发现 Skills

Automate Rippling tasks via Rube MCP (Composio). Always search tools first to retrieve current schemas.

Derive security requirements from threat models and business context. Use when translating threats into actionable requirements, creating security user stories, or building security test cases.

Verifies code implements exactly what documentation specifies for blockchain audits. Use when comparing code against whitepapers, finding gaps between specs and implementation, or performing compliance checks for protocol implementations.

Expert in threat modeling methodologies, security architecture review, and risk assessment. Masters STRIDE, PASTA, attack trees, and security requirement extraction. Use for security architecture reviews, threat analysis, and deriving security requirements.

Text storyboard: the translation layer from script to image, converting abstract literary works into concrete audiovisual descriptions. Invoked when the user needs to convert a novel or script into a text-based storyboard.

FFmpeg installation and verification skill providing cross-platform installation solutions.

Run a retrospective on recent work. Analyzes what went well, what didn't, and captures improvements for future sessions.

Autonomous agent for tackling big projects. Create PRDs with user stories, then run them via the CLI. Sessions persist across restarts with pause/resume and real-time monitoring.

Visual and front-end development assistant powered by Google Gemini 3. Use for UI analysis, design comparison, accessibility audits, color palette extraction, screenshot-to-code conversion, generating UI assets, and text-based design assistance from briefs.

Error handling best practices across languages — error types, recovery strategies, user-facing messages, and logging. Reference when implementing error handling or designing error flows.

Git best practices including commit message conventions, interactive rebase, conflict resolution, and repository hygiene. Reference for all git operations.

3D graphics in the browser. Three.js = core library. React Three Fiber (R3F) = React renderer for Three.js.

Systematic website audit (stack detection, 9 phases). Use when: "audit", "website audit", "site audit", "check website".

Test-Driven Development (TDD Red-Green-Refactor)

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

StoreKit updates and in-app purchase integration guidance for UIKit/AppKit apps.

AIDA - Multi-agent project generation with auto-init and full pipeline execution. Generate a complete project using multi-agent orchestration with TDD and quality gates. Enforces strict quality requirements via Stop Hooks (ralph-loop style).

MCP toolkit for the task lifecycle (aramb_tasks.*). Use these to create, update, and list tasks. The task lifecycle is the team-mode primitive; this toolkit is hidden in solo mode by tools/list filtering.

Use when creating git commits to ensure commit messages follow project standards. Applies the 7 rules for great commit messages with focus on conciseness and imperative mood.

Capability evaluation and self-optimization. Automatically assesses performance after task completion, logs errors, and continuously improves agent capabilities.

Generates creative solution ideas through brainstorming. Use this when developing multiple approaches to address an identified problem.

Parallel build orchestrator for SystemVerilog creation tasks. Decomposes designs into independent modules, builds in parallel phases, runs verification on each component, then integrates. Example: "/gf-build RISC-V CPU with ALU, regfile, decoder, control FSM"

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.