DevOps & Infra

paulingram Skill

Use BEFORE verifying any claim — a fix, a feature, a deploy, a diagnosis — to choose HOW to verify it. Enumerates the verification venues (local run, dev environment, replay of captured artifacts, seeded fixture, production read-only checks), states what each uniquely provides, proves whether the claim depends on it, picks the cheapest faithful venue, and records the choice as a verification_plan artifact. Adds the cheaper-faithful-method-found counterpart to the stuck verdicts (cannot-verify-without-deploy / env-failure / blocked) so "I need to wait for prod" is never the reflex when a faithful cheaper method exists, and a gate that needs a live environment obliges the run to PROVIDE one rather than ask.

paulingram Skill

Use when the architect-team pipeline reaches Phase 8 and is about to commit and push — the documentation the project depends on (the maps CODEBASE_MAP / ROUTE_MAP / DESIGN_MAP / INTEGRATION_MAP, plus the project README, CHANGELOG, and CLAUDE.md / AGENTS.md) must be brought current with the shipped change and then independently reviewed before the GitHub push. Also use on demand when documentation is suspected stale. Defines the documentation inventory, what "current" means for each doc, the Phase 8 update-then-audit flow, and the producer/checker split — the orchestrator updates, the system-architect independently audits.

paulingram Skill

The data-plane analog of `visual-to-api-design` — a 7-stage exploration pipeline for data engineering / data architecture asks (dbt projects / Airflow DAGs / Snowflake warehouses / Databricks lakehouses / Kafka streaming / data meshes / feature stores / data products). Stage 1 domain context (via domain-research-team with mandatory outside research on data-stack patterns) → Stage 2 conceptual data model → Stage 3 service design (tool + architecture + phenotype dispatch) → Stage 4 volume + velocity analysis → Stage 5 data security (PII / encryption / access control / regulatory) → Stage 6 MANDATORY validation + lineage + observability (per-transformation rules + aggregate + per-endpoint metrics) → Stage 7 OpenSpec authoring via openspec-propose. Each stage's 3-reviewer convergence wraps in ralph-loop with total-agreement completion-promise. Dispatched from Phase 0c of architect-team-pipeline; never invoked standalone for code generation. v3.5.0.

paulingram Skill

Use when a small-to-medium feature change (≤5 acceptance criteria) needs to be driven end-to-end faster than the full /architect-team can deliver, but with auto-merge to main on green QA. A sibling orchestrator playbook to architect-team-pipeline and bug-fix-pipeline; speed comes from dropping phases and parallel-review fan-out, not a weaker model. The body documents the M0-M8 phases: a single system-architect drafts the 5-artifact OpenSpec bundle with a mandatory ## QA Guidance section, two devs implement in parallel and cross-review each other, and one mini-qa agent runs unit + integration + 1-3 narrow Playwright flows against the live dev URL. On green it auto-merges to main with a Mini-Run: <slug> trailer; on persistent red it hands the work off to the unbounded full /architect-team pipeline as a continuation (no give-up cap). Accepts the same two input forms as /architect-team — a requirements folder OR plain-language prose.

paulingram Skill

Use when debugging a failure whose verification cycle is expensive — a container rebuild, an ECS / Kubernetes / Cloud Run rolling deploy, a slow CI run, a long compile, any feedback loop with a multi-minute turnaround — or when you notice you have already burned two or more deploy / rebuild cycles fixing one bug at a time. Triggers — "I'll fix this one and redeploy to see", whack-a-mole config debugging, a greenfield Docker / Vite / build / CI pipeline that has never run end-to-end, an env var or asset that is not reaching the production bundle, sequential one-fix-per-deploy loops, "the deploy is rolling, waiting to verify". Establishes that when verification is expensive you audit the entire failure pathway and batch every fix before spending a cycle, rather than hunting one root cause at a time.

cyz26 Bundle

Convert text-to-image outputs into game-ready transparent assets by removing plain backgrounds, removing corner watermarks/logos, trimming to subject bounds, and exporting fixed-size PNGs. Use when Codex needs to transform AI-generated artwork into icons, avatars, or sprite-ready assets with strict size and padding requirements (for example 256x256 UI icons).

marvin-lijunzan Bundle

End-to-end AI video creation pipeline for academic & tech tutorials. Integrates voice cloning (CosyVoice2/F5-TTS/Edge-TTS), automated script alignment, screen recording compilation, Whisper subtitle synchronization, and video assembly.

marvin-lijunzan Bundle

Export locally stored AI assistant conversations and prompts from Antigravity, Codex, DeepSeek, WorkBuddy, and Cursor into Markdown with a unified index. Use for manual or scheduled daily backups; do not use for cloud-only histories that are not present on disk.

dragoon0x Skill

Verify the design meets a specific OPTIK score threshold. Returns pass/fail with score breakdown. Use in CI/CD pipelines.

