Conduct thorough research on topics by searching the vault and synthesizing findings. Use when the user asks to research a topic, dig into something across notes, or wants a synthesis of what the vault knows about a subject.

Conduct an end-of-day review to capture progress and set up tomorrow. Use when the user asks for a daily review, end of day wrap-up, EOD note, what they did today, or wants to reflect on the day and plan tomorrow.

全局归档协议。只要任务需要写入任何文件（含 PLAN.md、报告、JSON 等归档物），必须按本技能执行 Session→ARCHIVE_ID、TIMESTAMP、双轨路径（根段须为 archives/）、回读校验与状态回执；WebUI 的 archive_grid 必须用 Markdown 中语言标识为 json 的围栏代码块输出。

Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say "write a report", "draft a proposal", "make a contract", "fill in this form", "reformat to match this template", or any task whose final output is a .docx file. Even if the user doesn't mention "docx" explicitly, if the task implies a printable/formal document, use this skill.

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.

Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment. Trigger for: - Explicit learning requests: teach, explain, ELI5, walk me through, quiz me, flashcards, "I'm rusty on"; definitions ("what is X") - Terse concept names implying "help me understand this": "Galois theory," "transformers, from scratch" - Confusion signals: "won't stick," "keep mixing these up," "not getting it" - Learning-path questions: prerequisites, sequencing, what to study before X - Conceptual questions about mechanisms, causes, or dynamics Don't trigger for: - Tasks: coding, writing, calculation, translation, factual lookup, news updates - Personal troubleshooting; resource/textbook recommendations - Claude's evaluative verdict: opinion prompts ("do you think X", "settle this", "honest take", "is X dead / still taken seriously") and interpretive takes ("was X really as harsh as people say")

Create, configure, and maintain custom agent profiles and author new skills via the `repl` tool. Use when the user wants to create an agent profile, build a custom agent, modify agent capabilities, attach or detach skills/connectors on a profile, author a skill, or inspect which connectors and tools are available. Also use whenever you need the `host.agents.*` or `host.skills.*` Python SDK.

Query images with a local Ollama vision model without loading the image into the main agent context. Use when you need to describe a screenshot, check whether rendered content is present, detect overlapping elements, or ask any visual question about a PNG/JPEG/WebP file. Requires Ollama running locally with the Gemma 4 multimodal model (`gemma4` on Ollama). Script: .agents/skills/vision/scripts/ask.py. Trigger phrases: "describe image", "what does this screenshot show", "does the canvas contain content", "check screenshot visually", "look at this image", "any overlapping elements", "vision query".

Working pattern for enterprise-edition features in Grida — the commercial/hosted concerns (entitlement, BYOD, billing) on top of the OSS core. Anchor for the `GRIDA-EE: <surface>` grep marker, `(ee)` route group, `*-hosted` package suffix, and namespaced `grida_*` schema. Use when adding or touching an EE-only feature, or deciding whether a feature is EE territory. Surface skills (`ee-billing`) are siblings.

NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and produces general-purpose visual features. Use when training, exporting, or running inference for a TAO NVDINOv2 backbone. Trigger phrases include "train NVDINOv2", "self-supervised ViT pretraining", "DINOv2 backbone", "visual representation learning".

Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Deformable-DETR model. Trigger phrases include "train deformable-detr", "Deformable DETR object detection", "lightweight DETR detector".

Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use when training, evaluating, exporting, or running inference on a TAO action-recognition model. Trigger phrases include "train action recognition", "video action classification", "RGB + optical flow action model", "TAO ActionRecognition".

Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI. Do NOT use for UPHY lane allocation or ODMDATA edits.

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

Use the `http` package to execute GET, POST, PUT, or DELETE requests. Use when you need to fetch from or send data to a REST API.

Performs a comprehensive, multi-step code review of pull requests or local code changes, using iterative refinement (generation, critique, synthesis) to ensure high-quality, actionable feedback. Use when you need to review code changes thoroughly.

Builds SQLiteCpp with Meson. Use when configuring Meson builds, tests, or Meson options.

Cache and refresh remote git repositories under ~/.cache/checkouts/<host>/<org>/<repo> so future references can reuse a local copy. Use this skill when the user points you to a remote git repository as reference or you encountered a remote git repo through other means.

Transcribe local audio/video and Apple Voice Memos quickly with cached MLX Whisper models, including bad/low-quality audio.