AI Ml AI Skills

Weekly read on community health — Discord joins, active channels, top contributors, themes and unanswered questions, plus Crisp support conversations and YouTube comments when connected

Turn on CometChat Dashboard extensions in an Android v6 app — stickers, polls, collaborative whiteboard and document, message translation, link preview, thumbnail generation, message shortcuts — and…

Manage registered Bedrock vaults. List all vaults, set a default vault, or remove a vault from the registry. The registry lives in the plugin directory and maps vault names to filesystem paths. Use…

经济金融论文正文写作。根据PAPER_OUTLINE.md大纲和REFINED_DESIGN.md研究设计，生成完整的论文正文草稿（英文/中文），覆盖Introduction到Conclusion所有章节。

Create, track and close one verifiable goal with acceptance criteria and evidence, using the goal tool and the package's Stop continuation.

Upgrade React applications to latest versions, migrate from class components to hooks, and adopt concurrent features. Use when modernizing React codebases, migrating to React Hooks, or upgrading to…

Creates and edits Defold shader files (.vp, .fp, .glsl). Use when asked to create, modify, or configure any Defold vertex shader, fragment shader, or GLSL include file.

Read and manage the NetBird mesh VPN: which peers exist and which are connected, when a peer was last seen, agent version drift, groups, access policies, network routers and routed resources, mesh…

Delete an MCP server from a live LiteLLM proxy. Ask for the server_id and confirm before calling DELETE /v1/mcp/server/{server_id}.

Loads when a session shows many tool calls (often the same name repeated) with no terminal text, no `complete` call, and either hits `stopWhen: stepCountIs(...)` (default 10) OR exhausts max output…

Create, revise, or diagnose screenplays and develop director treatments or pre-storyboard decisions covering causality, character action, dialogue, performance, visual storytelling, sound, editing,…

Designs or reviews relational, document, key-value, graph, or search data models with ownership, invariants, access paths, migrations, consistency, retention, privacy, and recovery behavior. Use for…

OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns

Run a binary industrial-inspection DEFT loop with TAO RT-DETR: measure on frozen KPI/test roles, mine gap-similar real and clean images with SigLIP, accumulate admitted COCO data, retrain from one…

The single source of truth for how TFW commands survey their runtime, choose an execution mode (teams / subagents / sequential), route models, and run the TOH LOOP — the autonomous plan-execute-verify…

Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR…

将具体执行委派给 pi coding agent + ZenMux 便宜执行模型（默认强档 deepseek/deepseek-v4-pro：1M 上下文、推理型；廉价快档 inclusionai/ling-3.0-flash：256K、非思考、更省），Claude 负责任务-模型匹配判断、任务书编写、驱动（一次性 pi -p 或 tmux…

当分析云配置、审查基础设施、优化成本或审计安全时，在部署前验证云资源配置。

Fix auto-fire targeting (survivors, ARPG, tower defense) with pending damage to stop overkill.

Review AAS stack manifests, preview plans and selection evidence in Workbench without applying changes.

Валидация конфигурации 1С. Используй после создания или модификации конфигурации для проверки корректности

Designs execution sandboxes for coding agents. Use when modeling process isolation, filesystem policy, network controls, workspace mounts, or destructive-command boundaries.

Search indexers and manage Prowlarr. Use when the user asks to "search for a torrent", "search indexers", "find a release", "check indexer status", "list indexers", "prowlarr search", "sync indexers",…

Use when beginning a new heist — deploys associates to survey the target codebase, existing tests, dependencies, documentation, and the ledger to produce a reconnaissance dossier for the don's review

This skill should be used when the user needs to translate PowerPoint presentations (.pptx) between languages, preserving formatting and layout. Supports parallel slide-by-slide translation with…

This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration,…

初五的新闻通稿Skill。起草、改写和终审新品发布、公益与社会责任、活动举办、专家观点或全年回顾类新闻稿，适用于消费品及其他企业传播。写稿默认交付完整可审阅稿；正式发布前按终审规则核对事实与承诺。单篇叙事分析使用media-narrative-analysis，是否值得发仍有取舍时再交judgment-hub。

Diagnose HPC runtime and scheduler problems for materials simulations, including MPI/OpenMP/GPU layout, modules, CUDA/Kokkos hints, scratch paths, walltime, job arrays, restart strategy, scheduler…

Pressure-test current messaging - a homepage, a message hierarchy, a pitch, a product page, campaign copy - against the company's positioning, the words customers actually use, what competitors now…

Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.

