiling session briefing, and archiving completed features. Use when saving work, creating a PR, preserving session state, or manually checkpointing progress.

Writing Intelligence Compiler v2.0

bump-tantivy

Bump tantivy to the latest commit on main branch, fix compilation issues, and open a PR

Claude Prompt Optimizer

Scores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.