菜单
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Comprehensive Terragrunt 1.x skill for generating, validating, reviewing, and debugging Terragrunt configurations (root.hcl, terragrunt.hcl, terragrunt.stack.hcl, units, stacks, catalogs) across AWS, Azure, and GCP. Use this skill whenever the user mentions Terragrunt, terragrunt.hcl, root.hcl, stack files, units, HCL orchestration of OpenTofu/Terraform, remote state DRY configuration, run --all, dependency blocks between modules, or asks to scaffold/lint/diagnose multi-environment IaC layouts — even if they don't say "Terragrunt" explicitly but show Terragrunt HCL.
Orchestration playbook for driving the development agent fleet (code-builder, fact-verifier, coherence-checker, code-reviewer) through a build → verify → cohere → review → commit pipeline with explicit, deterministic hand-offs. Use when implementing a non-trivial change where correctness and fact-accuracy matter and you want the steps to actually run in order rather than hoping the orchestrator delegates. Also use when deciding which fleet agent to dispatch for a task, or when wiring a new agent into the pipeline. Covers how to pass context between agents, the fact-gate and coherence-gate before commit, the loop-back semantics on each gate, and handing off to commit-pr.
Use when running Linear.app operations from the command line — creating, updating, archiving, listing, or filtering issues, setting project milestones, or wiring blocked-by relations via the `linearis` CLI (binaries `linear` and `linearis`, JSON output) instead of an MCP or the web UI. Triggers on any Linear issue/project/milestone task in a terminal, and on syncing Kevin's Ogham roadmap with its shared-memory database. Covers generic install/auth setup, the CLI's sharp edges, and the pre-loaded Ogham project IDs. Not a full reference — that's `linear <cmd> --help`.
Tailor and polish a CV/resume to maximise its score in applicant tracking systems (ATS), covering both keyword/JD-matching screeners and modern LLM-rubric scorers (which often take no job description at all). Use this whenever the user wants to optimise, tailor, rewrite, or "ATS-proof" a CV or resume, asks why their resume isn't getting through screening, wants a keyword/gap analysis against a job description, wants to remove AI-generated texture from a CV, or wants to check whether a CV parses cleanly. Trigger even if the user only supplies a CV (with or without a job description), or asks to "make my resume match this job" or "pass the ATS". Do NOT use for writing a CV from a blank page with no material to work from, or for generic career advice unrelated to a document.
Playbook for getting external data into the repo deterministically — fetch a web page, doc, or API/registry result once, extract and normalize it, and cache it as a pinned, provenance-stamped artifact that agents read instead of re-fetching live. Use when you need facts an LLM or agent will rely on (docs, library/API behavior, Terraform/provider registry data, prices, schemas) to be reproducible and offline-readable rather than varying per run. Also use when deciding whether to snapshot vs. fetch live, and which extractor to use for a given source. Pairs with fact-verifier (snapshots become its tier-1 sources) and markdown-converter.
Deterministic, offline-first lookups over Azure Policy, Policy Initiative, and RBAC Role metadata sourced from AzAdvertizer's CSV exports — including the cross-references that exist nowhere else in one place (which roles a policy uses, which initiatives include a policy, which policies a role is used by). Use whenever you need accurate current facts about an Azure built-in policy, initiative/policy-set, or RBAC role — definitions, effects, allowed effect values, categories, role actions/dataActions, or the policy↔role and policy↔initiative relationships — for writing or reviewing Azure IaC, governance, or landing-zone work. Fetches each CSV once into a provenance-stamped cache and answers queries offline; stdlib only, JSON envelope output. Pairs with terragrunt-skill, azure-architect, and fact-verifier (snapshots become tier-1 sources).
| name | excalidraw-diagram |
| description | Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts. |
Generate .excalidraw JSON files that argue visually, not just display information.
Setup: If the user asks you to set up this skill (renderer, dependencies, etc.), see README.md for instructions.
