Machine learning

Guides ChatGLM2-6B Transformers inference, local demos, FastAPI/OpenAI-compatible serving, C-Eval evaluation, and P-Tuning v2 fine-tuning.

Score prompts for prompt injection with TypeSafe's Jev before they reach an LLM: a reference gate function a backend can call (allow / review / block with a…

Bulk-evaluate a folder of resumes against one job description and flag the ones whose wording mirrors the posting closely enough that a human should look…

Reference for the Claude API / Anthropic SDK - model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.

分析 Android 项目源码，用 LLM 从多维度生成 AI 自动化测试所需的先验知识文档，打包上报测试平台。核心价值：让 AI 测试 Agent 在运行前就知道「测什么、怎么断言、有哪些陷阱」。触发词：「分析我的 Android 项目」「生成测试画像」「理解这个 App 的业务」「提取测试先验知识」「帮我分析…

基于Sorftime MCP的深度选品调研。通过LLM Agent执行多维度分析：数据采集→属性标注→交叉分析→竞品VOC→壁垒评估→选品决策评估。交互式执行，输出Markdown报告和Dashboard看板。

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity…

Run an exact-HEAD GitHub PR review loop: trigger CodeRabbit if it is missing, wait without LLM polling, collect every review surface and unresolved thread…

Autonomous AI agent that modifies and iteratively improves a GPT language model training setup, running experiments within a 5-minute time budget to optimize…

Full desktop computer use for headless Linux servers and VPS.

Infer orthologous genes and gene families across species using OrthoFinder3 (HOG-based phylogenetic orthology), SonicParanoid2, Broccoli, ProteinOrtho, OMA /…

Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs.

Security warnings, patterns scanner, and LLM diff security reviews

Reference for Manus's built-in LLM catalog and how to call it correctly.

Upload a local file or image to a docshare instance (default https://docs.safzan.dev) and return a 24h-TTL download URL.

大模型数据动态定期洞察 Skill。用于自动从小红书、微信公众号、百度、行业媒体采集最新数据，**重点监控头部厂商和外部数商的"招募动态"**（数据标注任务招募、专家招募画像），推断下一代模型发力方向，生成 Excel 报告和市场洞察。…

通过 LaTeX 生成面向客户交付的「企业大模型技术方案」类 PDF（学术/公文风格排版），包含能力与客户系统映射、集成架构示意、分场景收益与 KPI、部署/安全/运维与版本控制表。适用于投标/POC 技术附件、客户技术建议书、需版式统一且可追溯的交付文档场景。

调研能源行业（电力/电网为主，兼顾油气及新能源）上下游企业大模型应用动态的专项技能。覆盖数据建设、行业模型、应用落地三个维度。当用户需要了解能源企业AI/大模型最新进展、生成行业动态报告、查询特定企业或场景的落地案例时，应使用此技能。

GPU/CPU capacity planning for NixOS AI and mining workloads.

Run local multimodal visual reasoning, OCR and image scoring with local LLM models.

🧠 ontology-clawra v5.1 - Local Ontology Reasoning & Learning Engine **USE THIS SKILL WHENEVER** you need structured reasoning, knowledge graph management…

Use for SEO, GEO, and AEO work: keyword research, on-page optimization, AI-citation readiness, technical SEO audits, content gap analysis, competitor…

Fetch public web pages with Jina AI Reader API and convert them into LLM-friendly Markdown.

Comprehensive AI leaderboard for LLM models and AI applications.