skills/visualizer/SKILL.md
Generate polished, self-contained visual explainers, reviews, diagrams, dashboards, comparison pages, and slide-mode HTML from technical or business inputs. Use when the user asks for a diagram, architecture overview, diff or plan review, project recap, comparison matrix, audit page, timeline, dashboard, or any explanation that would be clearer as a visual artifact than as plain terminal text. Also use proactively when the output would otherwise become a dense table or long text wall.
npx skillsauth add alvarovillalbaa/agent-suite visualizerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Turn complex material into visual artifacts that are faster to scan, easier to trust, and worth sharing.
The default output is a self-contained HTML artifact. When the environment supports it, preview or open the generated file after writing it. If opening is not available, still produce the artifact and report the path.
Use this skill to produce one of these artifacts:
Do not default to ASCII art, giant markdown tables, or text-only walls when the information has clear structure.
Use this skill even if the user did not explicitly ask for HTML when either condition is true:
You can still include a concise chat summary, but the primary artifact should be the HTML output.
Gather only the inputs that materially change the artifact:
If key context is missing, ask 2 to 4 targeted questions. Do not run a long survey.
Choose the narrowest mode that fits the job.
Use for:
Default structure:
Use for:
Default structure:
Use for:
Default structure:
Use for:
Default structure:
Use for:
Default structure:
Use for:
Keep each slide focused on one idea. If the user needs a full presentation system with controls, speaker mode, or remote navigation, hand off to code-slides.
Choose the rendering method deliberately. Read references/rendering-strategy.md before generating complex artifacts.
General rules:
Pick a strong direction and commit to it. Read references/visual-directions.md.
Preferred directions:
Avoid generic defaults:
Every output should:
For pages with 4 or more sections:
For diagrams:
For comparisons and audits:
scaffold_visualizer.py: Generate a strong starter HTML artifact for explainer, review, or slide-mode pages.rendering-strategy.md: Map content types to the right rendering approach.visual-directions.md: Visual systems, palette guidance, and anti-patterns.output-checklist.md: Final QA checklist before delivery.templates/explainer.html: Starter shell for explainers and architecture pages.templates/review.html: Starter shell for audits, plan reviews, and comparisons.templates/slide-mode.html: Starter shell for presentation-style output.code-slides when the user needs a full presentation system rather than a single visual artifact.quality-assurance or agentic-development first when the hard part is the underlying technical review, then use visualizer to present the result.code-documentation when the primary output should be written documentation rather than a visual page.development
Use for frontend engineering work such as components, routes, state management, accessibility, performance, design-system integration, and browser-facing debugging or refactors.
development
This skill should be used when the user asks to write, update, review, scaffold, move, remove, or continuously improve documentation for code, folders, services, repos, workflows, architectural decisions, or operational processes. Trigger for inline docs, `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`, `logs/`, `lessons/`, `items/`, `fixes/`, `audits/`, `raw/`, `plans/`, `specs/`, `sources/`, `lib/`, `references/`, `cookbook/`, `knowledge/`, `runbooks/`, `research/`, `official-documentation/`, `context/`, MDX docs, JSDoc/TSDoc, docstrings, ADRs, post-mortems, migration guides, documentation cleanups, and documentation-impact reviews.
tools
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. Covers AWS Amplify full-stack projects, serverless workloads (Lambda, API Gateway, Step Functions, SAM, CDK), and the full AWS database portfolio (RDS, Aurora, Aurora DSQL, DynamoDB, ElastiCache), as well as deep Azure references for diagnostics, storage, compute, compliance, identity, Foundry, and cross-cloud migrations.
development
Use for backend engineering work such as APIs, services, data models, persistence, queues, caching, auth, background jobs, and server-side debugging or refactors.