Review pull requests that change Compose UI by rendering @Preview composables on base and head and diffing them.
Score 70/100
Connect LLMs to MCP servers through composable patterns like router, evaluator-optimizer, and orchestrator flows without hand-managing server lifecycles.
Score 70/100
Assemble the context bundles for each sub-agent based on evaluate-story output. Produces spawn-ready packages for Planning, Implementation, QA, or MicroDelivery sub-agents.
Score 70/100
Use Lobster when an OpenClaw operator wants one deterministic typed workflow step, with approval gates and resumable execution, instead of re-planning the same multi-step tool…
Score 70/100
Rules pertaining to Composer dependency management, promoting best practices for declaring and updating dependencies.
Score 70/100
Teaches component composition patterns in React 19 including children prop, compound components, and render props.
Score 70/100
Automate Composio tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity.
Score 70/100
Use when connecting Claude to external apps (Slack, GitHub, Gmail, etc.) using the Composio Connect framework.
Score 70/100
Automate Composio Search tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Composition Over Configuration for flexible component design. Trigger: When building reusable UI components with flexible, consumer-controlled APIs.
Score 70/100
Write a CompoundSpec v2 JSON payload and apply it via compound_apply to create/update skills, instincts, and docs.
Score 70/100
Generate a CompoundSpec v2 JSON-only autolearn proposal from git diffstat + existing skills, while respecting strict file-scope constraints.
Score 70/100
Design content that appreciates in value over time — frameworks, datasets, reference guides, and living documents that become MORE cited, MORE shared, and MORE valuable as time…
Score 70/100
Compound Engineering workflow for AI-assisted development. Use when planning features, executing work, reviewing code, or codifying learnings.
Score 70/100
Compound fields (Name, Address, Geolocation): SOQL access rules, DML semantics, component access in Apex/LWC, reporting column behavior, formula field restrictions.
Score 70/100
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns…
Score 70/100
Generate comprehensive compound profiles including structure, properties, bioactivity, and development status. Use for drug analysis, SAR studies, and competitive profiling.
Score 70/100
Use Plan → Work → Review → Compound to compound skills and maintain project context.
Score 70/100
Use when the colony needs a complete multi-perspective map of a complex codebase
Score 70/100
Forensic, high-fidelity context handover for seamless continuation in a new chat. Produces a single Markdown transfer artifact plus reusable templates, preserving decisions,…
Score 70/100
Fetches ALL open issues from any GitHub repository using pagination and generates a comprehensive analysis including category breakdown, age distribution, stale issues (30+ days),…
Score 70/100
Use after implementing features - 7-criteria code review with MANDATORY artifact posting to GitHub issue; blocks PR creation until complete
Score 70/100
You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews.
Score 70/100
Deep comprehensive system status analyzer that provides honest truth reporting about entire Pomo-Flow application health, performance, and integrity
Score 70/100
Deep comprehensive system status analyzer that provides honest truth reporting about entire Pomo-Flow application health, performance, and integrity
Score 70/100
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure.
Score 70/100
Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space.
Score 70/100
Reduces token burn by compressing command output and deduplicating repeated file reads before they are sent to Claude Code, Codex, Cursor, and related coding-agent tools.
Score 70/100
Compress session conversation into structured summary for system memory. Activate when user says "compress", "compress session", or after significant work.
Score 70/100
Build with Solana compressed NFTs (cNFTs) - Merkle trees, minting at scale, transfers, and metadata. Use when creating large NFT collections or reducing mint costs.
Score 70/100
Pressure births diamonds, stars, and insights. Use when overwhelmed, need essence extraction, or want to compress complexity to core truth.
Score 70/100
Compression Optimizer - Auto-activating skill for Data Pipelines. Triggers on: compression optimizer, compression optimizer Part of the Data Pipelines skill category.