Provenance: The design methodology began as a fork of coleam00/excalidraw-diagram-skill. The render pipeline was rebuilt around Excalidraw (@excalidraw/excalidraw, MIT): the engine is fetched from a pinned, sha256-verified GitHub Release on first render, cached under references/vendor/, and served locally from then on — offline after that one-time fetch, like playwright install chromium. The icon-library ingestion approach (split a .excalidrawlib into per-icon files + an index, then place deterministically) is credited to github/awesome-copilot (MIT); the scripts here are an independent implementation. The MIT license on this skill covers the skill content; the vendored Excalidraw bundle and fonts remain under their own (MIT / respective) licenses, and any user-supplied icon libraries remain under theirs.
All colors and brand-specific styles live in one file: references/color-palette.md. Read it before generating any diagram and use it as the single source of truth for all color choices — shape fills, strokes, text colors, evidence artifact backgrounds, everything.
To make this skill produce diagrams in your own brand style, edit color-palette.md. Everything else in this file is universal design methodology and Excalidraw best practices.
Diagrams should ARGUE, not DISPLAY.
A diagram isn't formatted text. It's a visual argument that shows relationships, causality, and flow that words alone can't express. The shape should BE the meaning.
The Isomorphism Test: If you removed all text, would the structure alone communicate the concept? If not, redesign.
The Education Test: Could someone learn something concrete from this diagram, or does it just label boxes? A good diagram teaches—it shows actual formats, real event names, concrete examples.
Before designing, determine what level of detail this diagram needs:
Use abstract shapes when:
Use concrete examples when:
For technical diagrams, you MUST include evidence artifacts (see below).
Before drawing anything technical, research the actual specifications.
If you're diagramming a protocol, API, or framework:
Bad: "Protocol" → "Frontend" Good: "AG-UI streams events (RUN_STARTED, STATE_DELTA, A2UI_UPDATE)" → "CopilotKit renders via createA2UIMessageRenderer()"
Research makes diagrams accurate AND educational.
Evidence artifacts are concrete examples that prove your diagram is accurate and help viewers learn. Include them in technical diagrams.
Types of evidence artifacts (choose what's relevant to your diagram):
| Artifact Type | When to Use | How to Render |
|---|---|---|
| Code snippets | APIs, integrations, implementation details | Dark rectangle + syntax-colored text (see color palette for evidence artifact colors) |
| Data/JSON examples | Data formats, schemas, payloads | Dark rectangle + colored text (see color palette) |
| Event/step sequences | Protocols, workflows, lifecycles | Timeline pattern (line + dots + labels) |
| UI mockups | Showing actual output/results | Nested rectangles mimicking real UI |
| Real input content | Showing what goes IN to a system | Rectangle with sample content visible |
| API/method names | Real function calls, endpoints | Use actual names from docs, not placeholders |
Example: For a diagram about a streaming protocol, you might show:
Example: For a diagram about a data transformation pipeline:
The key principle: show what things actually look like, not just what they're called.
Comprehensive diagrams operate at multiple zoom levels simultaneously. Think of it like a map that shows both the country borders AND the street names.
A simplified overview showing the full pipeline or process at a glance. Often placed at the top or bottom of the diagram.
Example: Input → Processing → Output or Client → Server → Database
Labeled regions that group related components. These create visual "rooms" that help viewers understand what belongs together.
Example: Grouping by responsibility (Backend / Frontend), by phase (Setup / Execution / Cleanup), or by team (User / System / External)
Evidence artifacts, code snippets, and concrete examples within each section. This is where the educational value lives.
