DevOps & Infra

megabadcoder Skill

Use to babysit a long-running process (training run, batch job, migration, deploy) on a remote pod or locally while the user is away. Defines a launch contract, gates on immediate crash, polls for stability, triages anomalies as recoverable (fix + resume) or not (tear down + notify). Auto-triggers when the user asks you to launch a job and watch it / keep it alive / shut it down if it dies.

rick-orphen Skill

Deliver a change to production yourself instead of handing steps to the requester. Use when: work has to actually land — push/PR, database migration, deploy, production data fix, config change — or when you are about to write 'please run this' / 'paste this SQL' / 'double-click this'. Do NOT use when: you are still investigating a root cause.

abdulyasir100 Skill

Production-grade data engineering expertise. Covers ETL/ELT pipeline design, batch vs streaming architecture, data modeling (dimensional, data vault), quality frameworks (Great Expectations, dbt tests), Spark tuning, Airflow/Prefect orchestration, and Kafka streaming patterns.

chunyun1998-sudo Bundle

小红书长文写作 + 标题矩阵一体化工作流。按步骤执行：选题→搜索素材→立意阐述→用户确认立意→自动搜索素材+写稿→去AI味→敏感词检验→小标题提案→用户确认小标题→大标题提案（三档两语气矩阵）→用户选择→摘要提案→用户确认摘要→摘要插入文档开头。标题环节内置完整标题方法论（三档两语气/五道闸/角度库/落点规格/网感公式/诊断评审复盘收录），自包含 title-matrix 全部能力，无需外部依赖。

abdulyasir100 Bundle

Answer a hard question by fanning it out to a PANEL of models running in parallel — each answering independently with web search and bash, none seeing the others' work — then having Opus 4.8 judge every response into a structured analysis (consensus, contradictions, partial coverage, unique insights, blind spots) and write a final answer grounded in it. The panel is two independent Opus 4.8 runs (slug opus4.8-4.8), Opus 4.8 + GPT-5.5 via codex (opus4.8-gpt5.5), or those plus Gemini 3.1 Pro (opus4.8-gpt5.5-gemini3.1pro). Opus always judges and writes the final answer — the pipeline can't be reversed. Use this whenever the user asks to "run it through Fusion", wants a multi-model / panel / ensemble answer, wants a question cross-checked across models, or wants a higher-confidence answer with consensus and blind spots surfaced — even if they don't say "fusion". Best for high-stakes research, design calls, and debugging where being confidently wrong is expensive.

liuliuliushifu Bundle

Scan, clean, and audit configured temporary-file roots. Use for temporary-file size, stale-file cleanup, cleanup history, disk usage, or scheduled cleanup of build, deploy, and test scratch data.

kewang0622 Bundle

Fluent, well-oriented assistant for magnetic resonance imaging (MRI) research across the whole pipeline — physics, acquisition, reconstruction, analysis, and quantification. Use this WHENEVER a conversation touches MRI, even if the word "MRI" isn't said. Triggers include: MR physics (T1/T2/T2*, relaxation, contrast, spin/gradient echo, bSSFP, EPI), k-space and Fourier imaging, pulse sequence design and pulse programming (Pulseq, PyPulseq, vendor IDEA/EPIC), k-space trajectory design (Cartesian, radial, spiral, EPI, golden-angle), image reconstruction (parallel imaging — SENSE/GRAPPA/ESPIRiT/SPIRiT/NLINV, compressed sensing, low-rank, deep learning, diffusion/score-based, MR fingerprinting), reconstruction toolboxes (BART, SigPy, MIRT.jl, MRIReco.jl, torchkbnufft, DIRECT, Gadgetron), raw and image data formats (ISMRMRD, Siemens twix, GE P-file, Philips raw, DICOM, NIfTI, BIDS), image analysis and processing (FreeSurfer, FSL, SPM, AFNI, ANTs, fMRIPrep, nilearn), functional MRI, diffusion MRI and tractography (M

andersonlimahw Bundle

Firebase expert covering Firebase CLI, Firebase App Distribution, Crashlytics deobfuscation, Hosting deploys, Functions deploys, and the Firebase MCP Server. Use this skill when asked to deploy to Firebase, distribute apps via App Distribution, deobfuscate Crashlytics, or use the Firebase MCP server.

