Write "Top N best..." listicle articles for affiliate marketing with mini-reviews, pricing, pros/cons, and CTAs per entry.
Cloud-side inference with ExtendRT and Ascend backends. Use for server-side inference, Ascend 310/910 deployment, ModelParallelRunner for concurrent serving, ModelGroup for weight…
Lightweight skill generator with style learning - creates simple skills using flow-based execution and style imitation.
Apply Litestar dependency injection with Provide, Dependency markers, layered scopes, overrides, generator-based cleanup, per-request caching, and nested providers.
Generate ActivityKit Live Activity infrastructure with Dynamic Island layouts, Lock Screen presentation, and push-to-update support. Use when adding Live Activities to an iOS app.
Algorave-grade livecoded music workflow — TidalCycles patterns (Haskell DSL driving SuperDirt over OSC) + Hydra-synth visuals (browser or VS Code Simple Browser via a local HTML…
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics,…
把 ~/.claude/skills/ljg-* 里所有更新过的 skills 同步到 github repo (ljg-skills)，先推 master 分支（org-mode 输出风格），再切 md 分支（markdown 输出风格）做基础 markdown 化后推。Use when user says '/ljg-push', 'push…
给一个领域，找出背后真正撑着它的几根独立的力。十几个现象砍到不可再少的生成器——砍完能把现象一个个生回来，才算数。Use when user says '降秩', '找秩', '秩是什么', '这个领域靠什么撑着', '背后是什么', or wants to decompose any domain to its irreducible…
LlamaIndex MCP Server is built around LlamaIndex framework for LLM data access. The underlying ecosystem is represented by run-llama/llama_index (47,942+ GitHub stars).
Stand up an evaluation suite for an LLM feature from scratch — a representative dataset, the right metrics, a baseline score, and a CI gate — using DeepEval, promptfoo, or RAGAS.
Turn an example of the data you want from an LLM into a precise, validated output schema (Pydantic / Zod / JSON Schema) and wire it into structured-output calls.
LLM output validation patterns — structured output schemas, hallucination detection, retry-with-backoff, streaming output safety, tool-call validation, and confidence scoring.
U-llm-sdk and claude-only-sdk patterns. Use when working on projects with LLM service, designing LLM integrations, or implementing AI-powered features.
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.
Installs or updates Codex CLI and Claude Code. Use when CLI agents need installation or update.
Use when removing Claude-side hex-line integration surfaces such as MCP registration, permissions, hooks, and output style.
Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build config issues. Use when auditing build health.
Generates .NET Clean Architecture backend structure from entity definitions. Use when bootstrapping .NET backend projects.
Generates seed data from ORM schemas or entity definitions to any target format. Use when populating databases for development.
Generates Dockerfile and docker-compose configuration for multi-container development. Use when containerizing a project.
Generates GitHub Actions CI workflow configuration. Use when adding continuous integration to a project.
Sets up linters, pre-commit hooks, and test infrastructure. Use when adding code quality tooling to a project.
Configures ESLint, Prettier, Ruff, mypy, and .NET analyzers. Use when setting up linting and formatting for a project.
Configures Husky, lint-staged, commitlint, and Python pre-commit hooks. Use when adding Git hook automation to a project.
Configures Swagger/OpenAPI documentation for backend APIs. Use when adding interactive API docs to a project.
Upgrades npm/yarn/pnpm dependencies with breaking change handling. Use when updating JavaScript/TypeScript dependencies.
Run a quick concurrent HTTP benchmark against a URL before deeper performance work or regression triage.
LobeHub CLI Toolbox - AI-powered command-line tools including lobe-commit (ChatGPT Git commits with Gitmoji), lobe-i18n (automated internationalization), and lobe-label (GitHub…
Use when user mentions bookmarks, knowledge management, notes, saving URLs, or taking screenshots - provides quick reference for km (Zettelkasten notes), bookmark (URL manager),…
Run quick, offline, private LLM tasks on local models via llama.cpp, reusing models already downloaded by Ollama.