Example: Inside a "Backend" section, you might show the actual API response format, not just a box labeled "API Response"
For comprehensive diagrams, aim to include all three levels. The summary gives context, the sections organize, and the details teach.
| Bad (Displaying) | Good (Arguing) |
|---|---|
| 5 equal boxes with labels | Each concept has a shape that mirrors its behavior |
| Card grid layout | Visual structure matches conceptual structure |
| Icons decorating text | Shapes that ARE the meaning |
| Same container for everything | Distinct visual vocabulary per concept |
| Everything in a box | Free-floating text with selective containers |
| Simple Diagram | Comprehensive Diagram |
|---|---|
| Generic labels: "Input" → "Process" → "Output" | Specific: shows what the input/output actually looks like |
| Named boxes: "API", "Database", "Client" | Named boxes + examples of actual requests/responses |
| "Events" or "Messages" label | Timeline with real event/message names from the spec |
| "UI" or "Dashboard" rectangle | Mockup showing actual UI elements and content |
| ~30 seconds to explain | ~2-3 minutes of teaching content |
| Viewer learns the structure | Viewer learns the structure AND the details |
Simple diagrams are fine for abstract concepts, quick overviews, or when the audience already knows the details. Comprehensive diagrams are needed for technical architectures, tutorials, educational content, or when you want the diagram itself to teach.
Not every piece of text needs a shape around it. Default to free-floating text. Add containers only when they serve a purpose.
| Use a Container When... | Use Free-Floating Text When... |
|---|---|
| It's the focal point of a section | It's a label or description |
| It needs visual grouping with other elements | It's supporting detail or metadata |
| Arrows need to connect to it | It describes something nearby |
| The shape itself carries meaning (decision diamond, etc.) | Typography alone creates sufficient hierarchy |
| It represents a distinct "thing" in the system | It's a section title, subtitle, or annotation |
Typography as hierarchy: Use font size, weight, and color to create visual hierarchy without boxes. A 28px title doesn't need a rectangle around it.
The container test: For each boxed element, ask "Would this work as free-floating text?" If yes, remove the container.
Before anything else, determine if this needs to be:
If comprehensive: Do research first. Look up actual specs, formats, event names, APIs.
Read the content. For each concept, ask:
For each concept, find the visual pattern that mirrors its behavior:
| If the concept... | Use this pattern |
|---|---|
| Spawns multiple outputs | Fan-out (radial arrows from center) |
| Combines inputs into one | Convergence (funnel, arrows merging) |
| Has hierarchy/nesting | Tree (lines + free-floating text) |
| Is a sequence of steps | Timeline (line + dots + free-floating labels) |
| Loops or improves continuously | Spiral/Cycle (arrow returning to start) |
| Is an abstract state or context | Cloud (overlapping ellipses) |
| Transforms input to output | Assembly line (before → process → after) |
| Compares two things | Side-by-side (parallel with contrast) |
| Separates into phases | Gap/Break (visual separation between sections) |
For multi-concept diagrams: each major concept must use a different visual pattern. No uniform cards or grids.
Before JSON, mentally trace how the eye moves through the diagram. There should be a clear visual story.
Only now create the Excalidraw elements. See below for how to handle large diagrams.
Before you start, skim references/examples/ — worked diagrams (JSON + rendered PNG) that show this methodology in practice. Read the one closest to what you're drawing; it's faster to imitate good moves than to derive them.
After generating the JSON, you MUST run the render-view-fix loop until the diagram looks right. This is not optional — see the Render & Validate section below for the full process.
For comprehensive or technical diagrams, you MUST build the JSON one section at a time. Do NOT attempt to generate the entire file in a single pass. This is a hard constraint — Claude Code has a ~32,000 token output limit per response, and a comprehensive diagram easily exceeds that in one shot. Even if it didn't, generating everything at once leads to worse quality. Section-by-section is better in every way.
Phase 1: Build each section
type, version, appState, files) and the first section of elements."trigger_rect", "arrow_fan_left") so cross-section references are readable.boundElements array at the same time.Phase 2: Review the whole
After all sections are in place, read through the complete JSON and check:
Fix any alignment or binding issues before rendering.