andersonlimahw Skill

Stage 3 of the karpathy-graph pipeline, and the end-to-end entry point. Create a graph, assemble validated writes with provenance, and produce the machine and human artifacts. Use when the user asks to build or create a knowledge graph from a context, to add facts to an existing graph, or when running the whole extract-resolve-assemble-query pipeline in one go.

andersonlimahw Skill

Stage 4 of the karpathy-graph pipeline. Answer multi-hop questions from a knowledge graph by retrieving a bounded subgraph with edge citations, and ground or refute claims against actual graph paths. Use when the user asks a question that spans several facts, asks how two things connect, asks to verify or ground a claim, or when an agent needs task-specific context from an existing graph.

andersonlimahw Skill

Fan the karpathy-graph pipeline out across parallel agents that share the graph as memory instead of copying transcripts. Use when the context is too large for one pass — hundreds of documents, a whole codebase, many independent hypotheses — or when the user asks to parallelize graph construction, run a swarm, or use multiple agents to build a graph.

andersonlimahw Skill

Stage 1 of the karpathy-graph pipeline. Turn unstructured context — documents, source files, incident timelines, chat logs, research notes — into typed entities and subject-predicate-object relations that fit the graph ontology. Use when the user asks to extract entities, pull relations out of documents, map a codebase into a graph, or when building a knowledge graph and no nodes exist yet.

andersonlimahw Skill

Stage 2 of the karpathy-graph pipeline. Collapse duplicate surface forms into canonical entities using context as evidence, reversibly and with a recorded rationale. Use after extraction when the graph contains aliases, abbreviations, or spelling variants of the same thing, when isolated-node count is high, or when the user asks to deduplicate or merge entities.

andersonlimahw Skill

Stage 5 of the karpathy-graph pipeline. Score graph quality across extraction, resolution, structure, query, and operations, and run a ratchet loop that keeps only changes which improve the metric. Use when the user asks how good the graph is, wants to tune extraction prompts or the ontology, asks to measure or improve graph quality, or wants to detect resolution regressions.

andersonlimahw Skill

Data pipeline and analytics engineering patterns. Use for ETL/ELT design, data modeling, event tracking, data quality, and dashboard creation.

andersonlimahw Skill

New repository bootstrap workflow. Use when creating a new project repository from scratch, setting up all the foundational tooling, CI/CD, and team conventions.

andersonlimahw Skill

CI/CD pipeline and infrastructure patterns. Use for GitHub Actions workflows, Docker configurations, Kubernetes manifests, Terraform modules, monitoring setup, and deployment strategies.

veekunth217 Skill

CI/CD pipeline builder — GitHub Actions, self-hosted runners, Docker build/push, multi-environment deployments, secrets, rollback strategies

cmevietnam Bundle

Run a project's whole stack on a local Kubernetes cluster with `klocal`, on Rancher Desktop, kind, k3d or minikube. Use when setting up local development for a project, when the app needs a database and a real hostname to run, when a locally built image will not start in the cluster, when a hostname routes nowhere, or when a local login fails over http.

striderkein Skill

macOS でディスク空き容量を最大化する。Docker prune (volumes 除外で DB データ保持) + 安全キャッシュ削除 + node_modules 一括削除を段階的に実行。「容量足りない」「ストレージ空けて」「ディスク掃除」「空き容量増やして」「disk cleanup」「容量解放」「容量がやばい」等で発動。開発中に積もった不要キャッシュ・ビルドアーティファクトを掃除して GB 単位で空ける時に使う。

veekunth217 Skill

Deploys your app to DigitalOcean or AWS — generates Nginx config, SSL, systemd service, and step-by-step server setup for Ubuntu/CentOS

veekunth217 Skill

Docker best practices — Dockerfile authoring, docker-compose, multi-stage builds, container networking, volume management, Docker in CI/CD

veekunth217 Skill

Node.js API wizard — Express, Fastify, NestJS — with nvm pre-flight, TypeScript, DB, auth, Docker, and CI

veekunth217 Skill

Python project wizard — FastAPI, Django, Flask, Celery, Jupyter — with proper pyenv/venv setup, DB, Docker, and deploy options

vibeinfraid Skill

Systematic 7-step production SRE incident investigation and root cause mitigation for VibeInfra flight simulators (Linux kernel, Docker, Kubernetes, Nginx, PostgreSQL, Kafka).