ferroxlabs Skill

Incident response expertise covering incident command frameworks, severity classification, communication templates, role assignments, war room coordination, post-mortems, blameless culture, runbook design, and building organizational incident response muscle. Use when the user asks about incident commander, incident commander best practices, or needs guidance on incident commander implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

jpoindexter Skill

Design production retrieval-augmented generation systems — the full ingest→chunk→embed→index→retrieve→rerank→assemble→generate pipeline, with concrete numbers on chunking, embeddings, hybrid search, reranking, query processing, indexing ops, context assembly, and the failure modes that wreck precision.

johnqtcg Bundle

Senior-SRE log analysis specialist. Use when investigating incidents from logs, triaging error spikes, extracting timelines, correlating distributed traces, or separating signal from noise across plain-text, JSON (slog/zap), syslog, journald, container, and Kubernetes logs. ALWAYS use when the user asks to "analyze logs", "find the error", "what went wrong", "investigate this outage", "correlate request_id/trace_id", "look at the log file", or hands over log dumps / aggregator queries / kubectl logs output. Hands off to incident-postmortem when a blameless post-mortem document is requested.

dauquangthanh Bundle

Drafts CI/CD pipeline design for the project — stages, triggers, quality-gate integration, artefact flow. Produces a provider- neutral pipeline doc + a provider-specific YAML skeleton. Does not provision CI; does not run pipelines. Use when designing a CI/CD pipeline, setting up build automation, or choosing between GitHub Actions, GitLab CI, or similar providers.

dauquangthanh Bundle

Defines quality gates (coverage thresholds, lint / type / security scan pass criteria, performance budgets) that every PR and every release must pass. Produces a gate definition the CI pipeline enforces. Does not enforce them itself. Use when defining quality requirements, setting CI/CD thresholds, or establishing pass/fail criteria for PRs and releases.

dauquangthanh Bundle

Reviews a feature's code + config against OWASP Top 10:2025 and common CWE patterns. Produces a per-feature security review with findings, severity, and remediation outlines. Does not deploy, write exploits, or modify code. Use when reviewing security posture, checking for OWASP vulnerabilities, or performing a pre-release security audit.

dauquangthanh Bundle

Drafts Dockerfile / compose / image-build strategy for the project. Produces a multi-stage Dockerfile starter, a compose file for local dev, and the design doc. Does not build or push images. Use when dockerising an application, planning a container strategy, or when the project needs Docker or Docker Compose configuration.

dauquangthanh Bundle

Drafts the deployment strategy + release runbook — canary / blue-green / rolling, promotion flow, rollback, feature flags, release-notes seed. Produces a runbook the on-call team uses. Does not deploy. Use when planning a deployment strategy, defining a release process, or choosing between canary, blue-green, or rolling deployment patterns.

dauquangthanh Bundle

Drafts infrastructure-as-code plan — cloud accounts, networks, compute/storage/database resources, IAM boundaries. Produces a tool-neutral design + a starter module for the chosen IaC tool. Does not provision anything. Use when planning cloud infrastructure, designing IaC with Terraform or Bicep, or defining network and compute topology.

fbakiyev Skill

Оценить фактический доступ к облаку или кластеру, возможность непредусмотренного доступа, изоляцию и средства аудита для определённой нагрузки или изменения конфигурации. Использовать, когда результатом запроса должна быть оценка защищённости.

nexadevapp Skill

Orchestrates the full bugfix pipeline for a BUG-XXX or GitHub issue: an isolated tester reproduces the bug and updates the issue, a senior-dev agent writes a root-cause fix plan while a business-analyst agent links the affected requirement(s) in parallel, then the fix is implemented and gated on Definition of Done. Use when the user asks to "fix this bug", "resolve BUG-XXX", "run the bugfix pipeline", pastes a GitHub issue link and asks to fix it, or mentions an end-to-end bug resolution workflow.

nexadevapp Skill

Merges a finished work item branch into main through a serial merge gate. Rebases the worktree branch onto main, resolves any conflict, runs the full unfiltered regression suite, fast-forwards main, closes the GitHub issue, and removes the worktree. Works for a use case, a technical task, a bug, or a change request. Use when the user asks to "merge the use case", "land the branch", "run the merge gate", "merge UC-XXX", or mentions the merge queue. Invoked by /deliver-cluster after every pipeline that finishes green.

nexadevapp Skill

Orchestrates the full bugfix pipeline for a BUG-XXX or GitHub issue: an isolated tester reproduces the bug and updates the issue, a senior-dev agent writes a root-cause fix plan while a business-analyst agent links the affected requirement(s) in parallel, then the fix is implemented and gated on Definition of Done. Use when the user asks to "fix this bug", "resolve BUG-XXX", "run the bugfix pipeline", pastes a GitHub issue link and asks to fix it, or mentions an end-to-end bug resolution workflow.

nexadevapp Skill

Orchestrates the full per-use-case delivery pipeline: writes the specification and the design if they are missing, implements the use case, writes E2E tests, and evaluates coverage against the spec. Iterates automatically until quality gates pass. The use case must be elaborated by /engineer-requirements first, and delivery runs in its own git worktree on a uc/UC-XXX branch. This skill must only be invoked explicitly via /deliver-use-case or by /deliver-cluster — never inferred from user messages.

