DevOps & Infra

arvo-ai Skill

Bitbucket code repository integration for managing repos, branches, PRs, issues, and CI/CD pipelines

arvo-ai Skill

CloudBees CI integration for investigating builds, deployments, pipeline stages, and test results during RCA

arvo-ai Skill

Spinnaker CD platform integration for investigating pipeline executions, application health, and triggering rollbacks during RCA

getlago Skill

Phase 2 of the loop pipeline for lago-front. Takes an ISSUE-ID, reads spec.md from the run state dir, declares the minimal diff in plan.md, implements it in a dedicated worktree — or in the current checkout with `--in-place` (automatic inside a Conductor workspace) — and gets lint + types + translations gates green. Use when user says "/loop-build <ISSUE-ID> [--in-place]" or the loop-run orchestrator invokes the build phase.

getlago Skill

Cleanup phase of the loop pipeline for lago-front, for the `worktree` layout only. Finds local worktrees in front-worktrees/ whose PR is merged and destroys them via lago-worktree destroy, after user confirmation. Use when user says "/loop-clean", asks to clean up merged worktrees, or the loop-run orchestrator runs its sweep step.

getlago Bundle

Phase 3 of the loop pipeline for lago-front. Takes an ISSUE-ID, reviews the worktree diff against spec.md and plan.md with clean context, and writes a PASS/FAIL verdict to review.md in the run state dir. Use when user says "/loop-review <ISSUE-ID>" or the loop-run orchestrator dispatches the review phase in a fresh subagent.

getlago Skill

Post-PR revision phase of the loop pipeline for lago-front. Takes an ISSUE-ID (or nothing, when run inside the checkout that owns the PR) and feedback, applies ONLY the requested changes in the worktree recorded in state.md — a lago-worktree worktree or, in the `in-place` layout, the current checkout — re-runs gates, commits, pushes, and watches CI. Use when user says "/loop-revise <ISSUE-ID> <feedback>", or asks to change something in a PR the loop opened.

getlago Skill

Harvest phase of the loop pipeline for lago-front. Reads the proposals loop-run and loop-revise appended to _flywheel.md, admits only the ones that pass the governance rules, prunes checks the journal shows to be dead, refreshes the styleguide mirror, applies the result to the loop-* skills and the .agents docs, and opens a PR. Use when user says "/loop-flywheel", asks to apply flywheel feedback, or asks to turn the flywheel into a PR.

arvo-ai Skill

On-prem Kubernetes cluster integration for running kubectl commands via Aurora agent relay or uploaded kubeconfig

vannifr Bundle

Use when setting up or auditing a project's CI/CD pipeline together with local verification — ensures pnpm/npm verify (or equivalent) actually covers everything CI checks, adds pre-commit/pre-push git hooks that enforce this locally, and keeps trunk-based development honest (small commits, frequent pushes, CI checked per push not per batch). Load before building a new .woodpecker.yml/.github/workflows, before adding SonarQube/coverage, or when "it passed locally but failed in CI" comes up.

vannifr Skill

Scaffolds and runs a minimal, real load/stress test (k6 by default, Artillery as an alternative) against a site's or API's critical endpoints — the "performance budget test" that NFR checklists ask for but that a Lighthouse-only audit never actually exercises, since Lighthouse simulates exactly one user. Works on any HTTP-reachable site or API, static-front or backend. Trigger on "load test this", "how does this hold up under traffic", "stress test the API", "set up performance budget tests", or when an NFR audit flags load-testing as unverified. NOT for browser-rendering performance (Lighthouse/CWV — use nfr-gap-audit's baseline or production-cwv-review). NOT something to run against production without explicit, scoped authorization — generating real load against a live site has real cost and risk (rate limits, real infra bills, false alerts, genuine degradation for real visitors); always confirm target, intensity, and time window with the user first, and prefer a staging environment when one exists.

qtalen Bundle

AWS AI-DLC adaptive software development workflow (Inception / Construction / Operations). Use whenever the user requests any software development work — building features, requirements analysis, user stories, application/functional/NFR/infrastructure design, code generation, build & test planning, or reverse engineering an existing codebase. This workflow OVERRIDES other built-in workflows for software development requests.