veekunth217 Skill

Kubernetes management — Helm charts, ArgoCD GitOps, Ingress, ConfigMaps, HPA autoscaling, blue/green deployments, debugging

aungminthu1722 Bundle

Runs a scripted movie dubbing pipeline that turns a video or audio file into a Burmese voice-over — AssemblyAI transcription with speaker diarization into a speaker-tagged SRT, agent-only translation that preserves the original timestamps, then edge-tts voices rendered per speaker (a female voice for female characters, a male voice for male characters), an optional agent-written opening hook, an editor-ready subtitle file, and a music mix long enough to cover the whole film; working files are cleaned up automatically. Use when the user wants a Burmese voice-over or dub from a film, a subtitle file to import into a video editor, subtitles with speaker labels, SRT translation, or a hook or cold-open line over a movie. Only the translation is done by the agent; every other stage is scripted Python.

jia-ben00 Bundle

Safely bootstrap and run any GitHub repository or local project directory: detect the tech stack, run a supply-chain security gate before executing anything, prepare the environment, install dependencies (lockfile-first with China-mirror fallback), start the service, health-check it, and deliver a reproducible run command with troubleshooting notes. Optionally sandbox the run in a hardened Docker container (docker_sandbox.py) and emit a CycloneDX SBOM (sbom.py). Use when the user asks to "run this repo", "clone and run a project", "get this project running", "launch/start this project", "install and run an open-source project", "set up this codebase and start it", "verify this project runs", "make this demo work", or when an unfamiliar codebase must be brought to a running state before modifying, debugging, or evaluating it. 也适用于中文指令："跑一下这个仓库 / 把这个项目跑起来 / clone 并运行 / 本地启动这个开源项目 / 帮我安装运行这个项目 / 验证这个项目能否运行"。

googlesandy Bundle

Use when creating, testing, deploying, or managing Google SecOps detection rules — the detection engineering workflow, retrohunts, rule quotas, detection delays, context-aware analytics (entity graph in rules), risk scoring, error troubleshooting, performance optimization, or composite detections. Complements secops-yara-l (YARA-L query syntax) with the detection engineering workflow. Triggers: "create a detection rule", "deploy rule", "retrohunt", "rule not firing", "detection delay", "entity graph in rule", "risk score rule", "composite detection", "rule error", "tune a rule".

chengrouter Bundle

Import a repository, URL, SKILL.md, or pasted description into a persistent ChengOS Skill package, edit the package in its workspace, and validate it for review.

chengrouter Bundle

Use this skill when the user has questions about building, debugging, or understanding ChengOS workflows — including node selection, port wiring, field configuration, error troubleshooting, and workflow pattern recommendations.

chengrouter Skill

Use this skill when the online UI chat assistant must guide a user through designing a ChengOS workflow and generate an importable workflow JSON file. The assistant uses Workflow API endpoints for templates, node schemas, and LLM model lists.

chengrouter Bundle

在指定时间（早上6点）发送一封单次提醒邮件到 45420@qq.com，提醒收件人开会。

hdl-tools Bundle

Cross-domain loop orchestration for the chip design pipeline. Provides the fix_request protocol, iteration-cap logic, escalation templates, and dispatch patterns for routing verification/formal failures to the RTL orchestrator and back. Use when driving the closed-loop verification↔RTL feedback cycle.

planexeorg Skill

OpenClaw skill for connecting to PlanExe via Model Context Protocol. Supports three deployment scenarios: cloud-hosted service, remote Docker, and local Docker.

planexeorg Skill

Use after the napkin_math pipeline has produced parameters.json (from extract-parameters-from-digest or extract-parameters-from-full) to validate it against the 16 structural checks the rest of the pipeline assumes. Writes validation.json next to parameters.json. Deterministic Python — no LLM call.