107 skills · sorted by relevance
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
The English summary is being prepared. Showing the original description.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
The English summary is being prepared. Showing the original description.
Offensive methodology for attacking GraphQL APIs during penetration tests and bug bounty engagements. Covers the full attack lifecycle: endpoint discovery, introspection abuse and blind schema reconstruction when introspection is disabled, authentication and authorization bypass through Relay node IDs and nested object traversal, injection via variables and directives, query batching for brute force and OTP bypass, denial of service through depth bombs and alias amplification, WebSocket subscription hijacking, information disclosure through verbose errors and field suggestion oracles, and file upload abuse via the multipart GraphQL specification. Includes tool-specific guidance for InQL, graphql-cop, CrackQL, BatchQL, Altair, GraphQL Voyager, and clairvoyance. Trigger on: GraphQL, graphql, introspection query, batching attack, query depth, GraphQL injection, GraphQL IDOR, field suggestion, GraphQL auth bypass, GraphQL DoS, GraphQL security, graphql-cop, InQL, CrackQL, BatchQL, Relay node, alias amplificat...
The English summary is being prepared. Showing the original description.
Design and review Java database code using MyBatis and MyBatis-Spring. Covers mapping query results to objects, safe SQL parameters, transactions, pagination, batch writes, and investigating slow or unnecessarily repeated queries.
Organize a task into parallel work streams with clear dependencies, separate places for changes, and explicit checks. Batch independent reads and tests, coordinate concurrent work, and report completed or blocked tasks with verification results.
Carry out Benchmark Email tasks through Rube MCP, which links an AI agent with external tools. The skill discovers supported actions and their input formats, confirms an active connection, and executes the requested operations.
Automate Boxhero tasks through Rube MCP, a connection for agent tools. Discover suitable actions and their input requirements, verify the connection, and run individual or batch operations using the current tool definitions.
Improve GSAP animation performance by reviewing animated properties, browser layout work, and simultaneous updates. Use transforms, grouped updates, reusable animations, and targeted cleanup to reduce stuttering in lists, mouse followers, and scroll effects.
Integrate Microsoft Graph SDK into .NET, TypeScript/JavaScript, or Python applications to access Microsoft 365 data. Covers authentication, permissions, paginated results, incremental synchronization, change notifications, and retries when requests hit service limits.
Tune cognee ingestion speed, query response time, and LLM costs by adjusting concurrency, text chunk sizes, request limits, and model choices. Estimate ingestion costs before processing and assess options for background work and deployment scaling.
Refactor Handsontable code by separating plugin responsibilities, reducing dependencies, batching rendering work, and updating coding patterns. It provides compatibility rules and testing guidance to preserve existing APIs, CSS classes, settings, and behavior.
Review Handsontable code changes for architecture, code quality, performance, accessibility, and test coverage. Findings include severity, confidence, and file locations, helping developers assess whether changes follow project rules and demonstrate the intended behavior.
Automate Boxhero tasks through Rube MCP, a connection for agent tools. Discover suitable actions and their input requirements, verify the connection, and run individual or batch operations using the current tool definitions.
Carry out Benchmark Email tasks through Rube MCP, which links an AI agent with external tools. The skill discovers supported actions and their input formats, confirms an active connection, and executes the requested operations.
Improve GSAP animation performance by reviewing animated properties, browser layout work, and simultaneous updates. Use transforms, grouped updates, reusable animations, and targeted cleanup to reduce stuttering in lists, mouse followers, and scroll effects.
Assess API business workflows for flaws that automated scanners can miss. The skill examines skipped steps, simultaneous transactions, authentication tokens, GraphQL, and webhooks, helping testers document weaknesses and their financial or operational impact during authorized assessments.
Integrate files generated during MSBuild into compilation or build output. Address missing generated source and content by choosing target timing, using the configured intermediate directory, and registering files so Clean can remove them.
Investigate GraphQL APIs for unauthorized data access, unsafe updates, and permission inconsistencies with REST APIs. The skill covers schema discovery, checks across users and organizations, and validation steps that turn suspected weaknesses into reproducible findings with concrete impact.
Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the `gpunetio_ib_write_lat` client + server pair under `doca/tools/gpunetio_ib_write_lat/`, checking GPU-NIC pairing, reading the half-iter / full-iter / CUDA-side usec columns, characterizing median / p99 / jitter for a real-time control loop, picking GPUNetIO vs GPI vs CPU-initiated `perftest`, or weighing the latency-vs-batching trade-off. Trigger even without 'GPUNetIO' or 'ib_write_lat': 'GPU kernel RDMA latency benchmark', 'how fast can a CUDA kernel post a WRITE', 'p99 RDMA latency on H100 + ConnectX', 'kernel-launched WR tail latency', or 'compare GPU-init vs CPU-init perftest'. Route elsewhere for bandwidth runs (doca-gpunetio-ib-write-bw), the GPI surface (doca-gpi), library debugging (doca-gpunetio), or DOCA install.
The English summary is being prepared. Showing the original description.
Use when the user asks to "build our social posting calendar", "set weekly slots and queue depth per channel", or "plan the evergreen recycle rotation"; produces the always-on brand calendar — pillar allocation with hero/hub/help balance and give:ask targets (all labeled Estimated starting heuristics to calibrate against own analytics, never scored rules), per-channel recurring slots with queue depth, a batching workflow, an evergreen recycle cycle with freshness re-checks, deliberate open slots for realtime/trend moments fed by trend-spotter go/skip verdicts, and first-comment/publish-order ops — cadence commitments filed to the channel registry, and no batch ships to the queue without a SHIP verdict from social-quality-auditor pre-publish mode. Not for repurposing an existing asset or the paid-amplification calendar — use content-amplifier. 社媒排期/内容日历/栏目配比/常青循环复用
The English summary is being prepared. Showing the original description.
Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP server, and guides reliable desktop automation. Covers connecting an agent to the MCP endpoint (SigV4, streaming URL, and Active Directory SAML/Domain Join), BLOCKING vs POLLING connect modes, the computer-use tools (screenshot, click, type, key, scroll), screenshot-budget and action-batching discipline, MCP tool forwarding (forwarded___ tools), session lifecycle and expire-on-delete, and troubleshooting connection errors. Use when building or debugging an agent that drives a remote Windows desktop or GUI application via WorkSpaces Applications / AppStream — including "dcv session not ready", "client_disconnected", 400 signing-region, POLLING/connection_status, SAML assertion, or forwarded tool questions. Not for Amazon WorkSpaces Personal/Core virtual desktops or general AppStream fleet administration unrelated to agent access.
The English summary is being prepared. Showing the original description.
Optimize Anthropic Claude API costs with model routing, prompt caching, batching, and spend monitoring. Use when analyzing Claude API billing, reducing costs, or implementing cost controls and budget alerts. Trigger with phrases like "anthropic cost", "claude billing", "reduce claude spend", "anthropic budget", "claude pricing optimize".
The English summary is being prepared. Showing the original description.
Implement rate limiting for Anima API code generation requests. Use when batching component generation, handling rate limit errors, or optimizing API throughput for large design systems. Trigger with: "anima rate limit", "anima throttling", "anima batch generation".
The English summary is being prepared. Showing the original description.
Tune Alchemy-backed reads with measured latency, cache semantics, batching, concurrency, and freshness SLOs. Use when an integration is slow or wasteful. Trigger with "optimize Alchemy performance", "cache Alchemy data", or "reduce Alchemy latency".
The English summary is being prepared. Showing the original description.