Phase 3: Render & validate
Now run the render-view-fix loop from the Render & Validate section. This is where you'll catch visual issues that aren't obvious from JSON — overlaps, clipping, imbalanced composition.
Plan your sections around natural visual groupings from the diagram plan. A typical large diagram might split into:
Each section should be independently understandable: its elements, internal arrows, and any cross-references to adjacent sections.
Central element with arrows radiating to multiple targets. Use for: sources, PRDs, root causes, central hubs.
○
↗
□ → ○
↘
○
Multiple inputs merging through arrows to single output. Use for: aggregation, funnels, synthesis.
○ ↘
○ → □
○ ↗
Parent-child branching with connecting lines and free-floating text (no boxes needed). Use for: file systems, org charts, taxonomies.
label
├── label
│ ├── label
│ └── label
└── label
Use line elements for the trunk and branches, free-floating text for labels.
Elements in sequence with arrow returning to start. Use for: feedback loops, iterative processes, evolution.
□ → □
↑ ↓
□ ← □
Overlapping ellipses with varied sizes. Use for: context, memory, conversations, mental states.
Input → Process Box → Output with clear before/after. Use for: transformations, processing, conversion.
○○○ → [PROCESS] → □□□
chaos order
Two parallel structures with visual contrast. Use for: before/after, options, trade-offs.
Visual whitespace or barrier between sections. Use for: phase changes, context resets, boundaries.
Use lines (type: line, not arrows) as primary structural elements instead of boxes:
Timeline: Tree:
●─── Label 1 │
│ ├── item
●─── Label 2 │ ├── sub
│ │ └── sub
●─── Label 3 └── item
Lines + free-floating text often creates a cleaner result than boxes + contained text.
Choose shape based on what it represents—or use no shape at all:
| Concept Type | Shape | Why |
|---|---|---|
| Labels, descriptions, details | none (free-floating text) | Typography creates hierarchy |
| Section titles, annotations | none (free-floating text) | Font size/weight is enough |
| Markers on a timeline | small ellipse (10-20px) | Visual anchor, not container |
| Start, trigger, input | ellipse | Soft, origin-like |
| End, output, result | ellipse | Completion, destination |
| Decision, condition | diamond | Classic decision symbol |
| Process, action, step | rectangle | Contained action |
| Abstract state, context | overlapping ellipse | Fuzzy, cloud-like |
| Hierarchy node | lines + text (no boxes) | Structure through lines |
Rule: Default to no container. Add shapes only when they carry meaning. Aim for <30% of text elements to be inside containers.
Colors encode information, not decoration. Every color choice should come from references/color-palette.md — the semantic shape colors, text hierarchy colors, and evidence artifact colors are all defined there.
Key principles:
Do not invent new colors. If a concept doesn't fit an existing semantic category, use Primary/Neutral or Secondary.
For clean, professional diagrams:
roughness: 0 — Clean, crisp edges. Use for modern/technical diagrams.roughness: 1 — Hand-drawn, organic feel. Use for brainstorming/informal diagrams.Default to 0 for most professional use cases.
strokeWidth: 1 — Thin, elegant. Good for lines, dividers, subtle connections.strokeWidth: 2 — Standard. Good for shapes and primary arrows.strokeWidth: 3 — Bold. Use sparingly for emphasis (main flow line, key connections).Always use opacity: 100 for all elements. Use color, size, and stroke width to create hierarchy instead of transparency.
Instead of full shapes, use small dots (10-20px ellipses) as:
The most important element has the most empty space around it (200px+).
Guide the eye: typically left→right or top→bottom for sequences, radial for hub-and-spoke.
Position alone doesn't show relationships. If A relates to B, there must be an arrow.
CRITICAL: The JSON text property contains ONLY readable words.
