AI Ml AI Skills

Audit, compare, and document Opik integrations across Python SDK, TypeScript SDK, and OTEL/API backend. Use when adding a new integration, reviewing an existing one, or generating first-pass…

Mine your CRM's call notes, meeting notes, support tickets and lost-deal reasons (HubSpot, Pipedrive or Upsales), support chats (Crisp), community threads (Discord) and YouTube comments for the exact…

Ship a CometChat Android v6 app safely — server-minted auth tokens instead of the dev Auth Key, keeping credentials out of the APK, release-build and R8/ProGuard checks, user provisioning server-side,…

Design, organize, and manage Helm charts for templating and packaging Kubernetes applications with reusable configurations. Use when creating Helm charts, packaging Kubernetes applications, or…

Troubleshoot and manage TrueNAS SCALE over SSH. Use this whenever the user mentions TrueNAS, the NAS, ZFS, a pool or dataset, a scrub, a snapshot, replication, a failing or degraded disk, SMART data,…

Create, list, update, delete, and clean up workspaces via the daemon HTTP API at $FRIDAYD_URL. Use when the user asks to create, edit, delete, or list workspaces, spaces, projects, or environments;…

根据剧情、使用方式与美术方向设计道具形制、结构、材质及多视角/关键细节设定图。用于道具设计、道具资产、道具设定图、道具细节图、prop、物品图；输出静态参考图任务说明与资产合同， 本 Skill 独立完成静态参考图任务说明、资产锁定、审核字段、负向约束和可供后续制作直接读取的资产合同。

Designs or reviews logs, metrics, traces, alerts, correlation, dashboards, and diagnostic instrumentation so failures and performance changes can be detected and explained at component boundaries. Use…

Advanced prompt optimization and composition system for all prompt types (system prompts, task-specific, creative, technical, agentic). Use when users need to refine, optimize, or transform prompts to…

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries.…

当开发无服务器函数时，分析函数架构设计，优化冷启动性能，解决函数扩展问题。验证事件处理，设计微服务架构，和最佳实践。

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference…

Celeste-style 2D precision platformer movement — momentum running, coyote time, variable jumps, dash, wall jump/slide, climb stamina, pixel corner correction.

Audit pages and user journeys against a declared WCAG scope. Use when identifying keyboard, screen-reader, focus or contrast barriers and planning verified remediation.

Валидация расширения конфигурации 1С (CFE). Используй после создания или модификации расширения для проверки корректности

Designs remote execution and bridge runtimes for coding agents. Use when implementing remote sessions, local-UI remote-execution, reconnect logic, or permission bridging.

This skill should be used when managing Tailscale mesh VPN networks. Use when the user asks to "check tailscale status", "list tailscale devices", "ping a device", "send file via tailscale",…

Use when adversarial brainstorming is needed after reconnaissance — the Proposer, Devils-Advocate, and Synthesizer each run ONE pass (no rounds); the Don is grilled on the IDEA first, one question at…

This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that…

First-response triage for cross-code (LAMMPS/VASP/QE/MOOSE) simulation failures: classifies the failure signature (nonconvergence, NaN/Inf, exploding energy, unstable timestep, pressure blow-up,…

Explain repeated competitive outcomes - why deals are won or lost against a competitor or across a period - from buyer and deal evidence rather than rep folklore, with the cohort defined, buyer-stated…

Use when auditing an agent codebase against the 12-Factor Agents methodology, reviewing LLM-powered system architecture, or assessing agentic app compliance. Triggers on "analyze agent architecture",…

Navigating the skill ecosystem and guiding onboarding. Lists agents, recommends best fit for tasks. Don't use for task execution (Nexus), agent design (Architect).

E-Mail-Entwürfe auf die Merkmale prüfen, mit denen Spamfilter Werbepost erkennen, und empfangene Nachrichten auswerten, die im Junk gelandet sind. Nutze diesen Skill, wenn eine Mail vor dem Versand…

Use to review a dispatch before handoff, requirements and plans before implementation, or code after implementation. Runs a fresh reviewer, then a separate context-aware adjudicator; returns…

Repository guidance for using Valibot as the schema validation library within the hr-skills monorepo. Use when writing or modifying schemas in packages/hr-skills-ref/src/client/schema.ts or…

Use when building RAG and agent applications over documents with LlamaIndex — SimpleDirectoryReader loading, node parsers, VectorStoreIndex with local or external vector stores (Chroma, PGVector,…

Creates clear, reviewable implementation plans before executing. Use after brainstorming and before writing any code.

Structures validated requirements into an atomic, traceable, typed dependency graph and derives a trustworthy dependency order. Use when normalizing requirement wording, preserving stable IDs,…

Official Capacitor package guide plus Capgo ecosystem plugin recommendations. Use this skill when users need native functionality, want the right official Capacitor package, or need a stronger…

Use before creative product or engineering work when the user wants to design a feature, component, workflow, behavior change, or other solution whose goals, constraints, and tradeoffs need…

Structured first-pass exploration of an unfamiliar codebase — what to read, in what order, what to map, what traps to find. Use when entering any new or inherited project before writing code.

Help developers use the DevExtreme CheckBox component (dxCheckBox) in Angular, React, Vue, jQuery, and ASP.NET Core Controls. Use when someone asks about CheckBox configuration, value states,…

Score the best candidate on the held-out TEST split exactly once and seal the run. Use as the last evaluation step, after optimization stops. The run dir enforces the seal — a second finalize raises…

Enforces Form + GlobalKey<FormState> with TextFormField whose sync validator returns a localized String? (never a hardcoded literal), AutovalidateMode.onUserInteraction, async availability checks…

Applies Kim and Mauborgne's Blue Ocean Strategy to create uncontested market space through value innovation. Uses the Strategy Canvas to map competitive factors, the ERRC Grid to…

stripe should become a local, searchable operational workspace, not only an endpoint wrapper. Use for 587 operation/source entries against https://api.stripe.com/.

Build a proportionate, ordered containment/eradication/recovery plan with risk scores and submit each action via propose_action for policy and human approval; use when a case is confirmed malicious…

Update existing project documentation after code changes. Detects outdated sections, updates module and feature docs, and ensures cross-references remain valid. Use this skill after implementing…

Create and improve Odoo custom module tests using the Odoo test framework. Use when the user asks to add tests, create TransactionCase/HttpCase tests, test Odoo business logic, mock external APIs, use…

Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to…

Use this skill to assess and plan a migration from AWS MSK (Managed Streaming for Apache Kafka) to Confluent Cloud. Triggers on user intent like "migrate MSK to Confluent Cloud", "move off MSK", "MSK…

Load this skill whenever the project supports light/dark mode, colour theme switching, high-contrast mode, or responds to prefers-color-scheme. Under no circumstances hard-code colours that break in…

Diagnoses Kubernetes Connector (K8s Tunnel Client / Helm chart `orca-tunnel`) install and connectivity failures from raw customer input — error text, `helm status`, `kubectl describe`, or pod logs —…

Node.js package management - install, update, run scripts

Guides the agent through Capacitor app development with React — project structure, hooks for native features, state management patterns, using Capacitor plugins in React components, and React-specific…

Manages NotebookLM notebooks — query, add, list, search, enable/disable, remove. Use when a notebooklm.google.com URL appears or user mentions NotebookLM. Handles URLs through its own Chrome agent —…

Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.

Read, write, and search local Obsidian vault markdown files via the filesystem.

用于遇到缺陷、测试失败或异常行为，且必须在提出修复方案前调查根因的场景。未经根因分析不得只修复表象。

Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to…