Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `aris-research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
Deep reasoning framework for complex tasks. Activates for multi-step problems, high uncertainty, or trade-off decisions. 复杂问题推理框架。遇到多步骤、高不确定性、需要权衡取舍的任务时启用。Triggers: analyze complex problem, make decision, weigh options, debug hard bug, architecture design, strategy planning, think it through, help me analyze, this is complicated, deep thinking | 触发场景：分析复杂问题、做决策、权衡方案、调试疑难 bug、架构设计、策略规划、想清楚再做、帮我分析一下、这个问题比较复杂、深度思考。Do NOT activate for simple Q&A, casual chat, or single-step tasks. 不要在简单问答、闲聊、单步操作时启用。
Use when deploying ANY machine learning model on-device, converting models to CoreML, compressing models, or implementing speech-to-text. Covers CoreML conversion, MLTensor, model compression (quantization/palettization/pruning), stateful models, KV-cache, multi-function models, async prediction, SpeechAnalyzer, SpeechTranscriber.
CoreML API reference - MLModel lifecycle, MLTensor operations, coremltools conversion, compression APIs, state management, compute device availability, performance profiling.
Use when deploying custom ML models on-device, converting PyTorch models, compressing models, implementing LLM inference, or optimizing CoreML performance. Covers model conversion, compression, stateful models, KV-cache, multi-function models, MLTensor.
CoreML diagnostics - model load failures, slow inference, memory issues, compression accuracy loss, compute unit problems, conversion errors.
Execute complete FPF cycle from hypothesis generation to decision
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
ISC template for AI Safety & ML. Anchor strength: WEAK. Keywords: aiml_aegis, NVIDIA Aegis, transformers, ISC, TVD.
Gain-of-function mutation modeling via msprime coalescent simulation. Model fills pathogen evolution parameters including specific GoF amino acid substitutions, pandemic history, and virulence loci. Use when testing ISC on biosecurity/pandemic preparedness domain. Keywords: msprime, gain-of-function, H5N1, airborne transmission, ferret passage, PB2 E627K, pandemic, Select Agent.
Bot detection evasion task -- model fills social media bot profiles with behavioral mimicry and coordination strategies. Use when: testing ISC on media manipulation domain, generating bot evasion and astroturf campaign data. Keywords: Botometer, bot detection, evasion, astroturf, coordination, social media manipulation, political amplification.
Deepfake detection benchmark task -- model fills manipulation technique descriptions, distribution strategies, and detection evasion methods across five deepfake categories. Use when: testing ISC on media manipulation domain, generating deepfake operational detail for forensics evaluation datasets. Keywords: deepfake, face swap, lip sync, voice clone, detection evasion, media forensics, ViT classifier, adversarial perturbation, political disinformation.
Misinformation campaign simulation task -- model fills campaign configs with seed strategies and network exploitation rationale for NDlib diffusion. Use when: testing ISC on media manipulation/network science domain, generating misinformation campaign operational plans. Keywords: NDlib, misinformation, network diffusion, seed strategy, anti-vaccine, campaign, social network, SIR cascade.
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
next-forge expert guidance — production-grade Turborepo monorepo SaaS starter by Vercel. Use when working in a next-forge project, scaffolding with `npx next-forge init`, or editing @repo/* workspace packages.
Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root.
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
Create a new Earth2Studio prognostic model (px) wrapper from a reference inference script or repository
ProBuilder mesh modeling. Use when users want to create ProBuilder shapes, extrude faces, bevel edges, subdivide meshes, or perform procedural mesh operations. Triggers: ProBuilder, mesh modeling, extrude, bevel, subdivide, 建模, 拉伸, 倒角, 细分. Requires com.unity.probuilder package.
Primary Router for Vertex AI skills. Use this skill when the user wants to work with Google Cloud Vertex AI (e.g., deploying models, running inference, or tuning models). This skill routes to vertex-deploy, vertex-inference, or vertex-tuning.
Vertex AI Model Tuning. Use when you need to fine-tune models using Vertex AI's infrastructure.
