Selecting and implementing AWS services and architectural patterns. Use when designing AWS cloud architectures, choosing compute/storage/database services, implementing serverless or container patterns, or applying AWS Well-Architected Framework principles.

Design and implement Internal Developer Platforms (IDPs) with self-service capabilities, golden paths, and developer experience optimization. Covers platform strategy, IDP architecture (Backstage, Port), infrastructure orchestration (Crossplane), GitOps (Argo CD), and adoption patterns. Use when building developer platforms, improving DevEx, or establishing platform teams.

Operating production Kubernetes clusters effectively with resource management, advanced scheduling, networking, storage, security hardening, and autoscaling. Use when deploying workloads to Kubernetes, configuring cluster resources, implementing security policies, or troubleshooting operational issues.

Displays chronological events and activity through timelines, activity feeds, Gantt charts, and calendar interfaces. Use when showing historical events, project schedules, social feeds, notifications, audit logs, or time-based data. Provides implementation patterns for vertical/horizontal timelines, interactive visualizations, real-time updates, and responsive designs with accessibility (WCAG/ARIA).

Async communication patterns using message brokers and task queues. Use when building event-driven systems, background job processing, or service decoupling. Covers Kafka (event streaming), RabbitMQ (complex routing), NATS (cloud-native), Redis Streams, Celery (Python), BullMQ (TypeScript), Temporal (workflows), and event sourcing patterns.

Debugging workflows for Python (pdb, debugpy), Go (delve), Rust (lldb), and Node.js, including container debugging (kubectl debug, ephemeral containers) and production-safe debugging techniques with distributed tracing and correlation IDs. Use when setting breakpoints, debugging containers/pods, remote debugging, or production debugging.

Data ingestion patterns for loading data from cloud storage, APIs, files, and streaming sources into databases. Use when importing CSV/JSON/Parquet files, pulling from S3/GCS buckets, consuming API feeds, or building ETL pipelines.

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).

When distributing traffic across multiple servers or regions, use this skill to select and configure the appropriate load balancing solution (L4/L7, cloud-managed, self-managed, or Kubernetes ingress) with proper health checks and session management.

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.

Implements search and filter interfaces for both frontend (React/TypeScript) and backend (Python) with debouncing, query management, and database integration. Use when adding search functionality, building filter UIs, implementing faceted search, or optimizing search performance.

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.

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.

Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance. **Trigger**: evidence draft, evidence pack, claim candidates, concrete comparisons, evidence snippets, provenance, 证据草稿, 证据包, 可引用事实. **Use when**: `outline/subsection_briefs.jsonl` exists and you want evidence-first section drafting where every paragraph can be backed by traceable citations/snippets. **Skip if**: `outline/evidence_drafts.jsonl` already exists and is refined (no placeholders; >=8 comparisons per subsection; `blocking_missing` empty). **Network**: none (richer evidence improves with abstracts/fulltext). **Guardrail**: NO PROSE; do not invent facts; only use citation keys that exist 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.

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.

Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`. **Trigger**: evidence binder, evidence plan, section->evidence mapping, 证据绑定, evidence_id. **Use when**: `papers/evidence_bank.jsonl` exists and you want writer/auditor to use section-scoped evidence items (WebWeaver-style memory bank). **Skip if**: you are not doing evidence-first section-by-section writing. **Network**: none. **Guardrail**: NO PROSE; do not invent evidence; only select from the existing evidence bank.

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.

Planner-pass coverage + redundancy report for an outline+mapping, producing `outline/coverage_report.md` and `outline/outline_state.jsonl`. **Trigger**: planner, dynamic outline, outline refinement, coverage report, 大纲迭代, 覆盖率报告. **Use when**: you have `outline/outline.yml` + `outline/mapping.tsv` and want a verifiable, NO-PROSE planner pass before writing. **Skip if**: you don't want any outline/mapping diagnostics (or you have a frozen/approved structure and will not change it). **Network**: none. **Guardrail**: NO PROSE; do not invent papers; only report coverage/reuse and propose structural actions as bullets.

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`.