Automatically adapt document formatting to cultural conventions - date formats, currency symbols, letter styles, number separators, and honorifics based on detected…
Logfire is Pydantic's observability SDK for Python applications, with first-class tracing for AI, LLM, and agent workloads.
实作结构化日誌，包含正确的日誌层级和敏感数据处理。 使用时机：新增日誌、除錯、设置可觀测性。 关鍵字：logging, log level, structured logging, observability, 日誌, 记录, 结构化日誌。
Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side.
Generate logos using Replicate AI and make them transparent with background removal.
Convert standard Markdown (especially pasted from ChatGPT or similar) into Logseq-Flavored Markdown: nest code blocks inside bullets, fix heading-to-indent levels, drop horizontal…
Apply production-ready Lokalise SDK patterns for TypeScript and Node.js. Use when implementing Lokalise integrations, refactoring SDK usage, or establishing team coding standards…
Loki Log Query Agent is built around Grafana Loki log aggregation system. The underlying ecosystem is represented by grafana/loki (27,858+ GitHub stars).
Lombok annotations and best practices for Java 21+ projects. Use when reducing boilerplate, configuring builders, or choosing between Lombok and Records.
Analyzes long strangle volatility plays with OTM call and put at different strikes. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0.
Use when working code needs behavior-preserving simplification because readability, duplication, dead code, naming, nesting, wrappers, or abstraction debt is the problem; not when…
Evaluate-Loop Step 4: EVALUATE EXECUTION. This is the dispatcher agent — it determines the track type and invokes the correct specialized evaluator.
Use when the user wants to install or bootstrap loopd in a fresh git repository. Scaffolds .loopd/ (charter, config, per-loop state files, scripts, pre-push hook) in the current…
Auto-discovers and configures Language Server Protocol (LSP) servers for your project's languages
Use when lua coroutines for cooperative multitasking including coroutine creation, yielding and resuming, passing values, generators, iterators, asynchronous patterns, state…
Luigi Task Generator - Auto-activating skill for Data Pipelines. Triggers on: luigi task generator, luigi task generator Part of the Data Pipelines skill category.
Use when an LWC needs a stable, typed handle to a specific DOM element it owns — focusing inputs, imperatively validating a known form field, invoking a `@api` method on a child…
ACTIVATE when writing or modifying shell scripts, setup scripts, hooks, or troubleshooting on macOS. ACTIVATE when commands like `grep -P`, `realpath`, `sed -i`, `mapfile`,…
Zoom Meeting SDK for macOS native apps. Use when embedding Zoom meetings in macOS with default/custom UI, PKCE + SDK auth, host start/join flows, and desktop meeting feature…
Build professional native macOS apps in Swift with SwiftUI and AppKit. Full lifecycle - build, debug, test, optimize, ship. CLI-only, no Xcode.
Generate entitlements.plist with appropriate sandbox capabilities for macOS applications
Build, run, and debug local macOS apps or desktop executables with shell-first Xcode/Swift workflows.
Use when the user wants OpenClaw to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository.
Операционный навык по MADSpec Framework и MADSpec CLI. Использовать, когда агент работает внутри проекта MADSpec, должен понимать поэтапный процесс работы, артефакты `.madspec`,…
Maestro 기반 모바일 테스트 자동화 워크플로우를 시작합니다. planner -> grouper -> generator -> executor -> healer 순서로 Agent 기반 테스트를 자동 실행합니다.
maf-command-generator のエクスポートパイプライン設計リファレンス。Go コードがどのようにマスターデータ（JSON）からデータパック成果物（.mcfunction, loot table JSON）を生成するかを解説する。エクスポートの仕組み変更、新エンティティのエクスポート追加、生成物の構造理解、convert…
Phase-2-Skill (T-30-2) für Mager-Konjugation: TUV-L-Perspektive ('Die SuS benennen drei Merkmale, indem sie...') → AB-S-Perspektive ('Du benennst drei Merkmale, indem du...').
Smart entry point for any commit-worthy work. Classifies the request by type (feat/fix/hotfix/refactor/chore/docs/perf/test/style/ci) and scale (trivial/minor/major), then routes…
Utilizes Magic by 21st.dev to generate, compare, and integrate multiple production-ready UI component variations.