erikdarlingdata Skill

Pre-release checklist for PerformanceMonitor — version bumps, changelog, cloud testing, and validation (Lite + Darling; Full Dashboard and CLI Installer are deprecated and out of this process)

arvo-ai Skill

OVHcloud infrastructure integration for managing instances, Kubernetes clusters, networks, and object storage via CLI and Terraform

getlago Skill

Phase 1 of the loop pipeline for lago-front. Takes a Linear ticket URL (required) and optionally Notion spec page URLs, reads all sources, verifies every premise the ticket states against the running code, and writes an operational spec to the run state dir. Use when user says "/loop-spec <linear-url> [notion-urls...]" or asks to spec a ticket for the loop pipeline.

babamba2 Bundle

Create ABAP programs (Report/CRUD/ALV/Batch) with Main+Include structure, OOP or Procedural, and full agent-driven coding/QA pipeline

lyravoid Skill

Configuring a Shirone blog site - site identity, theme colors, navigation, sidebar, pages, comments, Umami analytics, music, anime sources, fonts, llms.txt, npm package initialization, and build/deploy. Use when enabling or tuning features, changing site behavior, preparing deployment, or configuring a project that consumes shirones.

repoprompt Bundle

Safely process an explicitly ordered batch of RepoPrompt CE pull requests end to end: preserve a dirty original checkout, isolate each PR in an external disposable worktree, use window- and context-scoped CE rpce-cli Agent Mode review, repair and validate, require exact-head hosted checks, merge with merge commits, and clean up. Optionally verify or install a final cloud artifact only when separately requested. Use when an authorized maintainer asks to integrate and merge one or more ordered RepoPrompt CE PRs. Do not use for review-only triage, release-only work, or deployment-only work.

lyravoid Bundle

Operate Shirone content separation and dual-repository workflows after configuration is established. Use for content:sync, content:watch, content:status, content:export, content:clean, content:eject, safe backups, reverse-export diffing, and dual-repository CI/CD operations. Use shirone-content-config to configure CONTENT_DIR, CONTENT_REPO_URL, shirone.content.json, mounts, or config/*.yaml overlays.

dev-core-busy Bundle

Gibt eine eng umrissene Codeaufgabe an den {marke}-Agenten ab und holt sie als geprueften Patch zurueck – spart Anthropic-Tokens bei mechanischer Breitenarbeit. Nutzen, wenn eine Aenderung VIEL Datei-Lesen und WENIG Beschreibung braucht und eine vorhandene Testdatei das Ergebnis beweist.

synit-io Bundle

Create, edit, migrate, repair, review, and validate Docker Agent configuration files written in YAML. Use for agent.yaml files, single-agent or multi-agent teams, models and providers, built-in toolsets, MCP definitions, RAG, commands, Docker Agent skills, permissions, hooks, structured output, budgets, flavors, runtime settings, or Docker Agent schema and startup errors. Do not use for Docker Compose or Dockerfiles unless the task also requires a Docker Agent configuration.

64x-lunicorn Bundle

Configures a project's CI gate from the checks in .claude/64x-lunicorn.yml on GitHub, GitLab or Forgejo, generating the pipeline with Secret scan, Workflow lint where the forge supports it and the single required CI gate, the branch protection, merge settings and repo metadata, or local git hooks without a forge, and reports drift. Use when a project's gate is set up for the first time, re-run after its checks changed, or brought back in line after it drifted.

oyadotai Skill

Drive real Chrome browsers through Oya Browser. Start a browser on Oya Cloud, Browserbase, Steel, Anchor or Browser Use under a persistent persona, read pages as markdown with numbered elements, click and type, solve CAPTCHAs and MFA, and hand off to a human when needed. Use when the user asks to browse a site, automate a web task, fill a form, log in somewhere, scrape, or run several browsers at once. Works through the Oya MCP tools (start_browser, analyze_page, click, type…), the `oya` CLI, or the @oya-ai/browser SDK.

huaweicloud Bundle

Invoke this skill to search, discover, browse, find and install any Huawei Cloud (华为云) agent skill.Triggers include: "华为云","华为云有什么skill","华为云相关skill","华为云agent skill 市场","华为云skill类目","explore Huawei Cloud skills","show Huawei Cloud skill categories","does a Huawei Cloud skill exist for...","which Huawei Cloud skills exist","搜索华为云技能","有没有管理ECS/OBS/RDS的skill","帮我找 XX 华为云skill","介绍 XX Skill 内容","华为云 XX Skill 具体做什么","安装华为云Skill".

huaweicloud Skill

Use when creating, connecting, or managing Huawei Cloud Sandbox instances and workspace terminals, or when a task needs a temporary runtime to deploy, run, or preview a web application. Covers sandbox lifecycle (check-user, sign-agreement, connect, release), session-based terminal execution, and credential injection. Triggers on: sandbox, workspace, terminal, web app deployment, deploy web app, preview app, deploy github, github repo, deploy repo, website, static site, web application, hwlink, devstation, hdkitservice, remote exec. NOT for: ECS instances (use huawei-ecs), CCE clusters (use huawei-cce).