Lead-Magneten und Erfassungsstrecken einwilligungsbasiert und transparent planen, erstellen und prüfen. Nutze diesen Skill für Whitepaper, Checklisten, Vorlagen, Rechner, Webinare und Kurse hinter…

Use when the user wants to lint a repo following the Karpathy LLM Wiki pattern (raw/ + wiki/ + SCHEMA.md / index.md / log.md). The skill detects path, scans wiki pages + schema layer, reports…

Build ServiceNow Service Catalog items, variables, variable sets, catalog client scripts, record producers, and order guides with reference qualifiers and dynamic pricing.

Copy-paste detector for the hr-skills TypeScript packages (packages/hr-skills-build, packages/hr-skills-ref). Run jscpd to detect duplicated code and measure duplication percentages before…

End-to-end e-commerce product catalog generation — turn a folder of raw product photos into clean packshots, product cutouts, Amazon-style dimensions images, lifestyle scenes, and marketplace-ready…

Validates that a skill's companion scripts declare their OS and binary dependencies correctly, and checks whether those dependencies are actually present on the current machine.

Decides what to do about a third-party dependency after it is adopted, for the whole time it is owned. Use when an advisory, an abandoned or archived upstream, version drift, a license change, or an…

Guides the agent through upgrading a Capacitor app from v5 to v6. Use when the project is on Capacitor 5 and needs the v6 migration path. Do not use for other major versions, plugin-only upgrades, or…

SOC 2 compliance for Terraform — gap analysis, control implementation, evidence collection, and remediation guidance mapped to SOC 2 Trust Services Criteria.

Generate API tests from routes and contracts for authentication, validation, pagination, errors, uploads, and limits in Node.js or Python projects.

Advanced AI safety red team operations covering OWASP LLM Top 10 (2025), prompt injection (direct/indirect/multi-turn), jailbreak techniques (DAN, cognitive hacking, persona-based), data poisoning…

This skill should be used when validate-chunk reports test failures specifically, when the user says "tests are failing", "figure out what's wrong with the tests", "fix the failing tests", or when…

Reviews an existing conjoint study for threats to inference and returns severity-ranked findings on design, estimation, measurement error, external validity, and interpretation. Use when checking…

Follow up on open PRs in skillsaw — fix failing CI, address reviewer feedback, push updates, and validate backward compatibility. Use when an open PR needs maintenance.

Manage context window budget across long sessions — when to compress, what to give subagents, when to start fresh. Prevents silent quality degradation as conversations grow.

Build and configure the DevExpress Blazor TreeList (DxTreeList) — a hierarchical data grid / tree grid for Blazor Server, WebAssembly, and Hybrid apps. Use when displaying tree-structured or…

Drives any shell-invokable coding agent (Claude Code, Codex, Gemini CLI, opencode, Cursor, Factory Droid, GitHub Copilot CLI, Kimi, Pi, Antigravity, OpenClaw, IBM Bob, or a fully custom command) as…

塞尔达公主（塞尔达传说：旷野之息 / 王国之泪）思维视角 Skill。 用塞尔达的价值观和判断方式，分析你的真实问题。 不是角色扮演——用角色的思维框架，不要求角色的世界里有对应事物。 触发词：「用塞尔达的角度」「塞尔达会怎么看」「/zelda-botw-perspective」「切换到塞尔达视角」

Enforces pubspec/lock discipline — caret ranges in pubspec.yaml with a committed pubspec.lock as the only pin, a separately-recorded SDK version string, a version-pinned very_good_analysis include…

Guides leaders in developing and communicating a compelling AI vision that inspires rather than threatens, choosing augmentation over replacement as the strategic paradigm. Covers Perspective 1 (AI…

pokeapi should become a local, searchable operational workspace, not only an endpoint wrapper. Use for 4 operation/source entries against https://pokeapi.co.