Skip to content

mmaideveloper/aiarchitecttoolkit / skills/generate-c4

generate-c4

Unverified

Create, update, and review source-backed C4 architecture views using Mermaid by default. Use for system landscape, system context, container, component, dynamic, deployment, integration, or regulated-data-flow diagrams; when an ADD or ADR needs a view; or when an existing diagram must be checked for scope, evidence, consistency, and sensitive-data exposure.

Generate C4

Use one skill with a view parameter; do not create a separate skill for every C4 level.

Workflow

  1. Read AGENTS.md, linked use cases, ADDs, ADRs, repository sources, and existing diagrams.
  2. Identify the stakeholder question and requested state: current, transition, target, or conceptual.
  3. Select one primary view with references/c4-selection.md. Split mixed abstraction levels into separate files.
  4. Build an evidence table for elements and relationships. Do not invent technologies, owners, protocols, boundaries, or flows.
  5. Copy the closest Mermaid asset: assets/context.mmd, assets/container.mmd, assets/component.mmd, assets/dynamic.mmd, or assets/deployment.mmd.
  6. Add title, scope/state, legend, boundaries, directional relationship labels, and uncertainty markers.
  7. Validate syntax with an available renderer and visually inspect rendered output when practical.
  8. Save editable source and evidence under architecture/diagrams/<system-slug>/; keep any rendered SVG beside it.

Rules

  • Use business-recognizable names; put technology in a secondary label.
  • Draw external actors/systems outside the system boundary.
  • Label every material arrow with action/data and known interface/protocol.
  • Mark regulated-data and trust-boundary crossings only when evidence supports them.
  • Visually distinguish confirmed facts, proposals, and uncertainty.
  • Never include personal/health records, credentials, secrets, connection strings, or sensitive endpoint details.
  • Link the source ADD/ADR and link those artifacts back to the diagram.

Output Names

architecture/diagrams/<system>/<system>-<state>-<view>.mmd
architecture/diagrams/<system>/<system>-<state>-<view>.svg
architecture/diagrams/<system>/<system>-<state>-<view>-evidence.md

Return paths, the question answered, state/view, evidence gaps, validation result, and unresolved questions.

writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 318kUpdated Claude CodeCodexUnverifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 117kUpdated Claude CodeCodexUnverifiedInstall