发现 Skills

Analyze pull request code changes to determine which tests are affected, recommend test execution order, and identify missing test coverage for modified code paths

Static application security testing using Semgrep for finding vulnerabilities, code smells, and enforcing security policies across codebases.

Visual regression testing skill using Playwright, covering screenshot comparison, visual diff thresholds, responsive testing, baseline management, and CI integration.

Audit past Claude Code transcripts in a chosen scope and date window to extract reusable patterns, then walk through each one to promote it into a slash command, CLAUDE.md rule, memory entry, or new skill. Use when the user wants to retrospectively mine sessions for workflow improvements, recurring corrections, validated approaches, or repeated procedures worth capturing.

Looks up a skill by name, keyword, or domain in the curated catalog (skill-sources.json). Returns the source repo, tier of trust, install methods supported, and any guardrails (overlap warnings, deprecations). Use when the orchestrator detects a missing skill and needs to know where to fetch it from.

Open-source-first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the [REDACTED] decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source-first model router routes all tiers to [REDACTED] by default — Claude only kicks in as an escape hatch when needed. Includes [REDACTED] API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth profile rotation for Venice API keys, Gateway Guardian v4 with billing-aware escalation, through-OpenClaw inference probes, proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, and nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver to prevent dashboard overload, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, and ERC-8004 agent registry reader for discovering trustless agents on Base.

Testing in production with feature flags, canary deployments, synthetic monitoring, and chaos engineering. Use when implementing production observability or progressive delivery.

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.

Use when a user requests a code review, to evaluate code quality, to perform pre-PR checks, or when potential issues are found in code. Trigger scenarios: code review, review, check code, code inspection, code quality, code evaluation, “is there something wrong with this code?”, “please review this code”, pre-merge checks.

Creates visual novel dialogue content for Shadow Work including companion conversations, quest dialogues, NPC interactions, and environmental VN sequences with proper Yarn syntax and Chatterbox function integration. Use when the user asks to create dialogue, conversations, quest text, or VN sequences.

Security audit enforcement for AI agents. Automated security scans and health verification.

Type-safe FileMaker OData client with a Drizzle-inspired ORM and TypeScript code generation. Use it when working with FileMaker databases in TypeScript projects, querying FM data, defining typed schemas, generating types from FileMaker layouts, or troubleshooting fmodata/typegen issues. Triggers on FileMaker + TypeScript integration tasks.

Zod 4 schema validation patterns. Trigger when creating or updating Zod v4 schemas for validation/parsing (forms, request payloads, adapters), including v3 → v4 migration patterns.

Use when creating GitHub Copilot instructions - provides repository-wide and path-specific formats, applyTo patterns, excludeAgent options, and natural language markdown style

Install custom Antigravity and VS Code extensions into the editor and configure status bar buttons

Use this skill when the user asks about payment processing, Stripe integration, checkout flow, payment gateway, PCI compliance, or needs help with payments or Stripe.

Drive development using delegated agent workflows. Coordinates multi-agent task execution with proper supervision and result integration.

Official Figma Developer MCP integration for QuanuX. Allows agents to inspect designs, extract variables, and generate code from Figma files.

Show detailed token ROI report across all tracked sessions

Earnings preview / recap skill. The CLI automatically switches by “days to next / last earnings date”: if < 14 days it goes to preview (fetches A-share earnings forecasts via stock_yjyg_em or U.S. sell-side consensus), if within 14 days after release it goes to recap (fetches A-share quarterly reports via stock_yjbb_em or U.S. surprise %), otherwise it uses between. Invoked when the user asks questions like “When is Moutai's next earnings / How did this quarter perform / Earnings commentary / Q1 commentary / earnings forecast / earnings flash”. Reuses analyze-disclosure for earnings dates + analyze-estimates for consensus estimates. Does NOT require LLM_API_KEY; earnings commentary and interpretation of gaps vs. consensus are authored by Claude.

Linear: manage issues, projects, teams via GraphQL + curl.

Extract text from PDFs/scans (pymupdf, marker-pdf).

Build and manage a persistent knowledge base (a "second brain") using Markdown files. Use this when you need to store, retrieve, or link complex concepts, project context, or to "remember" information across sessions. Triggers include: (1) "Remember this", (2) "Build a knowledge base", (3) "Document this concept", and (4) summarizing findings into long-term memory.

This skill should be used when the user says "configure hooks", "set up quality gates", "add TaskCompleted hook", "configure PostToolUse hook", "set up permission hooks", "create hook configuration", "add typecheck hook", "set up test-on-complete hook", or wants to configure event-driven hooks and quality gates for their agentic company project.