Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B).
Manage Linux systems covering systemd services, process management, filesystems, networking, performance tuning, and troubleshooting. Use when deploying applications, optimizing server performance, diagnosing production issues, or managing users and security on Linux servers.
Writing optimized, secure, multi-stage Dockerfiles with language-specific patterns (Python, Node.js, Go, Rust), BuildKit features, and distroless images. Use when containerizing applications, optimizing existing Dockerfiles, or reducing image sizes.
Creates comprehensive dashboard and analytics interfaces that combine data visualization, KPI cards, real-time updates, and interactive layouts. Use this skill when building business intelligence dashboards, monitoring systems, executive reports, or any interface that requires multiple coordinated data displays with filters, metrics, and visualizations working together.
API design and implementation across REST, GraphQL, gRPC, and tRPC patterns. Use when building backend services, public APIs, or service-to-service communication. Covers REST frameworks (FastAPI, Axum, Gin, Hono), GraphQL libraries (Strawberry, async-graphql, gqlgen, Pothos), gRPC (Tonic, Connect-Go), tRPC for TypeScript, pagination strategies (cursor-based, offset-based), rate limiting, caching, versioning, and OpenAPI documentation generation. Includes frontend integration patterns for forms, tables, dashboards, and ai-chat skills.
Vector database implementation for AI/ML applications, semantic search, and RAG systems. Use when building chatbots, search engines, recommendation systems, or similarity-based retrieval. Covers Qdrant (primary), Pinecone, Milvus, pgvector, Chroma, embedding generation (OpenAI, Voyage, Cohere), chunking strategies, and hybrid search patterns.
Guide incident response from detection to post-mortem using SRE principles, severity classification, on-call management, blameless culture, and communication protocols. Use when setting up incident processes, designing escalation policies, or conducting post-mortems.
[wget][wget] 是一个命令行的下载工具。对于我们这些 Linux 用户来说，几乎每天都在使用它。下面为大家介绍几个有用的 wget 小技巧，可以让你更加高效而灵活的使用 wget。
Writing self-loop for surveys: run the strict section-quality gate, then rewrite only the failing `sections/*.md` files until the report is PASS. **Trigger**: writer self-loop, writing loop, quality gate loop, rewrite failing sections, 自循环, 反复改到 PASS. **Use when**: per-section files exist but C5 is FAIL/BLOCKED (thin sections, missing leads/front matter, citation-scope violations, generator voice). **Skip if**: you are still pre-C2 (NO PROSE), or evidence packs are incomplete (fix C3/C4 first). **Network**: none. **Guardrail**: do not invent facts; only use citation keys present in `citations/ref.bib`; keep citations in-scope per `outline/evidence_bindings.jsonl`; do not add/remove citation keys during rewrites.
Write the survey's front matter files (Abstract, Introduction, Related Work, Discussion, Conclusion) in paper voice, with high citation density and a single evidence-policy paragraph. **Trigger**: front matter writer, introduction writer, related work writer, abstract writer, discussion writer, conclusion writer, 引言, 相关工作, 摘要, 讨论, 结论. **Use when**: you are in C5 (prose allowed) and need the paper-like shell to stop the draft reading like stitched subsections. **Skip if**: `Approve C2` is missing in `DECISIONS.md`, or `citations/ref.bib` is missing. **Network**: none. **Guardrail**: no invented facts/citations; no pipeline jargon in final prose; no repeated evidence disclaimers; only use keys present in `citations/ref.bib`.
Fill `outline/tables_index.md` from `outline/table_schema.md` + evidence packs (NO PROSE in cells; citation-backed rows). **Trigger**: table filler, fill tables, evidence-first tables, index tables, 表格填充, 索引表. **Use when**: table schema exists and evidence packs are ready; you want a compact, citation-backed index table to support later writing and Appendix table curation. **Skip if**: `outline/tables_index.md` already exists and is refined (>=2 tables; citations in rows; no placeholders). **Network**: none. **Guardrail**: do not invent facts; every row must include citations; do not write paragraph cells.
Create a novelty/prior-work matrix comparing the submission’s contributions against related work (overlaps vs deltas). **Trigger**: novelty matrix, prior-work matrix, overlap/delta, 相关工作对比, 新颖性矩阵. **Use when**: peer review 中评估 novelty/positioning，需要把贡献与相关工作逐项对齐并写出差异点证据。 **Skip if**: 缺少 claims（先跑 `claims-extractor`）或你不打算做新颖性定位分析。 **Network**: none (retrieval of additional related work is out-of-scope unless provided). **Guardrail**: 明确 overlap 与 delta；尽量给出可追溯证据来源（来自稿件/引用/作者陈述）。
Polish a single H3 unit file under `sections/` into survey-grade prose (de-template + contrast/eval/limitation), without changing citation keys. **Trigger**: subsection polisher, per-subsection polish, polish section file, 小节润色, 去模板, 结构化段落. **Use when**: `sections/S*.md` exists but reads rigid/template-y; you want to fix quality locally before `section-merger`. **Skip if**: subsection files are missing, evidence packs are incomplete, or `Approve C2` is not recorded. **Network**: none. **Guardrail**: do not invent facts/citations; do not add/remove citation keys; keep citations within the same H3; keep citations subsection-scoped.