huaweicloud Skill

Use when creating or managing Cloud Backup and Recovery (CBR) vaults, backups, and restore operations on Huawei Cloud. Triggers: CBR, backup, restore, vault, snapshot, disaster recovery. NOT for: OBS object versioning (use huawei-obs), RDS automated backups (use huawei-rds).

huaweicloud Skill

Use when creating or managing CCE Kubernetes clusters. Covers cluster creation, node pools, SWR registry, autoscaling. Triggers: CCE, Kubernetes, K8s, cluster, node pool, container, SWR. NOT for: serverless functions (use huawei-functiongraph), serverless containers (use huawei-cce for CCI redirect).

huaweicloud Skill

Use when managing Cloud Trace Service (CTS) audit logs, trackers, and traces on Huawei Cloud. Triggers: CTS, Cloud Trace, audit log, tracker, trace, operation record. NOT for: CES monitoring alarms (use huawei-cloud-eye), log analysis (use LTS).

huaweicloud Bundle

Use when managing secrets, credentials, encryption keys, certificates, or any sensitive data on Huawei Cloud. Covers CSMS (Cloud Secret Management Service) for secrets, KMS for encryption keys, and credential rotation. Triggers on: secret, credential, API key, token, password, encrypt, decrypt, KMS, CSMS, DEW, certificate, CSR, rotation. Activates for ANY task involving secrets or credentials — load this skill first before touching secrets.

huaweicloud Bundle

Huawei Cloud ECS

huaweicloud Bundle

Use whenever the user wants to DEPLOY, host, or purchase anything on Huawei Cloud that creates billable resources: application deployments (部署应用到华为云, deploy my app, 上线, 搭建), architecture proposals, cost estimation, multi-resource provisioning (VPC, subnet, security group, ECS, EIP, RDS, OBS, CDN, DNS, FunctionGraph, CCE, GaussDB and more), session-scoped state tracking, and reverse-order destroy. Trigger words: 部署, 部署到华为云, 上线, 购买, 搭建, 开通, 成本估算, 多少钱, 销毁, deploy, deploy to Huawei Cloud, provision, purchase, architecture, hosting. Reusing an existing VPC does NOT make it single-resource - any purchase (ECS, EIP, disk, keypair, rules) must pass the cost+balance gate here. NOT for: sandbox preview (huawei-sandbox - free, no purchase), read-only or lifecycle operations on EXISTING resources (query/reboot/resize/delete - use the service skill directly).

huaweicloud Bundle

Use when managing IAM users, groups, roles, policies, agencies, projects, or access keys on Huawei Cloud. Covers IAM policy structure, least-privilege design, temporary credentials (STS), OneAccess integration, and security best practices. Triggers on: IAM, permission, policy, role, user, group, AK/SK, access key, agency, project, authorization. NOT for: DEW secret management (use huawei-dew).

huaweicloud Bundle

Use when creating, configuring, or managing OBS buckets and objects on Huawei Cloud. Covers bucket creation, lifecycle policies, versioning, static website hosting, CORS, access control (IAM/bucket policy/ACL), cross-region replication, event notifications, and presigned URLs. Triggers on: OBS, bucket, object storage, lifecycle, versioning, static website, CORS, presigned, replication. NOT for: EVS block storage (use huawei-ecs), SFS file storage, CBR backup (use huawei-cbr).

huaweicloud Skill

Use when creating, configuring, managing, or troubleshooting RDS instances on Huawei Cloud. Covers MySQL, PostgreSQL, SQL Server. Triggers: RDS, MySQL, PostgreSQL, database instance, backup, read replica. NOT for: GaussDB (use huawei-gaussdb), DDS (use huawei-dds-dcs).

huaweicloud Bundle

Use when creating, configuring, or managing VPC networks, subnets, security groups, EIPs, NAT gateways, VPN connections, or network ACLs on Huawei Cloud. Triggers on: VPC, subnet, security group, EIP, NAT, VPN, network ACL, route table, bandwidth. NOT for: DNS or CDN configuration.

huaweicloud Skill

OpenCode entry skill for HuaweiCloud DevKit. Use when a developer asks OpenCode to use Huawei Cloud Skills, KooCLI, APIs, SDKs, future MCP tools, or low-priority Terraform guidance.