DevOps & Infra

lingwei-zheng Bundle

Academic research, literature review, research design, paper drafting, manuscript revision, research-to-paper workflow routing, and experiment planning for geography, human geography, GIScience, and health geography. Use when the user asks for literature review, systematic review, paper outlining, geography-specific title design, abstract writing, revision, citation or integrity checks, full pipeline support, or experiment/study planning. Use good-question when research-question quality is the primary task, peer-review for a formal referee report, good-story for an evidence-led manuscript story, and academic-advisor for submission strategy.

codyswanngt Skill

Ingest source material into the LLM Wiki. With an argument (URL, file path, or prompt) ingest that one source; with no argument run a full ingest across every enabled non-external-write source. Routes to the right connector and runs the ordered pipeline (source note → synthesis → index → log → verify → state → commit/PR).

chakhdz Skill

Optional add-on to identify papers with local GROBID. If it would install Docker or write files, first a simple plan, then wait for yes. Not part of the organize flow.

notharshhaa Bundle

Identify cloud cost optimization opportunities as a senior FinOps/cloud engineer across compute, storage, networking, and managed services, then produce a prioritized, evidence-based findings table and self-contained remediation plans that cut waste without hurting reliability. Strictly read-only — never resizes, deletes, or modifies resources. Use when asked to reduce cloud spend, find waste, right-size infrastructure, or review cost efficiency of IaC or a live account.

notharshhaa Bundle

Investigate a production incident as a senior SRE and produce a hypothesis-driven, evidence-logged investigation document plus recommended (never auto-applied) mitigations and durable follow-up plans. Strictly read-only — runs diagnostic and read-only commands only, never restarts, scales, rolls back, or changes anything itself. Use when asked to investigate an outage, degradation, error spike, latency regression, failed deploy, or any "why is production broken" question, or to run a blameless post-incident analysis.

notharshhaa Bundle

Review Kubernetes manifests, Helm charts, Kustomize overlays, and live workloads as a senior Kubernetes engineer, then produce a prioritized, evidence-based findings table and self-contained remediation plans. Strictly read-only — never applies, scales, deletes, or patches anything. Use when asked to review Kubernetes YAML, Helm charts, or cluster workloads for reliability, security, resource management, or best-practice compliance.

notharshhaa Bundle

Review Dockerfiles, container images, and Compose files as a senior container engineer, then produce a prioritized, evidence-based findings table and self-contained remediation plans covering image size, build speed, security, and correctness. Strictly read-only — inspects and scans only, never builds-and-pushes or edits. Use when asked to review Dockerfiles, container build setups, image layering, or container security and best practices.

notharshhaa Bundle

Review GitOps delivery pipelines, reconciliation status, and repository-to-cluster sync safety as a senior GitOps / platform engineer across ArgoCD, Flux, and Kubernetes controllers, then produce an evidence-based findings table and self-contained remediation plans. Strictly read-only — inspects apps, diffs, and health only, never triggers syncs, overrides drift, or mutates resources. Use when asked to review ArgoCD or Flux setups, diagnose OutOfSync apps, audit automated sync/prune policies, inspect sync-wave ordering, or fix secret operator reconciliation loops.

notharshhaa Bundle

Audit infrastructure for deprecated APIs, breaking changes, and End-of-Life (EOL) runtimes as a senior platform engineer before upgrading Kubernetes clusters, Terraform providers, or language runtimes, then produce an evidence-based upgrade readiness report and sequenced, zero-downtime remediation plans. Strictly read-only — scans and plans only, never initiates an upgrade or modifies state. Use when asked to plan a Kubernetes cluster upgrade, check for deprecated Kubernetes APIs or Helm charts, review Terraform provider major-version migrations, assess upgrade risks, or plan runtime EOL migrations.

notharshhaa Bundle

Review CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins, CircleCI, Azure Pipelines, etc.) as a senior release engineer, then produce a prioritized, evidence-based findings table and self-contained remediation plans covering reliability, speed, security, and correctness. Strictly read-only — never triggers, cancels, or edits pipelines. Use when asked to review CI/CD configuration for flakiness, slow builds, insecure secrets handling, missing gates, or supply-chain risk.

notharshhaa Bundle

Identify security risks and infrastructure misconfigurations as a senior security/DevSecOps engineer across IaC, Kubernetes, containers, pipelines, cloud config, and secrets handling, then produce a prioritized, evidence-based findings table and self-contained remediation plans. Strictly read-only and defensive — never exploits, never applies changes, never reproduces secret values. Use when asked to review infrastructure security posture, find misconfigurations, assess IAM/network/secrets exposure, or harden a deployment.

