AI Ml AI Skills

Data pipeline expert for ETL, Apache Spark, Airflow, dbt, and data quality

Image optimization analysis for SEO and performance. Checks alt text, file sizes, formats, responsive images, lazy loading, CLS prevention, image SERP rankings (via DataForSEO), and image file…

NodeGroup operation Skill for the edgewize nodegroup project. Use this whenever the user wants to query, create, update, delete, bind, unbind, or troubleshoot NodeGroup resources, including node…

AI Berkshire skill: 投资论文追踪：买入后的纪律系统. Source: skills/thesis-tracker.md.

Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describe patent figures with…

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed…

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting…

Internal cross-platform artifact persistence, assembly, citation-audit, and PDF compilation runtime for meta-paper-write.

Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.

Web全栈攻击:SQLi/命令注入/SSTI/XSS/SSRF/NoSQL,认证JWT/OAuth/SAML,LFI/上传,Tomcat/WS/STOMP/XFF/PATH_INFO/CDN502/网宿JS挑战绕过。Use when testing Web injection, auth bypass, server-side, WAF/CDN bypass.

Creates structured Request for Comments (RFC) documents for proposing and deciding on significant changes. Use when the user says "write an RFC", "create a proposal", "I need to propose a change",…

Explain code, concepts, or system behavior with adjustable depth levels

移动开发。iOS、Android、SwiftUI、Jetpack Compose、React Native、Flutter、跨平台。当用户提到移动开发、iOS、Android、跨平台时路由到此。

Compute electronic clinical quality measures (eCQMs) over structured data using CQL/QDM logic, lifting note-derived numerator and exclusion facts from OpenMed to improve measure capture. Use when the…

Run comprehensive quality checks on tabular data (CSV/Excel/TSV/JSON), detecting missing values, duplicates, outliers, format issues, and type inconsistencies to produce an overall score, grade, and…

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML…

Capture the current state of a working thread or conversation into a single coherent Basic Memory note — synthesize where it landed, don't append a log. On re-capture, rewrite the same note in place…

Reference for the `letta mcp` CLI, which finds and invokes MCP tools available to this agent. A system reminder already lists your connected MCP servers and the basic search/schema/call commands;…

Domain routing and boundary guidance for authorized source code security review, including dangerous function tracing, data-flow analysis, logic flaw detection, and dependency review. Use when a task…

Create analytical charts and plots from existing data. Use for exploratory or reporting visuals such as bars, lines, scatters, and dashboards; not for publication-grade scientific figures or…

Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.

Go (Golang) naming conventions — covers packages, constructors, structs, interfaces, constants, enums, errors, booleans, receivers, getters/setters, functional options, acronyms, test functions, and…

Server-side AG-UI streaming protocol implementation: StreamChunk event types (RUN_STARTED, TEXT_MESSAGE_START/CONTENT/END, TOOL_CALL_START/ARGS/END, RUN_FINISHED, RUN_ERROR,…

使用 Classic 预设流程完成单个 change 的轻量调整。在用户明确调用 /comet-tweak、选择 tweak，或恢复 workflow: tweak 时使用。

Interactive click-to-segment using Segment Anything 2 — AI-assisted labeling for Annotation Studio

Magazine-inspired editorial layout with refined serif typography, structured grids, and elegant reading experiences.

Hyperflow memory manager. Use to view, search, add, edit, prune, or clear hyperflow project memory — "show memory", "search memory for X", "clear memory", "what does hyperflow remember about Y". CRUD…

Dollar-cost averaging across all platforms

Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use `a-b-test-design`…

[omh] Hermes Context Budget Review workflow: plan compact context, token/cost budgets, summarization checkpoints, and overflow recovery before long agent work. Use when the user says:…

Embed proteins with Meta AI's ESM-2 (`fair-esm` package). Use this skill when: (1) Extracting per-residue or per-sequence embeddings for downstream ML, (2) Masked-LM likelihood / mutation effect…

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

Formulate and audit real strategy using Richard Rumelt's "Good Strategy Bad Strategy": an honest diagnosis, a guiding policy, and coherent action instead of goals, vision, and wishful thinking. Use…

Researches any project idea against live data from GitHub and Dev.to to surface what already exists, how mature the space is, and where the real opportunity lives. Use when a developer describes…

Extract subtitles and transcripts from Bilibili and YouTube videos. Use when the user wants to get subtitles from B站 (Bilibili) or YouTube, extract Chinese/Japanese video transcripts, watch…

何时用:仅当用户明确指向企业微信(给企微同事/群发消息、查企微会话)时使用;泛指发消息默认走本地通讯工具,邮件走 wecomcli-email。查询可发消息的聊天会话范围,向单聊/群聊发送文本、Markdown、图片、文件、语音、视频消息。

使用 pytest、TDD 方法论、固件（Fixtures）、模拟（Mocking）、参数化及覆盖率要求的 Python 测试策略。

Checks biomedical manuscripts against reporting guidelines such as CONSORT, STROBE, PRISMA, and TRIPOD to identify missing or weak reporting elements before submission or revision.

Use when evaluating stocks through Feng Liu's weak-hand (弱者体系) reverse investing lens: assume you have less information, seek asymmetric risk/reward, buy at points of maximum pessimism, and manage…

Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron…

Create and configure URP Decal Projectors

Pre-print setup for a company about to report: the expectation bar, EPS-quality watch, call questions, scenarios and the reaction framework. Triggers on earnings preview, what to watch for [company]…

Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts

AI DevKit · Connect the current agent session to an available Telegram channel bridge.

查看 Prismer Evolution 插件的调试日志，诊断 hook 运行状态

Verify that Minutes is properly set up and working — model downloaded, mic accessible, directories exist, no stale state. Use when the user says "is minutes working", "check my setup", "verify…

Reconstruct a complete, searchable memory from an untrusted meeting or conversation transcript. Use for EverRoom background transcription-summary jobs when the caller requires the fixed memory JSON…

读取本地或工作区 PDF 内容，并输出结构化解读结果。

Patterns for parallel subagent execution using Task tool with run_in_background. Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be…

Audit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, evaluated from a non-human user's perspective. Use when asked if a product is agent-ready,…

Help users navigate complex product decisions by weighing competing priorities and calculating long-term value. This skill covers build-vs-buy logic, technical debt evaluation, and communicating…