发现 Skills

Linear programming skill for resource allocation, scheduling, and optimization problems

Mathematical programming skill for formulating and solving linear programming models for resource allocation, production planning, and capacity optimization.

Monte Carlo simulation engine skill for probabilistic modeling, risk quantification, and uncertainty propagation

Monte Carlo methods for uncertainty quantification

Nordic Semiconductor nRF5x/nRF Connect SDK expertise

Generate QML components with proper property bindings, signal/slot connections, and Qt Quick Controls integration

Navigate institutional review board processes, informed consent, confidentiality, and ethical considerations in human subjects research

Analyze skill gaps and prioritize learning investments across the organization

Expert skill in type theory foundations for implementing type systems including inference, checking, and subtyping

Security vulnerability scanning for dependencies and code, with CVE database checking and risk assessment

Sync and deploy BatDigest by generating `batdigest-flask/dist`, inlining CSS, syncing into `batdigest-static`, committing/pushing, verifying live parity, and submitting IndexNow. Use when asked to "sync batdigest", "deploy batdigest", "generate dist", "inline css", "verify live deploy", or "submit IndexNow" for BatDigest.

Ops-focused Proxmox VE management via REST API — monitor, control, provision, and troubleshoot VMs and LXC containers with battle-tested operational patterns. Use when asked to: - List, start, stop, restart VMs or LXC containers - Check node status, cluster health, or resource usage - Create, clone, or delete VMs and containers - Manage snapshots, backups, storage, or templates - Resize disks (API + in-guest filesystem steps) - Query guest agent for IP addresses - View tasks or system event logs Includes helper script (pve.sh) with auto node discovery from VMID, operational safety gates (read-only vs reversible vs destructive), vmstate snapshot warnings, post-resize guest filesystem steps, and a separate provisioning reference. Requires: curl, jq. Writes: ~/.proxmox-credentials (user-created, API token, mode 600). Network: connects to user-configured Proxmox host only (HTTPS, TLS verification disabled for self-signed certs). Helper script: scripts/pve.sh (relative to this skill) Configuration: ~/.proxmox-credentials

A practical framework distilling the thinking model of video creator 影视飓风Tim — visual storytelling, democratizing tech popularization, and a methodology for creating hits on Bilibili.

Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

A high-level orchestration skill that mandates a "Research-First, Plan-Second, Approve-Third" workflow, forcing the agent to investigate existing codebase utilities and present a detailed, hierarchical action list for user review before any code modifications are made.

Security-focused code review for staged changes or specified files. Checks for injection, auth flaws, crypto misuse, data exposure, and insecure patterns. Works with any language.

Relay incoming Telegram messages to Julia via the local MCP bridge server (http://localhost:3001). Use whenever a user sends a message that requires Julia's intelligence to answer. Forward the message, wait for Julia's reply, then send it back to the user.

Knowledge base for the codebase-mapper plugin. Provides writing guidelines, tone rules, and diagram conventions for generating human-readable project guides. Referenced by all codebase-mapper agents during document generation. TRIGGER WHEN: referenced by codebase-mapper pipeline agents (codebase-explorer, overview-writer, tech-writer, flow-writer, onboarding-writer, ops-writer, config-writer, guide-reviewer) during document generation. DO NOT TRIGGER WHEN: outside the /map-codebase pipeline (general documentation work should use docs:readme-craft or codebase-mapper:docs-create).

Expert guidance for building with Radix UI -- Primitives (unstyled accessible components) and Themes (pre-styled design system). Covers composition patterns, asChild prop, accessibility, animation, theming, color system, and keyboard navigation. Trigger when working with Radix components, @radix-ui packages, or building accessible UI primitives. Also trigger on mentions of "radix", "radix-ui", "radix primitives", "radix themes", "@radix-ui/react-*", or the unified "radix-ui" package. TRIGGER WHEN: working with Radix components, @radix-ui packages, or building accessible UI primitives DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Organize code by feature intent, not framework layers. Structure projects to clearly communicate business purpose at first glance.

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.

Security scanning patterns using gitleaks, PII detection, and secret scanning. Use when writing scripts that handle sensitive data, committing code, or setting up security automation. Includes gitleaks configuration, custom PII rules, and pre-commit hooks.

Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.