rlm
Process files too large to fit in context (>100KB, >2000 lines). Uses Python REPL for structural analysis, LLM queries for semantic reasoning, and subagents for final synthesis. Triggers - large file, big docum...
Découvrez les skills Données et IA, comparez leurs dépôts et consultez leurs instructions.
Process files too large to fit in context (>100KB, >2000 lines). Uses Python REPL for structural analysis, LLM queries for semantic reasoning, and subagents for final synthesis. Triggers - large file, big docum...
Configure Buildkite CI for Julia packages, especially for GPU testing and specialized hardware. Use this skill when setting up Buildkite pipelines.
Configure GitHub Actions CI for Julia packages including testing, documentation, and benchmarks. Use this skill when setting up or modifying CI workflows.
Write benchmark suites for Julia packages using BenchmarkTools.jl. Use this skill when creating organized, reproducible benchmark suites.
Run benchmark suites locally and in CI using AirspeedVelocity.jl. Use this skill when running benchmarks or setting up CI performance tracking.
Create new Julia packages with modern infrastructure including tests, documentation, and CI. Use this skill when starting a new Julia package from scratch.
Use Git and the GitHub CLI for version control and pull request workflows in Julia package development. Use this skill when working with Git remotes, branches, and PRs.
Run Julia tests with filtering, conditional loading, and environment-based selection. Use this skill when running tests or configuring test infrastructure.
Configure and write doctests for Julia packages using Documenter.jl. Use this skill when adding testable code examples to docstrings or setting up doctest infrastructure.
Write tests for Julia packages using TestItemRunner.jl patterns including Aqua, JET, and doctests. Use this skill when adding or organizing tests.
テストコード生成ガイド。TDD/BDDによるユニット・統合テスト作成に使用。
Playwrightを使用してE2Eテストを生成・実行。クリティカルユーザーフローの検証。
Use when researching features in jellyfin-web (the Jellyfin server's web UI rendered in CEF) or jellyfin-desktop (old Qt app) for reference during implementation
Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z"
Skill for maintaining clear, DRY, and easy-to-navigate design documents for architect agents.
Diplomacy system work for civ-game (foreign economy/development/military simulation, treaties, alliances/organizations, relations like colony or subject, diplomatic actions, and diplomacy UI or events). Use whe...
Shape, refine, and stabilize human intent into a canonical prompt artifact. Iteratively clarifies ambiguity until user confirms readiness.
Compile the YAML artifact into PROMPT.md with deterministic structure. A final agent pass polishes for fluidity, conciseness, and correctness.
Execute the forged prompt exactly as written. Requires explicit consent and a ready artifact. Deletes artifact after successful execution.
Suite of tools for creating elaborate, multi-component HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or s...
Orchestrate multi-agent workflows using SwarmKit Python SDK. Use when tasks benefit from: (1) Parallel processing - analyzing many documents/items simultaneously, (2) Quality competition - running multiple agen...
Create presentation slides as standalone HTML files with automated PNG export. Use when users ask to: create slides, build a deck, make a presentation, design slides, export slides to images, or work with HTML-...
SwarmKit SDK development for TypeScript and Python. Use when building applications with SwarmKit to run AI agents (Claude, Codex, Gemini, Qwen) in secure sandboxes. Triggers: (1) Creating SwarmKit applications,...
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include website...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.