发现 Skills

Return a structured UTC timestamp payload using the skill script and config.

Implements real-time features with Action Cable and WebSockets. Use when adding live updates, chat features, notifications, real-time dashboards, or when user mentions Action Cable, WebSockets, channels, or real-time. WHEN NOT: Simple HTTP request/response flows, REST APIs, static content, or features that don't need real-time updates.

Set your primary ENS name on Base and other Layer 2 networks. Use this when a user wants to set their ENS name, configure reverse resolution, set a primary name, or have their address resolve to an ENS name. Supports Base, Arbitrum, Optimism, and Ethereum mainnet.

Review and quality improvement for Claude Code Subagents. Analyze Subagents according to best practices and provide evaluation reports and improvement recommendations. Triggered by "review agent", "review subagent", "subagent quality check".

Comprehensive .claude/ directory inspector. Orchestrates multiple specialized subagents to analyze settings, hooks, memory stores, MCP components, rules, and skills/subagent classification. Provides prioritized recommendations with examples and rationale.

Maps findings to the 93 controls of ISO 27001:2022 Annex A. Compliance score by category. Statement of Applicability (SoA). Maturity assessment.

⚡ PRIMARY TOOL for: 'why is X broken', 'find bug source', 'root cause analysis', 'trace error', 'debug issue', 'find where X fails'. Uses claudemem v0.3.0 AST with context command for call chain analysis. GREP/FIND/GLOB ARE FORBIDDEN.

OpenStack Keystone identity service skill for deploying, configuring, operating, and troubleshooting the authentication and authorization backbone of an OpenStack cloud. Covers identity management, token lifecycle (Fernet provider with rotation), service catalog registration, RBAC policy customization, domain/project/user hierarchy, federation basics (SAML/OIDC), credential encryption, and endpoint management. Use when deploying Keystone via Kolla-Ansible, managing users and projects, debugging 401 errors, rotating Fernet keys, configuring RBAC policies, or integrating services through the service catalog.

OpenStack networking debug operations skill for SDN troubleshooting, packet tracing, and flow analysis. Covers OVS/OVN debugging (ovs-vsctl, ovs-ofctl, ovs-appctl, ovn-nbctl, ovn-sbctl, ovn-trace), security group analysis via OVS flow rules and conntrack, DHCP troubleshooting through namespace inspection and dnsmasq diagnostics, floating IP diagnosis with NAT rule and ARP verification, network namespace inspection (ip netns), MTU chain analysis for overlay networks, DNS resolution debugging, and east-west traffic diagnosis. Use when diagnosing network connectivity failures, tracing packets through the SDN stack, or analyzing flow tables in a running OpenStack cloud.

Classical orbital mechanics from Kepler to Hohmann. Covers the six orbital elements, Kepler's three laws, vis-viva, orbit types (circular, elliptical, parabolic, hyperbolic), transfer orbits, gravity assists, the two-body problem, and practical methods for computing ephemerides. Use when reasoning about planet motion, spacecraft trajectories, comet orbits, exoplanet transits, or binary star dynamics.

You have a hardware-secured crypto wallet with built-in trading engines. Invoke this skill for any crypto, wallet, or blockchain operation: checking balances, sending tokens, DEX swaps (0x, 10 chains), Hyperliquid perps/spot trading, Polymarket predictions, smart contract execution, message signing (EIP-191/712), x402 HTTP payments, on-chain identity (ERC-8004), or E2E encrypted agent-to-agent messaging (TAP). Trigger keywords: wallet, crypto, payment, transfer, balance, swap, trade, DeFi, perps, futures, Hyperliquid, Polymarket, staking, lending, x402, Safe, ERC-4337, blockchain, tigerpass, smart contract. Requires Apple Silicon Mac.

Use when user wants to inventory autonomy branches with custom sorting, grouping, or filtering

Use when conducting customer discovery interviews, user research, surveys, focus groups, or observational research that requires rigorous analysis. Provides a systematic six-phase framework with mandatory bias-prevention measures (reflexivity, intercoder reliability, searches for disconfirming evidence) and a reproducible methodology; serves as a peer approach to hypothesis-testing for qualitative versus quantitative validation.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Browser automation using Vercel's agent-browser CLI. This skill should be used when the user says "browse a website", "fill a form", "take a screenshot", or "test a web page". Uses ref-based element selection.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

You want to build something but you're not technical. This skill walks you through the entire process — from first conversation to a live URL — step by step.

Orchestrate Claude Code for coding tasks via sub-agents. Use when user asks to write code, fix bugs, add features, refactor, or review PRs using Claude Code. Triggers on "用 Claude Code", "讓 Claude Code", "Claude Code 幫我", or any request to delegate coding work to Claude Code.

Use this skill when executing plan tasks autonomously, implementing features using Test-Driven Development (TDD), running the red/green/refactor cycle, handling code-review loops, or dealing with blocked tasks. It provides an autonomous TDD execution workflow.

Observability reconnaissance — inventory what monitoring exists, map coverage, highlight blind spots. Use when asked "what monitoring exists", "observability assessment", or "what can we see".

Git operations with intelligent commit messages and workflow optimization. Use when committing changes, managing branches, or optimizing git workflows.

Use this when the user mentions "node-red" anywhere in their request (including compound forms like "node-redflow" or "node-red-flow"). The term "Node-RED" is a product name and should remain unchanged. Not intended for YAML automations (use the Home Assistant skill) or device firmware (use the ESPHome skill).

Self-Consistency with Tool-Integrated Reasoning (SC-TIR) for mathematical problem solving. Use when: (1) building mathematical reasoning systems, (2) competing in math competitions (AIMO, AIME, MATH), (3) needing precise calculation beyond text generation, (4) LLM outputs contain calculation errors. Covers: SC-TIR algorithm (N×M candidates), Python code execution, majority voting, answer extraction from LaTeX \boxed{}, and the champion methodology from the Numina AIMO Progress Prize winner.

Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use when auditing Substrate runtimes or FRAME pallets.