mcp-tool-writer
Create, modify, and manage MCP tools for the Naki mahjong AI assistant. Use when adding new MCP tools, modifying existing tools, or fixing tool-related issues. This skill understands the Protocol-based MCPTool architecture.
critique
Multi-perspective dialectical reasoning with cross-evaluative synthesis. Spawns parallel evaluative lenses (STRUCTURAL, EVIDENTIAL, SCOPE, ADVERSARIAL, PRAGMATIC) that critique thesis AND critique each other's critiques, producing N-squared evaluation matrix before recursive aggregation. Triggers on /critique, /dialectic, /crosseval, requests for thorough analysis, stress-testing arguments, or finding weaknesses. Implements Hegelian refinement enhanced with interleaved multi-domain evaluation and convergent synthesis.
constraints
Formal constraint theory unifying deontic logic (P/O/F/I operators), Juarrero's trichotomy (enabling/governing/constitutive), Hohfeldian rights (claim-duty, privilege-noright, power-liability, immunity-disability), and category-theoretic composition. Use when modelling permissions, obligations, prohibitions, rights structures, agent authority, governance systems, ontology validation, or any domain requiring formal constraint specification. Integrates with ontolog via λ-calculus mapping.
yandex-keyword-research
Research keywords for Russian/CIS markets using Yandex Wordstat data. Analyzes search volumes, trends over time, and regional distribution. Use when user asks about keyword research, search volumes, trending topics, or what people are searching for in Russia/CIS.
searching-web
Searches the web using Tavily API for real-time information. Use when the user needs current information, wants to search the internet, or asks questions requiring up-to-date web data.
nsforge-formula-search
外部公式搜尋。觸發詞：搜尋公式, Wikidata, BioModels, 物理常數, PK模型, 反應動力學。
energyplus-assistant
Use this skill when analyzing EnergyPlus IDF building energy models, including QA/QC validation, HVAC topology analysis, ECM testing, or running simulations. Supports fast validation without Docker (direct parsing) and comprehensive analysis with MCP tools when needed. Handles Windows path formats, environment detection, and intelligent method selection. (project)
nsforge-derivation-workflow
步進式推導工作流。觸發詞：推導, derive, 組合公式, 建立模型。
test-model
Validate model correctness using MCP tools. Checks element references, relationships, view definitions, and syntax.
code-review
Review code for quality, bugs, security issues, and best practices. Use this skill when the user asks for code review, code analysis, or wants feedback on their code.
code-review
Expert in conducting thorough code reviews for Python projects using GitHub MCP, covering test coverage, security practices, PEP 8 compliance, and code organization. Use when reviewing code or PRs.
nsforge-verification-suite
驗證工具組合。觸發詞：驗證, verify, check, 維度, dimension。
qa-security-scan
Security scanning templates and checklists for OWASP Top 10, authentication, authorization, data protection. Use when conducting security testing or vulnerability assessment. This skill provides comprehensive security testing: - OWASP Top 10 checklist with remediation - Authentication and authorization testing - Data protection verification - Security report generation - Integration with Codex CLI MCP for automated scanning Triggers: "security scan", "vulnerability check", "OWASP", "security test", "セキュリティスキャン", "脆弱性チェック", "セキュリティテスト"
local-test
Test local Jekyll build and visualize pages using Playwright MCP. Starts the development server, navigates through key pages, captures screenshots, and validates rendering. Use when testing local changes before deployment.
playwright
Browser automation with Playwright MCP. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows. Use when user wants to test websites or automate browser interactions.
autonomous-ui-inspection
Autonomous UI inspection using a dual channel: (1) visual screenshots via Playwright MCP tools, (2) numeric layout metrics via Puppeteer scripts. Includes server --check standardization so agents can start/stop reliably.
e2e-tester
End-to-end testing using Playwright MCP. Automate user workflows, take screenshots, validate UI/UX, perform visual regression testing, and verify complete user journeys. Use after feature implementation or before deployment.
playwright-wrapper
Playwright 브라우저 자동화 래퍼. MCP 대신 CLI 직접 호출. E2E 테스트, 스크린샷, 웹 자동화에 사용.
