Portable Library

Department plugins and installable skills with real paths, real commands, and fewer stale assumptions.

This catalog now mirrors the department-scoped plugins repo. Every skill lives under a concrete <department>/skills/<slug> path, and the install flows differ by runtime, so the site surfaces both the library and the current install matrix.

Featured Skills

Agentic Development

Use for end-to-end software execution in an unfamiliar or complex repo: orienting the codebase, choosing an execution model, planning and verifying changes, reviewing architecture or PRs, and coordinating work across the specialized `frontend` and `backend` engineering skills.

Cloud Management

Cross-cloud CLI-first cloud operations for AWS, Azure, and GCP. Use when the assistant needs to identify which cloud provider or multi-cloud estate a repo uses, deploy new resources or services, wire automatic deployments, inventory and optimize infrastructure, or diagnose and repair cloud failures entirely from the terminal, with explicit approval gates for high-cost, destructive, identity-sensitive, or hard-to-reverse changes.

Code Slides

Create and evolve code-based slide decks and presentations (pitch decks, demos, product walkthroughs, technical talks) with HTML/CSS/JS or React/TypeScript. Use when a user asks for slides implemented in code, a single-file HTML presentation, responsive behavior across mobile/tablet/desktop, PowerPoint/PPTX-to-web conversion, remote-control navigation, configurable right-side or bottom navigation, iframe-based deck rendering, visual style exploration, or image workflows that combine AI-generated assets, external URLs, local repo images, and code-as-image product mockups. Trigger this skill for new deck creation, redesigns, refactors, framework migrations, PPT conversions, and slide-quality QA.

Finances

Use for finance work across accounting reconciliation, financial modeling, and fundraising materials. Covers statement-to-ledger reconciliation, receipt linking, cash flow and scenario models, cap tables, investor messaging, materials audits, and fundraising process diagnostics.

Go to Market

Go-to-market planning and revenue execution skill for positioning, target segment definition, first-customer acquisition, launch plans, messaging hierarchies, pricing, channel strategy, technical pre-sales, growth experimentation, revenue intelligence, pipeline and forecast review, retention and expansion planning, content-to-revenue attribution, client reporting, and commercialization decisions. Use when the user needs a coherent market-facing plan tying product value to buyers, message, motion, channels, pricing, experiments, deal support, call insights, attribution, post-sale growth, revenue metrics, launch timing, and launch risks.

SEO and GEO

Use for SEO, GEO, and AEO work: keyword research, on-page optimization, AI-citation readiness, technical SEO audits, content gap analysis, competitor benchmarking, structured data, Core Web Vitals, internationalization, entity optimization, backlink analysis, content refreshes, and monitoring. Trigger when the user wants better search visibility in traditional or AI search systems.

Installation Modes

The repo is now plugin-first, so install targets depend on the runtime.

The old flat skills/<slug> commands are no longer the source of truth. Use these runtime-specific flows for full department plugins, selective skill installs, or local development.

Claude Code marketplace

Marketplace plus one department plugin

Full department plugins with teams, hooks, commands, references, and skills.

/plugin marketplace add alvarovillalbaa/plugins /plugin install engineering@agent-company

This is the current top-level plugin flow from the repo README. Install departments, not root-level single skills.

Vercel `npx skills`

Skills only

Cross-agent skill installs from a department or a single skill folder.

npx -y skills add ./engineering npx -y skills add ./marketing/skills/seo-and-geo

The repo is department-scoped now, so both department roots and individual skill folders are valid targets.

Codex manual install

Skills only

Installing one skill or a small set of skills with local control.

mkdir -p ~/.codex/skills cp -R engineering/skills/frontend ~/.codex/skills/

Use the department path that owns the skill instead of the old flat `skills/<slug>` layout.

Codex `$skill-installer`

Individual skills

Direct GitHub-backed skill installs inside Codex.

$skill-installer https://github.com/alvarovillalbaa/plugins/tree/main/engineering/skills/frontend

Point the installer at the concrete department skill path in GitHub.

OpenClaw manual install

Skills, optionally agents and commands

Local runtime skill folders, optionally alongside copied agents or commands.

mkdir -p ~/.openclaw/skills cp -R marketing/skills/code-slides ~/.openclaw/skills/

OpenClaw still works as a selective local copy workflow.

Git clone

Everything

Local development, direct loading, inspection, or forking.

git clone https://github.com/alvarovillalbaa/plugins.git cd plugins

Clone once when you want the entire company package and all department plugins locally.

Sparse checkout

Individual folders

Pulling only one department or skill subtree from Git.

git clone --filter=blob:none --no-checkout https://github.com/alvarovillalbaa/plugins.git cd plugins git sparse-checkout init --cone git sparse-checkout set engineering/skills/frontend git checkout main

Useful when you only need one skill path and want to avoid cloning the full repo.

Reset

Catalog

9 skills ready to explore

Results are ranked using the same local vector + lexical blend that powers the MCP layer, now against the current department-scoped plugin catalog.

Engineering

Agentic Development

General software-engineering orchestration skill for unfamiliar or complex repositories.

Use for end-to-end software execution in an unfamiliar or complex repo: orienting the codebase, choosing an execution model, planning and verifying changes, reviewing architecture or PRs, and coordinating work across the specialized `frontend` and `backend` engineering skills.

ai engineeringbackendcloud management

engineering/skills/agentic-development

How it works

  • Run the repo scan helper if available, or manually map the repo from the root.
  • Read repo-local instructions before proposing architecture or touching code.

Engineering

AI Engineering

AI and data engineering skill for ML systems, pipelines, prompt workflows, evaluation, and production AI architecture.