notharshhaa Bundle

Review Terraform (or OpenTofu) code and infrastructure design as a senior cloud/IaC engineer, then produce a prioritized, evidence-based findings table and self-contained remediation plans. Strictly read-only — runs plan/validate only, never apply, destroy, or state changes. Use when asked to review Terraform modules, root configurations, state management, or IaC design for correctness, security, cost, and maintainability.

notharshhaa Bundle

Validate production deployment readiness as a senior release manager/SRE by checking whether a service or release meets reliability, security, observability, rollback, and operational bars before it ships, then produce a go/no-go assessment with an evidence-based gap list and self-contained remediation plans for blockers. Strictly read-only — never deploys, promotes, or changes anything. Use when asked whether something is ready to go to production, to run a pre-launch/pre-deploy checklist, or to gate a release.

rtfm-it-services-llc Skill

Use this skill whenever a new client signs or client onboarding comes up in any form: a deal hits Closed Won, someone says "we signed", "kickoff", "welcome email", "get them set up", "take over from their old IT guy", or names a new client that needs setting up. Also trigger for planning or quoting onboarding work, building a credential collection list, deploying agents to a new environment, or the 30-day review. This is the handoff target for msp-sales pipeline stage 7 (Closed Won). Apply alongside msp-legal (paper gates before work starts), msp-pricing (onboarding is always billed separately), msp-brand (every client-facing message), and hand off to msp-helpdesk and msp-qbr at the end.

surgepix Bundle

Upload local files to SurgePix cloud storage and return a public HTTPS URL. Use when the user says "upload", "get a URL", "上传文件", "传到CDN", needs a remote-accessible URL for an API call, or wants to convert a local file path into a public link.

ice-lfernandes Bundle

Orchestrates the feature pipeline — one use case per run, 5 design skills → spec.md for the executor

ice-lfernandes Bundle

Designs the tests for an already-modeled use case — what test exists at what level, what data, what error cases — into the `40-testes.md` partial, and installs the architecture tests in a project that doesn't yet have them. Use when the request involves writing or designing tests, coverage, ArchUnit, boundary tests, integration tests, or "this is missing tests". Piece of the `/new-feature` pipeline: in design mode requires `10-dominio.md` in the given folder and stops without it.

ice-lfernandes Bundle

Details the domain and application layer of an already-designed use case — aggregate, value objects, invariants, ports, and events — into the `10-dominio.md` partial. Use when the request involves modeling the domain, defining an aggregate or value object, designing a use case's ports, or detailing a spec already created by `use-case-design`. Piece of the `/new-feature` pipeline: requires `00-caso-de-uso.md` in the given folder and stops without it.

ice-lfernandes Bundle

Delimits a use case's boundary and emits the parent spec that the layer skills detail — trigger, payload, response, side effects, invariants, errors, and canonical names. Use when the request involves "new use case", "design before implementing", "implementation spec", a new endpoint/event/job, or when a request bundles several actions and it's necessary to know whether it's one use case or several. First piece of the `/new-feature` pipeline.

ice-lfernandes Bundle

Extends a project's docker-compose.yml and Dockerfile after project-bootstrap's base generation — adds the database or messaging service a modeled use case needs, keeps the compose-side image tag consistent with the one test-architect pins in TestcontainersConfiguration.java, and syncs with 20-persistencia.md / 40-testes.md. Use when the request involves adding a service to docker-compose, containerizing a new dependency, configuring Testcontainers at the compose level, or "docker-compose is missing the database" — also fires when persistence-architect or test-architect detect a service their spec needs isn't in docker-compose.yml yet.

ice-lfernandes Bundle

Designs the inbound REST adapter for an already-modeled use case — endpoints, DTOs, status codes, error map, pagination, idempotency, and OpenAPI — into the `30-rest.md` partial. Use when the request involves exposing a use case via HTTP, designing an endpoint or controller, deciding status and error body, paginating a collection, applying `Idempotency-Key`, or fixing the OpenAPI contract. Piece of the `/new-feature` pipeline: requires `10-dominio.md` in the given folder and stops without it.

ice-lfernandes Bundle

Designs the Kafka producer/consumer adapter for an already-modeled domain event — topic, partition key, serialization, consumer group, delivery semantics, retries and DLQ — into the `25-mensageria.md` partial. Use when the request involves publishing a domain event to Kafka, consuming a Kafka topic, designing a producer or consumer adapter, deciding topic/partition/serialization, or wiring retry/DLQ for a message listener. Piece of the `/new-feature` pipeline: requires `10-dominio.md` in the given folder with an Events block that names external delivery, and stops without it.

ice-lfernandes Bundle

Designs the persistence layer of an already-modeled use case — tables, aggregate mapping, migrations, queries, indexes, and datasource configuration — into the `20-persistencia.md` partial. Use when the request involves modeling the database, mapping an aggregate to JPA, writing or reviewing migrations, deciding indexes and keys, diagnosing N+1 or slow queries, or tuning the pool and datasource properties. Piece of the `/new-feature` pipeline: requires `10-dominio.md` in the given folder and stops without it.

mmiani Bundle

Use when implementing or extending a feature in a Kotlin Multiplatform project. Provides pre-coding inspection, KMP source-set discipline, state pipeline design, architectural defaults, security/performance guardrails, and implementation rules. Forward-looking only — not a review skill.

nxs-cafi Skill

CI/CD e Infraestrutura: GitHub Actions, Docker multi-stage, Docker Compose, Kubernetes, Trivy, deploy strategies. Use para criar pipelines, dockerizar apps Java/Python, configurar K8s, ou revisar infraestrutura de deploy.

texarkanine Bundle

Deploy application with checklist and configuration

open-mercato Skill

Open Mercato repo-local extension of the shared `om-code-review` skill (installed from open-mercato/skills into .agents/skills/). Adds the Docker-vs-local gate runner detection, the template parity gate, Open Mercato layer classification, and the repo's severity taxonomy on top of the shared workflow.

pyfagorass Bundle

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

multiatlas Skill

Convierte una misión técnica arriesgada (deploy, migración, envío masivo, operación destructiva) en un battle-plan ejecutable a ciegas — acción, observación esperada, fallo probable, contramaniobra, triggers de bifurcación y condiciones de aborto. Genera el plan con el mejor modelo disponible (redactor), lo somete a red-team adversarial y lo repara, para que después lo ejecute un modelo más barato con ese criterio ya embotellado. Invocar antes de cualquier misión donde el "camino feliz" no basta y un fallo silencioso cuesta caro.

relationalai Bundle

Take a built RelationalAI model to production — deploy it into a Snowflake schema and version it through the op log (branch, collaborate, merge, and tear down with the `rai models` CLI), or deploy it as a Snowflake CoWork (Cortex) agent. The one path-to-prod skill across deployment targets. Use when deploying a model, managing its deployed lifecycle, or operationalizing it as a Cortex agent — not for first-time install/connect (see rai-setup), building the model (see rai-ontology, rai-pyrel), or interpreting reasoner output.

traderalice Skill

Scan an investment theme by decomposing its value chain, then surface the handful of names actually worth researching — each with why and the next question. Use when the user has a theme/sector/thread but no specific ticker yet: "what's worth looking at in semis", "scan the AI-infra space", "I'm curious about uranium / obesity drugs / power grid", "who are the picks-and-shovels in X", "map the supply chain for Y", "find the names worth watching in the X value chain". This is the have-a-theme / no-target step — it turns "I don't know what to look at" into a short, reasoned shortlist.

amatray Bundle

Systematically set up, solve, and verify an economic model with step-by-step derivations and cross-model mathematical checking. Use when user wants to formalize an economic idea into a model, solve a model, derive equilibrium conditions, check derivations, or verify mathematical results. Also use when user says "solve", "derive", "set up the model", "formalize", "verify the math", "check derivation", "model setup". Not for the solving_models pipeline repository (the one with AGENTS.md), where a model starts as a sketch interview under prompts/sketch_interview.md; do not use there.

fhgomes Bundle

Offensive-defensive security specialist focused on HUNTING MALICIOUS CONTENT — malware, viruses, trojans, backdoors, webshells, ransomware, cryptominers, stealers, keyloggers, droppers, supply-chain attacks and obfuscated code — inside files, folders, repositories (PoC/proof-of-concept), URLs, websites, executables, installers, scripts, dependencies (npm/pip/maven), Docker images, e-mail attachments and USB drives. ALWAYS use when the user asks: "analyze this file", "is this .exe safe?", "scan this folder", "does this repo/PoC have a virus?", "is this link malicious?", "is this site phishing?", "check this installer", "I downloaded this, is it safe to run?", "is my PC infected?", "what is this weird process?", "analyze this script", "is this npm/pip package trustworthy?", "does this .docx/.pdf have a macro?", "check this hash", "quarantine this", "triage this binary", "static analysis", "sandbox", "reverse engineering", "this code is obfuscated", "IoC", "VirusTotal", "YARA". Also trigger when the user mention

librefang Bundle

Expert knowledge for AI DevOps automation -- CI/CD patterns, infrastructure monitoring, deployment strategies, and incident response playbooks

juicesharp Skill

Answer structured research questions via targeted parallel analysis agents. Consumes question artifacts from discover. Produces research documents in thoughts/shared/research/. Second stage of the research pipeline — always requires a questions artifact.

therapys Skill

Take the current changes from a dirty tree to an open pull request — branch, commit, push, and open the PR. Use when the user says any of: 'create a pr to main/dev', 'open a pr', 'push to main', 'commit and push', 'push this to git', 'ship it', 'push to the linear branch and open a draft PR', or asks to do the same across multiple repos ('push to each repo except infra').