发现 Skills

Analyze investment research reports (supports PDF/images/Word and multiple other formats), extract stock information and generate structured investment strategy tables

Learn patterns from a specific GitHub repository. Clones, analyzes code structure, extracts patterns, and populates procedural memory. Use for: targeted learning from known quality repos, quick knowledge acquisition, specific pattern extraction. Triggers: /repo-learn, /curator-repo-learn, 'learn from repo'.

Produce a verifiable technical specification before coding. 6 mandatory sections: Interfaces, Behaviors, Invariants (from Aristotle Phase 2), File Plan, Test Plan, Exit Criteria (executable bash commands + expected results). Use when: (1) before implementing features with complexity > 4, (2) as Step 1.5 in orchestrator workflow, (3) when requirements need formalization. Triggers: /spec, "create spec", "write specification", "technical spec".

SDD-RIPER workflow executor with phase gating

Shopify app development - Remix, Admin API, checkout extensions

Infrastructure and development cost estimation for technical projects. Use when planning budgets, evaluating build vs buy decisions, or projecting TCO for architecture choices.

Business investment analysis and capital allocation advisor. Use when evaluating whether to invest in equipment, real estate, a new business, hiring, technology, or any capital expenditure. Also use for ROI calculations, IRR, NPV, payback period, build vs buy decisions, lease vs buy analysis, vendor evaluation, or deciding where to allocate limited budget for maximum return.

../../../agents/engineering-team/cs-workspace-admin.md (Workspace administration documentation)

../../../marketing-skill/skills/launch-strategy/SKILL.md

MCP Server Builder

../../../c-level-advisor/skills/strategic-alignment/SKILL.md

Build n8n workflow automations — nodes, expressions, JavaScript code, and integration patterns. Use when creating or debugging n8n workflows.

Use when creating or updating pull requests — generates accurate titles and descriptions from the diff. Also covers PR state changes (draft, ready, close, reopen, merge).

Use when the current PR has AI reviewer comments (CodeRabbit, Cursor, etc.) that need to be reviewed and addressed, or when the user says "pr review", "review comments", "fix review comments".

Use when writing MySQL queries, designing Aurora schemas, optimizing indexes, troubleshooting slow queries, fixing deadlocks, planning schema migrations, or tuning Aurora connection pools and failover.

Patterns for implementing authorization in erify_api with current StudioMembership + AdminGuard behavior, plus planned RBAC references

Presentation Optimization Assistant. Use this skill when the user requests the Presentation Optimization Assistant. Do not use it when the user's goal does not match this skill description.

Apply when creating, refactoring, changing, planning (plan mode) or reviewing any file that is a Spring configuration class, bean definition, dependency injection wiring, or configuration properties binding.

This skill should be used when the user asks about Formula 1 races, the F1 calendar, race schedules, session times, or race round details. It runs a bundled F1 CLI tool powered by the OpenF1 API.

Intelligent Multi-AI Router & Orchestrator. Owns and invokes the Playwright/Browser-Use multi-AI engine at skills/orchestrator/engine/. This skill is the PRIMARY ENTRY POINT for all research and multi-AI tasks. It reads the user's intent and routes to the correct specialist skill: - "landscape" / "market map" / "ecosystem" / "vendor landscape" / "market overview" / "competitive landscape" / "category survey" / "industry landscape" / "Gartner-style" → landscape-researcher skill - Product URL + research intent, specific product name + evaluate/benchmark/ research/analyse, "competitive intelligence", "capabilities report" → solution-researcher skill - "comparison matrix" / "add platform" / "update matrix" / "combo column" / "verify ticks" / "reorder matrix" → comparator skill - Any other multi-AI task, arbitrary prompt, or general question → direct multi-AI (this skill runs the engine and consolidates generically) USE THIS SKILL proactively whenever the user asks to run something across multiple AIs, compare AI outputs, get multi-source perspectives, or whenever a specialist skill (landscape-researcher, solution-researcher, comparator) would be appropriate. When in doubt, activate this skill — it will route correctly.

Web A/B: feature flags LaunchDarkly/Unleash, cookie segmentation, Cloudflare Workers A/B, header routing

Autonomous GenPark AgentsOrchestrator Agent Personality agent for the GenPark Nexus ecosystem.

Autonomous GenPark Blockchain Security Auditor agent for the GenPark Nexus ecosystem.

Autonomous GenPark Compliance Auditor Agent agent for the GenPark Nexus ecosystem.