Use for ML, data, and AI engineering work: data pipelines, ETL and ELT, DataOps, warehouses and lakehouses, streaming systems, prompt and agent design, RAG, constrained generation, experiment design, model evaluation, feature engineering, and computer vision systems from dataset prep through production deployment.

agentic developmentbackendcloud management

engineering/skills/ai-engineering

How it works

  • Load only the reference files relevant to the current task (see Workflow Router below).
  • For data engineering: choose the processing model first — batch vs. streaming, Lambda vs. Kappa, warehouse vs. lakehouse.

Engineering

Backend

Backend engineering skill for APIs, services, schemas, persistence, and server-side operational work.

Use for backend engineering work such as APIs, services, data models, persistence, queues, caching, auth, background jobs, and server-side debugging or refactors.

agentic developmentai engineeringcloud management

engineering/skills/backend

How it works

  • Pair with [`../agentic-development/SKILL.md`](../agentic-development/SKILL.md) for repo orientation, proof planning, and execution-mode selection.
  • Map the authoritative backend path before editing: endpoint, serializer/validator, service, job, model, schema, queue consumer, or migration owner.

Engineering

Cloud Management

CLI-first cloud operations skill for AWS, Azure, and GCP.

Cross-cloud CLI-first cloud operations for AWS, Azure, and GCP. Use when the assistant needs to identify which cloud provider or multi-cloud estate a repo uses, deploy new resources or services, wire automatic deployments, inventory and optimize infrastructure, or diagnose and repair cloud failures entirely from the terminal, with explicit approval gates for high-cost, destructive, identity-sensitive, or hard-to-reverse changes.

agentic developmentai engineeringbackend

engineering/skills/cloud-management

How it works

  • CLI-first cloud operations skill for AWS, Azure, and GCP.

Engineering

Code Documentation

Documentation skill for READMEs, architecture notes, runbooks, ADRs, changelogs, and code-adjacent technical writing.

This skill should be used when the user asks to write, update, review, scaffold, or reorganize documentation for code, folders, services, repos, workflows, architectural decisions, or operational processes. Trigger for `README.md`, `ARCHITECTURE.md`, `TESTS.md`, `SETUP.md`, `RUNBOOK.md`, `CHANGELOG.md`, `SECURITY.md`, `OVERVIEW.md`, `FAQ.md`, `DECISIONS.md`, `DEPENDENCIES.md`, `AGENTS.md`, `PLAN.md`, `SPEC.md`, `SOUL.md`, `PRINCIPLES.md`, `DESIGN.md`, `runbooks/**/*.md`, `docs/**/*.md`, MDX docs, JSDoc/TSDoc, docstrings, ADRs, post-mortems, migration guides, and PR documentation-impact reviews.

agentic developmentai engineeringbackend

engineering/skills/code-documentation

How it works

  • Documentation skill for READMEs, architecture notes, runbooks, ADRs, changelogs, and code-adjacent technical writing.

Engineering

Frontend

Frontend engineering skill for browser-facing implementation, UI systems, and design-quality work.

Use for frontend engineering work such as components, routes, state management, accessibility, performance, design-system integration, and browser-facing debugging or refactors.

agentic developmentai engineeringbackend

engineering/skills/frontend

How it works

  • Pair with [`../agentic-development/SKILL.md`](../agentic-development/SKILL.md) for repo orientation and proof planning.
  • Map framework boundaries, route ownership, state owners, design-system sources, analytics seams, and error-reporting seams before editing.

Engineering

Pentest

Authorized offensive-security skill for validating exploitability against approved targets.

Use for authorized hands-on offensive security work against staging, sandbox, or lab targets. Covers pentest planning, finding validation, exploitability proof, raw HTTP replay, browser and API testing, network and cloud assessment, secrets and misconfiguration discovery, bounded post-exploitation, and evidence-driven pentest reporting. Do not use for passive code review or compliance audits.

agentic developmentai engineeringbackend

engineering/skills/pentest

How it works

  • Authorized offensive-security skill for validating exploitability against approved targets.

Engineering

PR Management

Pull request management skill for designing or improving review systems, merge policies, SLAs, and workflow health at team scale.

Pull request management skill for teams from 1 to 1000+ engineers. Use when the user needs to design or improve PR workflow, review queues, merge policy, ownership rules, branch strategy, review SLAs, CI gating, metrics, or operating rituals for getting code reviewed and merged safely at scale.

agentic developmentai engineeringbackend

engineering/skills/pr-management

How it works

  • Pull request management skill for designing or improving review systems, merge policies, SLAs, and workflow health at team scale.

Engineering

Quality Assurance

End-to-end QA skill for testing, debugging, secure engineering, code review, and release confidence.

End-to-end quality assurance and secure engineering for any software repo: code review, test strategy, bug triage, debugging, flaky-test repair, coverage analysis and improvement, suite architecture, CI quality gates, secure coding reviews, security audits, threat modeling, compliance validation, and dependency or vulnerability management for frontend, backend, full-stack, and AI systems. Use when reviewing PRs, writing or repairing tests, debugging failing suites, improving release confidence, creating test plans, running passive security reviews, or translating threats into requirements. For authorized active penetration testing, exploit validation against a running target, or pentest reporting, use `pentest`.

agentic developmentai engineeringbackend

engineering/skills/quality-assurance

How it works

  • Run `python <skill-dir>/scripts/qa-scan.py <repo-root>` when the bundled scanner is available; otherwise perform the same stack and CI inventory manually.
  • Preserve and read the full failure artifact set before changing code: stack traces, failing assertions, screenshots, traces, query logs, retry logs, seeds, and the first bad CI step.
Agent Skills | Alvaro Villalba