Download PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`. **Trigger**: PDF download, fulltext, extract text, papers/pdfs, 全文抽取, 下载PDF. **Use when**: `queries.md` 设置 `evidence_mode: fulltext`（或你明确需要全文证据）并希望为 paper notes/claims 提供更强 evidence。 **Skip if**: `evidence_mode: abstract`（默认）；或你不希望进行下载/抽取（成本/权限/时间）。 **Network**: fulltext 下载通常需要网络（除非你手工提供 PDF 缓存在 `papers/pdfs/`）。 **Guardrail**: 缓存下载到 `papers/pdfs/`；默认不覆盖已有抽取文本（除非显式要求重抽）。
Write structured notes for each paper in the core set into `papers/paper_notes.jsonl` (summary/method/results/limitations). **Trigger**: paper notes, structured notes, reading notes, 论文笔记, paper_notes.jsonl. **Use when**: survey 的 evidence 阶段（C3），已有 `papers/core_set.csv`（以及可选 fulltext），需要为后续 claims/citations/writing 准备可引用证据。 **Skip if**: 还没有 core set（先跑 `dedupe-rank`），或你只做极轻量 snapshot 不需要细粒度证据。 **Network**: none. **Guardrail**: 具体可核对（method/metrics/limitations），避免大量重复模板；保持结构化字段而非长 prose。
Convert a taxonomy (`outline/taxonomy.yml`) into a bullet-only outline (`outline/outline.yml`) with sections/subsections. **Trigger**: outline builder, bullet outline, outline.yml, 大纲生成, bullets-only. **Use when**: structure 阶段（NO PROSE），已有 taxonomy，需要生成可映射/可写作的章节与小节骨架（每小节≥3 bullets）。 **Skip if**: 已经有批准过且可映射的 outline（避免无意义 churn）。 **Network**: none. **Guardrail**: bullets-only；移除 TODO/模板语句；每小节至少 3 个可检查 bullets。
De-slot and harmonize paper voice across `sections/*.md` without changing meaning or citation keys. **Trigger**: style harmonizer, de-template stems, remove slot phrases, discourse stems, 写作风格统一, 去槽位句式, 去生成器味. **Use when**: `writer-selfloop` is PASS but `output/WRITER_SELFLOOP_TODO.md` flags Style Smells (e.g., repeated count-based openers), or the draft reads like many sections share the same rhythm. **Skip if**: you need new evidence/citations (route to C3/C4), or you are pre-C2 (NO PROSE). **Network**: none. **Guardrail**: do not invent facts; do not add/remove/move citation keys; do not move citations across subsections; keep claim->evidence anchoring intact.
Write one survey-quality paragraph from evidence packs (tension → contrast → evaluation anchor → limitation). **Trigger**: grad paragraph, paragraph micro-structure, argument paragraph, 研究生段落, 论证段落, 对比段, 段落写作. **Use when**: you are drafting `sections/S*.md` (H3 body) and want subsection-specific, evidence-bounded prose instead of templates. **Skip if**: evidence packs are missing/incomplete (fix `subsection-briefs`/`evidence-draft`/`evidence-binder` first), or `Approve C2` is not recorded in `DECISIONS.md`. **Network**: none. **Guardrail**: do not invent facts or citations; no placeholders/ellipsis; keep claims conservative when evidence is abstract-level (avoid repeating evidence-mode boilerplate in every paragraph).
Plan tutorial modules from a concept graph, including module objectives and sequencing, saving as `outline/module_plan.yml`. **Trigger**: module plan, tutorial modules, course outline, 模块规划, module_plan.yml. **Use when**: tutorial pipeline 的结构阶段（C2），已有 `outline/concept_graph.yml`，需要把概念依赖转成可教学的模块序列。 **Skip if**: 还没有 concept graph（先跑 `concept-graph`）。 **Network**: none. **Guardrail**: 每模块明确 objectives + outputs（最好含 running example 步骤）；避免 prose 段落。
Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring. **Trigger**: polish draft, de-template, coherence pass, remove boilerplate, 润色, 去套话, 去重复, 统一术语. **Use when**: a first-pass draft exists but reads like scaffolding (repetition/ellipsis/template phrases) or needs a coherence pass before global review/LaTeX. **Skip if**: the draft already reads human-grade and passes quality gates; or prose is not approved in `DECISIONS.md`. **Network**: none. **Guardrail**: do not add/remove/invent citation keys; do not move citations across subsections; do not change claims beyond what existing citations support.