AI Ml AI Skills

Полный цикл создания расширения конфигурации 1С (CFE) - от scaffold до валидации. Workflow: cfe-init → borrow → patch → form → validate.

Designs plugin systems for coding-agent runtimes and CLIs. Use when adding plugin manifests, extension points, built-in plugins, or reloadable agent integrations.

This skill should be used when managing calendars and contacts on a self-hosted Radicale CalDAV/CardDAV server. Use when the user asks to "list my calendar", "what's on my calendar this week", "show…

Use when about to claim work is complete, fixed, or passing — sweeps for evidence before any assertions, because unverified claims are invalid

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a…

设计、优化和测试AI模型提示词，使用系统化的提示工程技术，包括少样本学习、思维链和结构化输出。

This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and…

Run ESM protein language models — ESMC for embeddings and representations, ESMFold2 for structure prediction, and ESM3 for generative multimodal protein design across sequence, structure, and function…

初五的决策级行业研究Skill。围绕行业进入、年度战略、投资／并购初筛、竞争定位或出海，研究行业边界、规模周期、情景、客户采用、技术成本、利润池、单位经济、公司竞争、GTM、渠道、政策与资本，交付可复核报告、证据底稿及风险机会判断。消费者专项使用consumer-research，媒体呈现研究使用industry-media-research。

Parse, navigate, and query materials science ontology structures — browse class hierarchies, inspect individual classes and their properties, look up object and data property definitions with…

Develop, pressure-test, or refresh product positioning against the alternatives customers actually consider. Use when defining a market position, revising positioning after competitor or category…

Vercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool calls, streaming responses, or building chat UI. Triggers on useChat, @ai-sdk/react,…

Technische, inhaltliche und internationale SEO-Probleme für Deutschland und den DACH-Raum prüfen und priorisieren. Nutze diesen Skill bei Ranking- oder Trafficeinbrüchen, bei Problemen mit Crawling,…

Use when user wants to break a PRD into Azure DevOps work items via vertical-slice plan. Workflow: read PRD → quiz user to lock durable decisions → draft slices with HITL/AFK + blocked_by → call az…

Read and change the classic Workflow engine (wf_workflow, wf_workflow_version, wf_activity, wf_transition, wf_context) — the checked-out-version model, running contexts, and when the right answer is…

Security-first vetter for SKILL.md files — checks permissions, suspicious patterns, and metadata before installing or publishing skills. Useful for validating third-party skills for this repo.

Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality,…

Red-green-refactor discipline. Use when writing new functionality.

Chooses a system's infrastructure foundation from a requirements-derived fit profile, and re-checks at any later point whether the foundation in use still fits. Use when choosing or inheriting a…

Guides the agent through upgrading a Capacitor app project to a newer major version. Covers multi-version jumps, dependency alignment, native platform checks, and verification. Do not use for plugin…

Structured platform troubleshooting — classifies the problem layer, collects evidence, forms a root-cause hypothesis, and proposes a fix with validation and rollback steps.

Search arXiv papers by keyword, author, category, or ID.

Use when reviewing a skillsaw PR. Dispatches 7 specialist reviewers (Architecture, Python Expert, Security & Supply Chain, QA Engineer, Technical Writer, Ecosystem, Slopinator) as parallel sub-agents…

Select optimal subagent topology (hierarchical, mesh, ring, star) based on task structure; adds Ruflo-style swarm intelligence to Superpowers

Create and use DevExpress Dashboard parameters — DashboardParameter, look-up settings (StaticListLookUpSettings, DynamicListLookUpSettings), pass parameters to SQL queries or stored procedures…

Establish the starting point. Use after implement-and-check and before any algorithm. Creates the run directory, freezes the seeded train/val/test split (written once), scores the unmodified seed…

Enforces a right-sized feature-first layered MVVM Flutter architecture — features are folders and cross-cutting foundations become packages only when a compile wall earns it, a strict downward-only…

Builds and evaluates Kaplan and Norton's Balanced Scorecard across four perspectives: Financial, Customer, Internal Process, and Learning and Growth. Creates strategy maps linking causal chains from…

randomuser should become a local, searchable operational workspace, not only an endpoint wrapper. Use for 1 operation/source entries against https://randomuser.me.

Incident-response playbook for suspected data exfiltration — archive staging, uploads to cloud storage, exfil over C2 or DNS, removable media and exposed cloud buckets; use when Wazuh flags staging or…

Independent single-phase or batch review of implementation plans against scope, codebase reality, actionability, and cross-phase consistency. Produces per-phase structured reviews with severity-rated…

Odoo OWL frontend engineering guidance covering components, templates, reactivity, hooks, props, plugins, registries, debugging, assets, and OWL 1/2/3 migration. Use when working with Odoo frontend…

"How should this be tested?" Evidence-backed risk map → scope and depth across functional domains and 10 testing-type axes; includes carry signals, excludes reasons. Not for: writing cases,…

Build and deploy Apache Flink user-defined functions (UDFs) in Java for stream processing over Kafka. Use this skill when users want to create scalar UDFs, user-defined table functions (UDTFs), or…

Load this skill whenever the project contains forms, inputs, selects, checkboxes, radio buttons, text areas, or any validation flow. Under no circumstances create a form without visible labels, error…

Triage an alert where a hosted AI or LLM inference service is abused through compromised credentials (LLMjacking), enabling or requesting foundation-model access, a spike of unauthorized inference,…

Analyzes the full impact of fixing an Orca alert — what closes, what breaks, and what the environment looks like after the fix. Use when user asks about impact, consequences, or blast radius of fixing…

Access MCP (Model Context Protocol) tool servers. Use mcp to list available servers and tools, or invoke MCP tools by server and tool name.

NestJS backend build agent for REST/GraphQL APIs, microservices, and enterprise backends. Extends build-agent with NestJS architectural patterns, dependency injection, testing strategies, and security…

A skill served from a local directory source.

Guides the agent through upgrading a Capacitor plugin to a newer major version. Supports upgrades from Capacitor 4 through 8, including multi-version jumps. Covers automated upgrade via official…

Run Codex code review with Claude's independent double-check. Use when asked "codex review", "review my code with codex", or wants Codex to review code changes. For adversarial review use…

从《医学穷源集·卷二》（明·王肯堂 撰，殷宅心 辑释；herbtcm.com…

Manage Linear issues, projects, and cycles via the Linear GraphQL API.

Git 工作流专家。规范化版本控制，确保提交历史清晰可追溯。支持 Conventional Commits 规范、Pull Request 最佳实践、分支管理策略和自动化工作流。

Find missing interface and service states such as loading, empty, partial, permission, timeout, stale data, validation, failure, interruption, and recovery. Use when a designer asks what states or…

Add or refine depth through elevation systems, raised and inset surfaces, layered overlap, and meaningful shadow behavior so interfaces feel structured instead of flat. Use when the user mentions…

Use when improving an existing website or codebase while retaining its recognizable identity, especially when evidence, scope, or redesign approval is uncertain.

Use when designing, building, or reviewing settings screens, account management, preferences, profile pages, or any destructive account action — delete account, change email/password, data export,…

Handles responsive web and mobile layout using constraints, hierarchy and platform-aware composition.

Liquid Background Hero (Open Design) — use only when explicitly invoked, not for general design requests