{
"id": "myElement1",
"text": "Start",
"originalText": "Start"
}
Settings: fontSize: 16, fontFamily: 3, textAlign: "center", verticalAlign: "middle"
{
"type": "excalidraw",
"version": 2,
"source": "https://excalidraw.com",
"elements": [...],
"appState": {
"viewBackgroundColor": "#ffffff",
"gridSize": 20
},
"files": {}
}
See references/element-templates.md for copy-paste JSON templates for each element type (text, line, dot, rectangle, arrow). Pull colors from references/color-palette.md based on each element's semantic purpose.
references/examples/ holds full diagrams that realize this methodology — each a real .excalidraw file paired with its rendered PNG, with references/examples/README.md explaining what each one demonstrates. These are exemplars, not fill-in templates: study the moves (shape-as-meaning, color-as-argument, evidence artifacts, multi-zoom), then design your own.
cicd-pipeline — simple/moderate: assembly-line flow, a decision diamond that branches pass/fail by color, evidence chips with real commands.oauth-authcode-flow — comprehensive/technical: a sequence diagram whose front-/back-channel coloring carries the security argument, plus dark evidence panels showing the actual RFC 6749 token exchange.For technical cloud/infra architecture diagrams, you can place real service icons (AWS, Azure, GCP, K8s) instead of generic rectangles. Icons are the concrete detail layer — the structure, flow, and visual argument are still yours to author (this is not license to drop icons in a uniform grid; that's "display", not "argue").
Only when a library is installed. Check references/libraries/ for a <set>/reference.md. If none exists, tell the user how to add one (see references/libraries/README.md) — don't invent icons.
Workflow:
references/libraries/<set>/reference.md to pick icons by name. It lists each icon's size so you can plan spacing — never open the icon JSON files, that's what the placement script is for.cd references
uv run python scripts/place_icon.py --diagram <file.excalidraw> \
--icon "Lambda" --library libraries/aws --x 400 --y 240 [--label "Auth"]
(x, y), regenerates all ids/groups so repeated placements never collide, merges image data for raster icons, and appends to the diagram. Flags: --anchor center, --scale <f> (best-effort), --label (see below).Gotchas:
--label or you'll double the caption. Render once to check.You cannot judge a diagram from JSON alone. After generating or editing the Excalidraw JSON, you MUST render it to PNG, view the image, and fix what you see — in a loop until it's right. This is a core part of the workflow, not a final check.
cd .claude/skills/excalidraw-diagram/references && uv run python render_excalidraw.py <path-to-file.excalidraw>
This outputs a PNG next to the .excalidraw file. Then use the Read tool on the PNG to actually view it.
Rendering is offline after a one-time engine download. The fonts are vendored under references/vendor/; the Excalidraw engine (vendor/excalidraw.mjs) is fetched once on first render from a pinned, sha256-verified GitHub Release (see vendor/bundle.lock.json) — exactly like playwright install chromium — then served locally. So a failed first fetch is a network problem; a render that fails after the engine is present is not — the renderer prints the real cause and exits non-zero within a few seconds. If the download fails, build the engine locally with references/scripts/vendor.sh.
After generating the initial JSON, run this cycle:
1. Render & View — Run the render script, then Read the PNG.
2. Audit against your original vision — Before looking for bugs, compare the rendered result to what you designed in Steps 1-4. Ask:
3. Check for visual defects:
4. Fix — Edit the JSON to address everything you found. Common fixes:
x/y coordinates to fix spacing and alignmentpoints arrays to route around elements5. Re-render & re-view — Run the render script again and Read the new PNG.
6. Repeat — Keep cycling until the diagram passes both the vision check (Step 2) and the defect check (Step 3). Typically takes 2-4 iterations. Don't stop after one pass just because there are no critical bugs — if the composition could be better, improve it.
The loop is done when:
If the render script hasn't been set up yet:
cd .claude/skills/excalidraw-diagram/references
uv sync
uv run playwright install chromium
text contains only readable wordsfontFamily: 3roughness: 0 for clean/modern (unless hand-drawn style requested)opacity: 100 for all elements (no transparency)