nexadevapp Bundle

Generates a GitHub Actions workflow that gates pull requests on Go code quality (golangci-lint, gofumpt/goimports and templ formatting, generated-code drift for sqlc and templ) and test coverage (go test with integration tests and an 80% threshold). Use when the user asks to "set up CI for code quality", "enforce coverage in CI", "add quality gates", "run golangci-lint in CI", or mentions CI/CD for linting, formatting, or coverage in a Go project.

nexadevapp Skill

Merges a finished work item branch into main through a serial merge gate. Rebases the worktree branch onto main, resolves any conflict, runs the full unfiltered regression suite, fast-forwards main, closes the GitHub issue, and removes the worktree. Works for a use case, a technical task, a bug, or a change request. Use when the user asks to "merge the use case", "land the branch", "run the merge gate", "merge UC-XXX", or mentions the merge queue. Invoked by /deliver-cluster after every pipeline that finishes green.

nexadevapp Bundle

Generates a GitHub Actions workflow that runs the Playwright for Go end-to-end tests of a Go application on every pull request. The workflow sets up Go, installs Chromium through the pinned `go tool playwright`, runs `go test -tags=e2e` (which provisions PostgreSQL via Testcontainers), and uploads trace artifacts on failure. Use when the user asks to "set up CI for Playwright", "run e2e tests in CI", "add a GitHub Actions workflow for Playwright", or mentions CI/CD for end-to-end tests.

nexadevapp Skill

Retrofits an existing Go web application into the Nexa Agentic Engineering methodology by reverse-engineering a requirements catalog, entity model, use case diagram, and use case specs from the live code (routes, handlers, views, services, SQL migrations, and queries), and from BMAD-method artifacts under `_bmad/`, when present. Then audits cross-cutting infrastructure and creates thin-pointer GitHub issues for already-shipped work. Use when the user asks to "onboard this codebase", "onboard this Go app", "onboard an existing app", "retrofit Nexa onto my project", "adopt the Nexa pipeline for an existing Go app", "reverse-engineer requirements from code", or mentions bringing a brownfield or already-built Go project under Nexa/`/deliver-use-case`/`/resolve-bug` for future work.

nexadevapp Skill

Orchestrates the full per-use-case delivery pipeline: writes the specification and the design if they are missing, implements the use case, writes E2E tests, and evaluates coverage against the spec. Iterates automatically until quality gates pass. The use case must be elaborated by /engineer-requirements first, and delivery runs in its own git worktree on a uc/UC-XXX branch. This skill must only be invoked explicitly via /deliver-use-case or by /deliver-cluster — never inferred from user messages.

nexadevapp Bundle

Generates a GitHub Actions workflow that gates pull requests on code quality (oxlint, oxfmt) and test coverage (Vitest with v8 coverage thresholds). Use when the user asks to "set up CI for code quality", "enforce coverage in CI", "add quality gates", or mentions CI/CD for linting, formatting, or coverage.

nexadevapp Skill

Writes Nexa workflow enforcement rules into the target project's CLAUDE.md to prevent the AI agent from bypassing the methodology. Ensures the agent never skips the requirements-to-spec pipeline, never proposes jumping straight to implementation, always checks for duplicate use cases, and always uses the next available use case number. Run once at project inception; re-run if rules need updating. Use when the user asks to "set up project rules", "enforce workflow rules", "configure CLAUDE.md rules", "add Nexa rules to the project", or mentions project rules, workflow enforcement, or CLAUDE.md setup.

nexadevapp Bundle

Generates a GitHub Actions workflow that runs Playwright end-to-end tests on every pull request. The workflow provisions a PostgreSQL database via Testcontainers, installs Chromium, runs the full E2E suite, and uploads trace artifacts on failure. Use when the user asks to "set up CI for Playwright", "run e2e tests in CI", "add a GitHub Actions workflow for Playwright", or mentions CI/CD for end-to-end tests.

grasscaograss Skill

项目构建、发布和运行工作流。当用户请求编译(build/compile)、发布(publish/deploy)、运行(run/start/launch)项目,或询问如何构建、发布、运行项目时使用。支持完整的开发工作流:构建项目、发布构建产物、在 Windows 环境运行已发布的应用。

mindgoblinstudios Bundle

Helm (Biz Manager): Business Manager. Captain of the ship. Runs the business: operations, follow-through, priorities, and the engine of income. Monthly business reviews and Friday ship's logs.

davie521 Skill

Automated Git PR workflow: detect status → commit → create PR → wait for CI → fix failures → review Copilot comments critically → loop until all green → auto-merge. Use when user says 'cpr' or 'cl', wants to push code through the full PR pipeline, or wants to review and fix Copilot code review comments.

davie521 Skill

Feishu (Lark) MCP integration: send messages, create groups, import/read documents, query users. No file upload/download and no direct cloud-doc editing (official lark-mcp limitations). Use when user mentions '飞书'/Feishu/Lark, or asks to send a message to a Feishu group or user, create a Feishu group, import or read a Feishu doc, or look up Feishu contacts. Requires the 'feishu' MCP server (official lark-mcp CLI, tools like mcp__feishu__im_v1_*) to be configured — if its tools are absent, tell the user to configure it instead of guessing.

davie521 Skill

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.