website-deployment

Feature lifecycle management with state, search, epic dispatch, and review gates. Capture ideas, plan, and ship as files (idea.md → plan.md → shipped.md) with orthogonal state (active/paused/replaced/abandoned). Single-feature autopilot and parallel-wave epic dispatch — every subagent in its own worktree, with a local CI-parity preflight gate before every push. Per-feature review override (external Gemini/Codex CI / internal subagent / skip). Auto-generated DASHBOARD.md with Paused, Epics, and Validation Warnings sections. Multi-repo workspaces: an aggregated cross-repo dashboard, cross-repo epics, contract-edit warnings, and coordinated producer-first deploy.

18 skills · 12 agents · hooks

Write, revise, and push blog posts to a Ghost site from Claude Code — a Ghost Admin API MCP plus a plan→draft→revise→push skill set.

7 skills · 1 MCP server

Evergreen engineering standards I hold code to — the judgment layer that AI-slop resistance needs on top of the mechanical quality stack. Project-structure conventions (consistent layout + naming so every repo looks the same), worktree isolation (every line of work in its own tree so parallel work never collides), and GitHub API discipline (zipball over per-file, rate-limit backoff), with automation-auth (GitHub App vs PAT) and hook-escape conventions on the way. Pure advisory skills that fire when the situation matches — no tooling, no setup, safe to leave enabled for a project's whole life. Backed by lessons from real incidents.

6 skills

Sprint planning and team coordination. Triage backlogs by deadline, assign work with self-service specs, audit feature specs for completeness, and generate team communication. Designed for small teams with mixed experience levels.

5 skills

One-shot setup for a new repo's standards: feat → dev → main promotion model with a PR CI gate, GitHub repo setup (branch protection, deploy environments, required reviewers, environment-scoped OIDC), and the language-agnostic quality stack (lefthook hooks + a shared justfile, run identically in CI). The /project-init skill detects current state and applies only the missing patterns — on new repos and existing ones alike, plus an on-ramp for multi-repo workspaces (scaffold a coordination repo via feature-init --workspace). Setup-only and disposable: the evergreen standards live in the engineering-standards and quality-workflow plugins, pulled in as dependencies. Backed by lessons from real incidents.

4 skills

Sister to feature-workflow for code-quality findings. Surfaces, triages, and resolves static-analysis output (skylos for Python, fallow for TS/JS) with the same backlog-and-epic discipline. User-invocable skills: /quality-verify-hook self-tests pre-commit hooks against known-bad fixtures (catches the silently-misconfigured-hook class of bug), /quality-audit produces fingerprinted snapshots + NEW/RESOLVED/PERSISTING delta (suppressed findings excluded from active counts), /quality-unblock triages failing hooks with playbook-driven fix/suppress/defer proposals and refuses bare suppressions. Plus the language-agnostic suppression-discipline standard (every ignore carries an inline rationale). Day-1 playbooks for 13 skylos + 12 fallow rule_ids.

4 skills

Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.

44 skills · 1 MCP server

CI/CD pipeline configuration, GitHub Actions/GitLab CI workflow setup, and automated deployment pipeline orchestration

4 skills · 1 command · 5 agents

Build, manage, and deploy Wix sites and apps. Includes CLI development skills and Wix MCP server for site management, eCommerce, CMS, dashboard extensions, and more.

37 skills · 1 MCP server

Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).

6 skills · 8 commands · 4 agents · hooks

DevOps, cloud, and deployment specialists - Kubernetes, Terraform, AWS, Azure, GCP, and SRE

Connect Claude to Prowler Cloud through the Prowler MCP server. Reads providers, scans, findings, compliance results and resources for AWS, Azure, GCP, Kubernetes, Microsoft 365, GitHub and the other providers listed at https://registry.prowler.com, and returns remediation guidance for failed checks. Writes are limited to Prowler Cloud itself: triggering scans, finding triage, mute rules and the mutelist, providers and integrations. Your cloud resources are not changed by the connector.

1 skill · 1 MCP server