Score 70/100
Analyze current context and recommend compression strategies for bloated or quota-heavy sessions
Score 70/100
Trading comparables analysis with peer multiples and implied valuation
Score 70/100
Comptabilité, fiscalité et facturation pour entreprises françaises. Gère écritures PCG, déclarations TVA, IS/IR, clôture annuelle, liasse fiscale (2033/2065), FEC, états…
Score 70/100
Dieser Skill wird aktiviert, wenn der Benutzer "benchmark", "token count", "performance test", "vergleich", "token reduktion messen", "performance analyse", "pipeline benchmark",…
Score 70/100
Dieser Skill wird aktiviert, wenn der Benutzer "mcp", "claude desktop", "mcp server", "tools", "mcp integration", "comptext als tool", "fhir mcp", oder "pipeline tool" erwähnt.
Score 70/100
NURBS curves and surfaces, mesh geometry, boolean operations, subdivision surfaces, tessellation methods, surface analysis, and point cloud processing for AEC computational design
Score 70/100
Understanding how digital systems actually work -- hardware, operating systems, networks, and information representation -- at a depth sufficient to reason about them rather than…
Score 70/100
Computational thinking as a problem-solving discipline independent of programming languages. Covers the four pillars (decomposition, pattern recognition, abstraction, algorithm…
Score 70/100
Create computed columns in Glide - Math, If-Then-Else, Relations, Rollups, Lookups, Templates. Use when adding calculations, formulas, lookups, or linking tables with relations.
Score 70/100
Automate desktop GUI workflows via Claude computer use API with screenshot capture and mouse/keyboard control.
Score 70/100
Claude Computer Use tool integration for desktop automation. Enables Claude to interact with computer environments through screenshots, mouse control, keyboard input, and…
Score 70/100
Let agents run disposable VMs for computer-use and GUI automation instead of controlling the host desktop.
Score 70/100
SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.
Score 70/100
Guide computer vision (classification, détection, segmentation) avec PyTorch, TensorFlow, OpenCV
Score 70/100
Expert guidance for computer vision development using OpenCV, PyTorch, and modern deep learning techniques for image and video processing.
Score 70/100
Basic operations for the Conan C++ package manager. Use when the user explicitly asks to 'use conan' for tasks like creating projects, installing dependencies, or building…
Score 70/100
C/C++ package manager skill covering Conan and vcpkg. Use when adding third-party library dependencies to C/C++ projects, managing binary compatibility, integrating with CMake, or…
Score 70/100
Forth/Factor/Joy: stack-based concatenative programming where composition replaces application.
Score 70/100
A strategic framework for spreading product news or company updates by targeting audiences in sequential stages—from internal teams to power users and then broader circles.
Score 70/100
Expert in entertainment industry concept art workflows, from initial ideation through final production-ready deliverables.
Score 70/100
概念边界辨析器：用于比较多个相近但不同层级的概念，区分它们在产品形态、系统技术、能力基座、任务边界、替代关系与互补关系上的差异，并生成中文边界矩阵、分层定义与统一口径。适合“AI 搜 vs Agentic Search vs 生成式 vs 传统搜推”这类容易混淆的分析场景。
Score 70/100
Explique un concept complexe de manière simple, progressive et avec des analogies. À utiliser quand l'utilisateur ne comprend pas quelque chose et a besoin d'une explication…
Score 70/100
Design progressive concept scaffolding with cognitive load management. Use when breaking down complex concepts into learnable steps for educational content.
Score 70/100
Переиспользуемые промпты в формате markdown — программирование агента на естественном языке
Score 70/100
Identify business entities, relationships, and high-level data structures from requirements and domain knowledge.
Score 70/100
Use when the user asks for shorter, denser, token-efficient replies — especially in Chinese. Triggers on "concise mode", "concise 模式", "use concise", "be brief", "less tokens",…
Score 70/100
Use when the user wants concise mode to be the default for every new chat across Codex CLI, Claude Code, and Cursor.
Score 70/100