Loading...
Loading...
Found 359 Skills
Decide how much proof a piece of work needs — from just looking at it, to walking the flow, to writing a test, to writing the test first. Use right after a feature works, before changing code that already works, and every time something that used to work breaks. Also use when the builder asks whether they need tests, or when a change touches money, auth, permissions, data they can't get back, or logic with rules and edge cases.
M365 email and collaboration security telemetry for detection engineering — Exchange Online mail flow (transport rules, journaling, DLP), mailbox delegation and forwarding rules, OAuth app permissions on mailboxes, SharePoint/OneDrive external sharing, Teams guest access, Purview Unified Audit Log (UAL) event types, MailItemsAccessed semantics, and BEC/phishing detection patterns. Use when authoring detections targeting email-based attacks, business email compromise, data exfiltration via collaboration tools, or insider threat indicators.
Covers Sale module — API choice (D7 object model vs ORM vs CSale*), FUSER, Basket, Order create/update, properties, statuses and events, payments, delivery/shipments, discounts and coupons, reservation/deduction, permissions, buyer accounts. Applied for cart/checkout, order lifecycle, pay/ship integration, and order automation. Key terms — sale, Basket, Order, Fuser, Payment, Shipment, PaySystem\Manager, Delivery\Services\Manager, doFinalAction, STATUS_ID, DiscountCouponsManager, tryReserve, CanUserUpdateOrder.
Apply James's AI trust principle to both outputs and autonomous actions. Use when generating or executing consequential changes, delegating tasks or assessing reliability; require independent verification, bounded permissions/time/data/money and recoverability proportionate to impact.
Meta Quest Passthrough Camera Access (PCA) for Unity — access the forward-facing RGB cameras on Quest 3 / Quest 3S to feed Computer Vision and Machine Learning pipelines. Use when capturing the passthrough camera image/texture, reading the camera pose and intrinsics, projecting camera pixels into world space via `PassthroughCameraAccess.ViewportPointToRay`, wiring camera frames into ML/CV models, or reasoning about resolution, permissions, vendor tags, and the pinhole/principal-point model. For projecting the image onto a flat world-space surface (frustum-slice quad / image-plane overlay) see references/principal-point-offset.md; for placing 2D ML detections as world-space 3D bounding boxes see references/detection-bounding-boxes.md. Skip if the user only wants to cast the user's POV (use the Media Projection API instead) or is doing screen-space-only overlays.
Use when writing, running, configuring, reviewing, or debugging code in a Deno project, or when scaffolding a new one. Covers dependency management with deno install and deno add, package.json and node_modules support, npm and JSR packages, permissions, where configuration belongs across package.json, tsconfig.json and deno.json, workspaces, the built-in toolchain (fmt, lint, test, check, bench, compile), and publishing.
Use when generating, integrating, refactoring, reviewing, or debugging Make record-list actions: CanvasTable actions are the default desktop/tablet selection and batch workflow, while 手机/phone 卡片/card and mobile detail pages reuse single edit/delete actions. Triggered by 复选框, 行操作, 选择操作栏, 编辑, 删除, 批量编辑, 暂无可用的操作, selectAll, Shift selection, selectionIntent, 手机卡片操作, 手机详情操作栏, 行级写权限预检, noPermissionRecordIds, record-write-permission, records/bulk, @qfei-design/make-app-actions, or action tests. Covers headless single-record action reuse, independent update/delete/bulkUpdate permissions, Canvas selection intent, immutable snapshots, Service precheck/bulk contracts, denial feedback, stale safety, and tests. Does not own CanvasTable internals, principal IAM policy, general Service layering, page shell, field editor internals, auth, runtime packaging, DSL, Make CLI, or filter/sort/group semantics.
Harden Tauri 2 applications with capabilities, permissions, scopes, CSP, and trust-boundary review. Use when exposing native APIs, adding plugins, handling untrusted content, or auditing a Tauri app.
Develop, build, deploy, and validate ordinary sandboxed HarmonyOS applications on a connected device. Use for the inner dev loop on an existing project when its APIs and permissions are available to ordinary apps. If they may require `hos_system_app`, an elevated APL, ACL/provisioning, or a Full SDK system API, use `ohos-system-app-dev` for privilege preflight.
First run of the video agent skills - sets up video editing on the creator's computer and in their project - tools, the video-agent/ folder, the Remotion studio, the creator's voice.md, permissions, and the optional accounts (Treg for Instagram, TikTok and YouTube, an ElevenLabs key, Codex). Use when the user says setup, onboarding, install, "start here", configure, connect my account, Treg, first time using video-script, video-edit, video-publish or any video skill, or wants to update their voice, niche, CTA or brand color. Checks Node, ffmpeg, yt-dlp and git with install commands for macOS, Windows and Linux, writes voice.md from their own videos or a short interview, pre-approves the tool commands in .claude/settings.json.
Anticipate permissions needed for a task and group requests into a numbered list for selective approval. Use when the user asks to predict or batch authorizations before execution.
Migrate Python LangChain, LangGraph, or Deep Agents applications to Pydantic AI and, when the source uses harness features, Pydantic AI Harness. Use for LangChain agents, chains, LCEL, direct LangGraph graphs, persistence, interrupts, streaming, and `create_deep_agent` projects with planning, filesystem or sandbox backends, skills, memory, subagents, permissions, approvals, or Deep Agents Code hosts.