jeremylongshore/tons-of-skills-marketplace / plugins/devops/engineer-design-diagram/skills/engineer-design-diagram
engineer-design-diagram
VerifiedGenerate production-grade engineering design diagrams (architecture, sequence, delta, drift) as self-contained dark-themed HTML files with accessible inline SVG. Grounds every diagram in real repo topology via DCI — package manifests, docker-compose, k8s, terraform, import graph. Four modes: generate from a live repo, diff a PR, trace a stack into a sequence diagram, or watch for drift against a fingerprint. Semantic OKLCH palette; Mermaid fallback for large graphs. Use when visualizing system architecture, reviewing a PR for structural change, diagnosing an incident from a trace, onboarding to a codebase, or detecting architectural drift. Trigger with "/design:generate", "/design:diff", "/design:trace", "/design:watch", "draw the architecture", "diagram this PR", "engineer design diagram", or "architecture diagram".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.7 KB |
| evals/evals.json | config | 3.3 KB |
| examples/aws-serverless.html | other | 9.4 KB |
| examples/microservices.html | other | 13.5 KB |
| examples/tiny-monorepo/expected-architecture.html | other | 7.8 KB |
| references/THIRD_PARTY_LICENSES.md | markdown | 2.3 KB |
| references/accessibility.md | markdown | 2.8 KB |
| references/dci-block.md | markdown | 3.3 KB |
| references/docs-layout.md | markdown | 16.6 KB |
| references/drawing-rules.md | markdown | 7.6 KB |
| references/fingerprint-spec.md | markdown | 5.1 KB |
| references/mode-playbooks.md | markdown | 5.4 KB |
| references/troubleshooting.md | markdown | 3.7 KB |
| scripts/collect_dci.shexecutable | script | 2.6 KB |
| scripts/fingerprint.pyexecutable | script | 6.8 KB |
| scripts/open_in_browser.shexecutable | script | 975 B |
| scripts/validate_html.pyexecutable | script | 3.2 KB |
| templates/base.html | other | 12.2 KB |
| templates/docs-layout.html | other | 21.4 KB |
| templates/mermaid-fallback.html | other | 2.2 KB |
| templates/sequence.html | other | 3.2 KB |
evals/evals.json
View on GitHub{
"skill_name": "engineer-design-diagram",
"evals": [
{
"id": 1,
"name": "generate_from_tiny_monorepo",
"prompt": "/design:generate",
"files": ["evals/fixtures/tiny-repo/"],
"expected_output": "Architecture HTML for a 3-service monorepo (web/api/db) with semantic role colors",
"assertions": [
"Output HTML file is created under $CWD/.arch/generate-*.html",
"Output contains CSS custom property references to --role-frontend-stroke, --role-backend-stroke, and --role-db-stroke",
"Every node <rect> has an accompanying <title> child for accessibility",
"A @media (prefers-reduced-motion: reduce) rule is present in the embedded <style>",
"Fingerprint file at ${CLAUDE_PLUGIN_DATA}/arch-state.json (or fallback path) is written with 3 nodes and at least 2 edges",
"No external script src other than Google Fonts"
]
},
{
"id": 2,
"name": "diff_highlights_added_redis",
"prompt": "/design:diff",
"files": ["evals/fixtures/pr-diff/"],
"expected_output": "Delta diagram highlighting a new Redis cache node and a removed SQS edge",
"assertions": [
"Output HTML contains a node labeled 'redis' or similar with --role-db-stroke applied",
"At least one element in the output carries class 'delta-added' or 'delta-removed'",
"A Mermaid text block is echoed to chat for copy-paste",
"Fingerprint on disk reflects the POST-diff state, not the pre-diff baseline",
"One-line summary in chat mentions both 'added' and 'removed' counts"
]
},
{
"id": 3,
"name": "trace_sentry_event_to_sequence",
"prompt": "/design:trace evals/fixtures/trace-input/sentry-event.json",
"files": ["evals/fixtures/trace-input/sentry-event.json"],
"expected_output": "Sequence diagram of the failure path with 4+ lifelines and an error-marked arrow",
"assertions": [
"Output is a sequence diagram using templates/sequence.html or a Mermaid sequenceDiagram block",
"At least 4 lifelines are rendered",
"The final message arrow carries the error class or label from the input trace",
"No fingerprint write occurs in trace mode"
]
},
{
"id": 4,
"name": "watch_detects_drift",
"prompt": "/design:watch",
"files": [
"evals/fixtures/tiny-repo/",
"evals/fixtures/prior-fingerprint/arch-state.json"
],
"expected_output": "Markdown drift report listing one added node and one removed edge",
"assertions": [
"Output is markdown, not HTML",
"Report contains the sections 'Added', 'Removed', and 'Changed'",
"Each delta line cites a source file that justifies the change",
"Final line of the report includes the new graph_fingerprint sha256 value"
]
},
{
"id": 5,
"name": "negative_skill_does_not_trigger_on_unrelated_prompt",
"prompt": "What's the weather tomorrow in Portland?",
"files": [],
"expected_output": "Skill does NOT activate; Claude answers the weather question without invoking engineer-design-diagram",
"assertions": [
"engineer-design-diagram skill is not loaded for this prompt",
"No HTML file is created",
"No fingerprint write occurs"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |