发现 Skills

Japanese translation: This file requires a Japanese translation for lead-intelligence.

Build a reusable Manim interpreter for technical concepts, charts, system diagrams, and product demos, intended to be handed off to a broader ECC video stack when needed. Use when the user wants a clear animated explanation rather than a generic talking-head script.

A direct-search workflow for PubMed and NCBI E-utilities to support biomedical literature searches, MeSH queries, PMID lookups, citation retrieval, and API-based literature monitoring.

Act as an agentic engineer using evaluation-first execution, task decomposition, and cost-aware model routing.

An engineering operating model for teams whose AI agents generate large volumes of implementation output.

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Documented expertise for managing carrier portfolios, negotiating rates, tracking carrier performance, assigning freight, and maintaining strategic carrier relationships. Intended for transportation managers with 15+ years of experience. Includes scorecard frameworks, RFP processes, market intelligence, and compliance checks. Used when managing carriers, negotiating rates, evaluating carrier performance, or building rate strategies.

Create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs anchored to actual files and line ranges. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured “explain how this works” requests.

Coordinates multi-AI-agent and task-aggregation workflows. Distributes work across multiple workers, handles errors, and merges results.

GitHub operations, automation, API integrations, and CI/CD workflows.

Used to retrieve Jira tickets, perform requirements analysis, update ticket status, add comments, or transition issues. Provides Jira API patterns via MCP or direct REST calls.

JetBrains Exposed ORM patterns (including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and the repository pattern).

Ktor server pattern (includes routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSocket, and testApplication tests).

Laravel plugin discovery, package management, dependency resolution, and service provider integration.

Japanese translation: This file requires a Japanese translation for messages-ops.

Japanese translation: This file requires a Japanese translation for motion-ui.

A pre-coding research workflow. Searches existing tools, libraries, and patterns before writing custom code. Invokes a researcher agent.

Use AgentShield to scan Claude Code configuration (the .claude/ directory) for security vulnerabilities, misconfigurations, and injection risks. Checks CLAUDE.md, settings.json, MCP server settings, hooks, and agent definitions.

Search existing skills in local paths, the Marketplace, GitHub, and the web before creating a new skill. Used when creating, building, forking, or searching for skills.

A skill that can retrieve A2UI UI JSON schematics and UI templates that best show the response. This skill is essential and must be used before generating A2UI (Agent-to-UI) JSON responses.

Bisect a ClickHouse regression using pre-built master binaries from CI. Use when the user wants to find the commit that introduced a bug.

Automate Ncscale tasks via Rube MCP (Composio). Always search tools first for current schemas.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementations.