DevOps & Infra

ghosteken Skill

Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration.

ghosteken Skill

Expert Terraform/OpenTofu specialist mastering advanced IaC automation, state management, and enterprise infrastructure patterns.

ghosteken Skill

Kubernetes deployment workflow for container orchestration, Helm charts, service mesh, and production-ready K8s configurations.

ghosteken Skill

Runs code review as a bounded finder-and-verify pipeline — parallel finder angles surface candidate issues across correctness, security, performance, architecture, and cleanup, then each candidate is independently verified before it's reported. Use before merging any change, after completing a feature or bug fix, or when evaluating code written by another agent or a human.

ghosteken Skill

Design, debug, and harden GitHub Actions CI/CD workflows, including reusable workflows, matrix builds, self-hosted runners, OIDC authentication, caching, environments, secrets, and release automation.

ghosteken Skill

Configure secure, high-performance connectivity between on-premises and cloud environments using VPN, Direct Connect, and ExpressRoute.

ghosteken Skill

Decision framework and patterns for architecting applications across AWS, Azure, and GCP.

ghosteken Skill

Terraform infrastructure as code workflow for provisioning cloud resources, creating reusable modules, and managing infrastructure at scale.

ghosteken Bundle

Harden Docker/container images and runtime deployments with secure base images, non-root users, CVE scanning, SBOM/signing, seccomp/AppArmor, and Kubernetes pod security controls. Use for Dockerfile security reviews, container CVEs, image scanning, distroless images, or production hardening.

unboundcompute Skill

Audit continuous-integration pipelines for the trust they extend to untrusted input: workflows that run on incoming change requests from forks while holding repository secrets, steps that let attacker-controlled content reach a privileged command, and cloud role trust conditions that accept a pipeline's short-lived token too broadly. Covers secret and token exposure on fork-triggered runs, poisoned-pipeline execution, and over-broad trust on the identity claim a pipeline presents to a cloud account. Use when reviewing CI/CD configuration, pipeline identity, or the boundary between a build and the cloud it can reach. An exploitable token or command from untrusted input is the finding.

unboundcompute Skill

Hunt for the ways an attacker gets code into your build without touching your repo: dependency confusion (a public package shadowing an internal name), typosquatting and slopsquatting (a package named after a model's hallucination), poisoned pipeline execution (untrusted input running as a build step), and over-privileged or injectable CI. Use when reviewing a build pipeline, a dependency manifest, an internal package registry, or a CI/CD configuration. The app code can be clean while the artifact you ship is not.

unboundcompute Skill

Audit the machine-learning models you load as untrusted code, not just data. Covers deserialization RCE from unsafe checkpoint formats (a model file that runs code on load), poisoned or backdoored weights, tampered or trojaned models pulled from a public hub, name and version confusion for model artifacts, and skipped integrity verification. Use when adding a model, checkpoint, or weights file to a pipeline, reviewing where models are loaded, or vetting a third-party model. A model file is executable input until you prove otherwise.

unboundcompute Skill

Hunt a CI/CD pipeline for attacker-controlled repository data that reaches a privileged execution context, after the trigger and the token scope are resolved. Covers an untrusted event field (an issue or pull-request title, a branch name, a commit message) interpolated directly into a run-step shell command, a pull_request_target or workflow_run job that checks out and builds the pull-request head with secrets in scope, a third-party action pinned to a mutable tag or branch rather than a commit digest, a cache a low-trust job writes and a privileged job restores and executes, a self-hosted runner reachable from fork pull requests, and an over-scoped pipeline token widening the blast radius. Use when reviewing workflow definitions, their triggers, and their token permissions, not the OIDC trust boundary the CI OIDC skill owns. Attacker-controlled repository data is the source, a privileged pipeline run step or checkout is the sink, and untrusted input reaching execution is the bug.

unboundcompute Skill

Test a system of multiple cooperating AI agents for attacks that exist only because agents message, spawn, and delegate to each other. Covers agent-to-agent injection (agent-in-the-middle), delegation abuse and recursive loops, orchestrator injection, confused-deputy across a trust boundary, identity spoofing between agents, capability collusion, and denial-of-wallet. Use when reviewing an orchestrator, a crew or swarm, agent-to-agent messaging, or any pipeline where one agent's output becomes another agent's input. Every internal edge where output becomes instruction is an injection channel.

unboundcompute Skill

Hunt for the configuration that lets a workload break out of its container onto the node: a pod that runs privileged or adds dangerous capabilities, a host namespace shared into the container (host PID, network, or IPC), a writable host path or device mounted in, and a security context that disables the defenses that would otherwise keep a process inside its container. Covers Kubernetes pods and standalone containers where a compromised or hostile process inside the container tries to reach the node, the kubelet, or other pods. Use when workloads run with elevated security contexts, host mounts, or shared host namespaces. The container process is the source, the node or host resource it reaches is the sink, and the escape the security context permits is the bug.

unboundcompute Skill

Test whether an attacker can plant content in the knowledge an AI agent later retrieves and trusts: a RAG index or vector store, an agent's persistent memory, or the search and web results it pulls at runtime. Covers poisoned documents that surface as authoritative context, memory entries that persist across sessions, retrieval-ranking abuse, and injected instructions that ride retrieved chunks. Use when reviewing a RAG pipeline, an agent with long-term memory, or any retrieval step feeding the model. The poison fires on an innocent query.

unboundcompute Skill

Adjudicate whether a server-side request-forgery primitive actually reaches high-value internal targets, especially a cloud instance metadata endpoint that hands out credentials. Covers proving the fetch is attacker-steered, reaching link-local and internal addresses, defeating allowlist and parser-based filters through DNS rebinding and URL confusion, retrieving instance credentials, and blind out-of-band confirmation. Use when a feature fetches a URL, host, or address the user can influence, or when triaging an SSRF lead for real impact.

unboundcompute Skill

Audit authorization expressed as configuration or framework convention rather than inline code: row-level security and policy rules, framework before-action and middleware filters that must be attached to every protected route, serverless and gateway access rules, and object-ownership checks. Covers routes that skip the filter, policies with a permissive default, rules that check authentication but not ownership, and gaps between where the rule is declared and where the data is accessed. Use when reviewing role- or policy-driven access control. Coverage and correctness are separate checks.

sam6dvpte34 Skill

Collect profile details from LinkedIn Recruiter search — name, title, experience, skills, contact signals. Use when the user wants to build a candidate pipeline from LinkedIn Recruiter.

lamm-mit Bundle

Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.

lamm-mit Skill

Ginkgo Cloud Lab SKILL Summary

lamm-mit Skill

Research Pipeline Skill Overview

inbharatai Skill

Create GitLab CI/CD pipelines — stages, jobs, caching, artifacts, environments, and Auto DevOps customization.

inbharatai Skill

Build end-to-end ML pipelines — data prep, feature engineering, model training, evaluation, and MLflow tracking.

inbharatai Skill

Build end-to-end ETL pipelines — extract from APIs/databases, transform, validate, and load into data warehouses.

inbharatai Skill

Design AWS architectures — VPCs, EC2, ECS, Lambda, RDS, S3, CloudFront, and Well-Architected Framework reviews.

inbharatai Skill

Create CI/CD pipelines — GitHub Actions, GitLab CI, Jenkins, and CircleCI with test, build, and deploy stages.

inbharatai Skill

Design Google Cloud architectures — GKE, Cloud Run, BigQuery, Pub/Sub, and Cloud Spanner solutions.

vibesec-advisory Bundle

Use when an agent proposes a write, send, deploy, publish, payment, CRM update, permission change, or other side effect.

vibesec-advisory Bundle

Use when an agent is about to write files, email, message, publish, deploy, submit, update CRM, store memory, call tools, or produce customer-facing work from ambiguous or inferred intent.

daemon-blockint-tech Bundle

Guides DevOps—CI/CD pipelines, GitOps, release management, container delivery, observability, and SRE practices for build/deploy systems. Use when building or fixing pipelines, implementing GitOps, tuning alerts and SLOs, or managing on-call/incidents for delivery infrastructure—not for IDP/golden paths/developer portals (platform-engineer), raw VPC/IaC design (infrastructure-engineer), rollout cutover planning (deployment-strategist), security gates (devsecops), app features (senior-fullstack-developer), multi-team program coordination (technical-program-manager), or incident program design (severity, on-call, postmortems, paging integrations—incident-management-engineer). For Kubernetes cluster bootstrap, Helm releases, add-ons, and cluster-level debugging, use cluster-deployment-engineer. App latency profiling and load testing: performance-engineer. ML safeguard serving: ml-infrastructure-engineer-safeguards. RL training platform jobs: ml-systems-engineer-rl-engineering.

daemon-blockint-tech Bundle

Guides DevSecOps practices that embed security into software delivery—shift-left scanning, CI/CD security gates, supply-chain integrity, cloud/container runtime controls, threat modeling, and vulnerability management with audit evidence. Use when designing or hardening delivery pipelines, adding SAST/SCA/secrets/IaC/container scans, implementing SBOMs or artifact signing, configuring OIDC and least-privilege CI/CD, writing OPA/Kyverno policies, triaging CVEs, mapping controls to SOC 2/ISO 27001/SSDF, securing GitHub Actions or agentic CI workflows, or running pre-release security reviews—not for general cloud provisioning without a security lens (use infrastructure-engineer), LLM prompt guardrails (prompt-engineer), or cluster Helm/add-on operations without security policy focus (cluster-deployment-engineer), or authorized manual web/API pentest (web-pentester), or binary/firmware RE (reverse-engineer).

daemon-blockint-tech Bundle

Guides production AI engineering—LLM apps, RAG, agents, eval harnesses, observability, cost/latency, and safe deployment. Use when building chatbots, copilots, retrieval, agent workflows, model routing, or LLM API integration—not research synthesis (ai-researcher), AI policy (ai-risk-governance), red-team (ai-redteam), prompt-only work (prompt-engineer), non-AI ADRs (senior-system-architecture), token programs (ai-token-improvement-plan-engineer), solution architecture (applied-ai-architect-commercial-enterprise), skills portfolio (ai-skill-manager), or vertical AI engineering management (engineering-manager-vertical-ai-products). Agent prompt authoring and eval harness design: prompt-engineer-agent-prompts-evals. Safeguard inference gateways and moderation infra: ml-infrastructure-engineer-safeguards. Safeguard classifier research: ml-research-engineer-safeguards.

daemon-blockint-tech Bundle

Guides VP-level cloud program leadership—multi-year cloud strategy and migration/modernization portfolio, landing zone and CCoE operating model at org scale, hyperscaler enterprise agreement and commit governance, hybrid/multi-cloud posture, cloud center of excellence and talent, and board/CFO/CTO cloud narratives. Use when setting cloud direction, prioritizing migration waves, governing EA/MACC and cloud spend envelope, designing federated cloud org model, steering CCoE and standards adoption, preparing executive or board cloud updates, or adjudicating product vs platform vs security cloud trade-offs—not for Terraform/K8s implementation (cloud-engineer, infrastructure-engineer), landing zone technical design (enterprise-cloud-architect, cloud-architect), monthly CUR FinOps (finops-analyst), TCO/NPV modeling (cloud-economist), full infra portfolio including DC capex (vp-of-infrastructure), or GL close (compute-accounting-manager).

daemon-blockint-tech Bundle

Guides CI/CD for agent skills repositories and skill packages—pipeline design (build, test, validate, package), GitHub Actions for PR checks and release promotion, environment gates, secrets hygiene (no secrets in repo), skill-creator integration (quick_validate.py, package_skill.py), .skill artifact strategy, rollback, and operational runbooks for skill releases. Use when the user mentions CI/CD, CI/CD engineer, pipeline design, GitHub Actions, skill validation CI, package skills, release pipeline, deploy skills, PR checks, continuous integration, or skill release workflow—not application-only CI without skill packaging (devops), pre-flight plan go/no-go (build-validator), IDP or golden paths (platform-engineer), org-wide SLO and error-budget programs without pipeline ownership (site-reliability-engineer), or portfolio catalog governance without pipeline YAML (ai-skill-manager).

daemon-blockint-tech Bundle

Guides secure coding and security-focused code review across languages and infrastructure—OWASP-oriented vulnerability patterns (injection, XSS, auth, crypto, deserialization, SSRF, XXE), secrets handling, and IaC security (Terraform, Kubernetes, Docker, GitHub Actions). Use when writing or reviewing code that handles user input, authentication, files, databases, network requests, cryptography, or infrastructure config—or when the user asks to check for SQL injection, XSS, SSRF, hardcoded secrets, OWASP issues, Terraform security, or GitHub Actions security. Not for authorized penetration test engagements (ai-redteam, cybersecurity), compliance program mapping (compliance-engineer), YARA/malware rules (yara-rule-authoring), or CI pipeline setup only (devsecops).