Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.

Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.

Coordinate black-box, agent-driven UX acceptance journeys against a disposable EmDash admin site. Use when preparing, dispatching, verifying, or reporting a manual browser journey performed by a separate tester agent. Do not use for deterministic Playwright tests or ordinary code review.

Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect drift or anomalies between snapshots, or do any kind of forensic network analysis in Kubernetes. Also trigger when the user mentions snapshots, raw capture, PCAP extraction, traffic replay, postmortem analysis, "what happened yesterday/last week", root cause analysis, RCA, cloud snapshot storage, snapshot dissection, or KFL filters for historical traffic. Even if the user just says "figure out what went wrong" or "compare today's traffic to yesterday" in a Kubernetes context, use this skill.

Use this skill when an InsForge maintainer has finished an OSS repo change and is ready to open, update, or submit the InsForge PR. Runs the release-quality deterministic E2E gate by building a package.json-derived InsForge test image tag, deciding whether sibling agent-e2e fixture coverage must change, dispatching the Deterministic Fixture E2E workflow, waiting for results, and triaging failures before PR submission.

Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.

Resume work on the current task. Loads the workflow Phase Index, figures out which phase/step to pick up at, then pulls the step-level detail via get_context.py --mode phase. Use when coming back to an in-progress task and you need to know what to do next.

Systematic first principles thinking for any problem domain. Use when the user says "analyze from first principles", "第一性原理", "从根本分析", "从零开始思考", "think from scratch", "question this design", "is this the right approach", "challenge assumptions", "挑战假设", "为什么要这样做", "有没有更好的方案", "why are we doing it this way", or needs to evaluate decisions, designs, or strategies without relying on analogies, conventions, or "best practices". Also triggers on "这个设计合理吗", "从本质上看", "回到基本面", "what's really true here", "what are we assuming", or any request to decompose a problem to its fundamentals.

Run ApiChief in the EF Core repo to emit baselines, summaries, deltas, review files, or breaking-change checks. Use when refreshing `*.baseline.json`, preparing API review artifacts, or validating API changes.

Configure and verify the OpenWork Slack assistant for an approved private-alpha organization, using its existing Slack app and individual-account connector. Use when a user wants @openwork in Slack or needs help installing or linking it.

Install the free OpenWork desktop app on macOS, Windows, or Linux and get the user to a first task. Use when someone wants OpenWork, an open-source Claude Cowork alternative, on their own computer.

Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and also on clear knowledge-closeout intent without the name: syncing or tidying project docs/rules/memory after development ("把文档和记忆整理一下", "收尾时把文档同步掉", "docs 和代码对不上了"), stale or conflicting CLAUDE.md/memory, a clean handoff to a teammate or a fresh session, or auditing whether workspace rules are actually followed. Do not trigger for pure coding/refactoring/debugging tasks, tidying data or prose (JSON, 周报, changelog announcements), or a bare "整理" with no project-knowledge context.

Use Understanding by Design (UbD) to plan one OpenMAIC classroom or a course series around transferable conceptual understanding. Use when the user wants backward design, enduring understandings, essential questions, GRASPS performance evidence, WHERETO learning experiences, or a concept-centered lesson rather than a list of facts. Do not use for visual style cloning, teacher-style imitation, or direct PPT import.

Evidence-based creation of a reusable personal course-making Skill from the user's own classroom and chat history. Use when the user asks to summarize, analyze, or learn from their past course-making records/history and create a personal, exclusive, or reusable Skill, such as “总结我的做课记录，给我做个专属 Skill” or “从我过去的课程和对话里提炼一个个人技能”.

当用户需要创建、读取、编辑或处理 Word 文档（.docx）时，使用此技能。触发场景包括提到“Word 文档”、“.docx”，或要求生成带目录、标题、页码、信头等格式的专业文档；也包括提取或重组 .docx 内容、插入或替换图片、在 Word 文件中查找替换、处理修订或批注，以及将内容整理为正式 Word 文档。如果用户要求生成“报告”“备忘录”“信函”“模板”等 Word / .docx 交付物，也应使用此技能。不要用于 PDF、电子表格、Google Docs，或与文档生成无关的一般编程任务。

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response payloads. Trigger on mentions of E2E testing, headless testing, MCP tool testing, or reproducing issues.

Review local code changes with git diff and update the official docs under docs/ to match. Use when the user asks to document current uncommitted work, sync docs with local changes, update docs after a feature or refactor, or when phrases like "git diff", "local changes", "update docs", or "official docs" appear.

Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.

Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.