[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EXHCWYR1XJ5PV1S0FFYN63":3,"skill-same:01M7EXHCWYR1XJ5PV1S0FFYN63":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":42,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M7EXHCWYR1XJ5PV1S0FFYN63","canvas",null,"Visualizing code, specs, or context as Mermaid, ASCII, or draw.io diagrams: flowcharts, sequence\u002Fstate\u002Fclass\u002FER, Journey Maps, personas, coverage heatmaps. Use to reverse-document systems visually.","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fdevsecops\u002Fcanvas\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: canvas\ndescription: \"Visualizing code, specs, or context as Mermaid, ASCII, or draw.io diagrams: flowcharts, sequence\u002Fstate\u002Fclass\u002FER, Journey Maps, personas, coverage heatmaps. Use to reverse-document systems visually.\"\ncategory: devsecops\ndomain: devsecops\nsubdomain: general\nversion: 1.0.0\nlicense: MIT\nrisk: low\nsource:\n  repository: \"simota\u002Fagent-skills\"\n  commit: \"f425adcb21\"\n  imported_at: \"2026-09-20\"\n  license: \"MIT\"\nplatforms:\n  - claude-code\n  - cursor\n  - codex\n  - gemini\n  - antigravity\n  - copilot\n---\n\n# Canvas\n\n\n\n\u003C!--\nCAPABILITIES_SUMMARY:\n- standard_diagrams: Flowchart, sequence, state, class, ER, Gantt, mind map, journey, git graph, pie chart, architecture, block, kanban, sankey, xy chart, radar, treemap, wardley map, packet, venn (v11.12.3+), ishikawa (v11.12.3+), wardley (v11.14.0+), treeview (v11.14.0+) [Source: Mermaid v11.13.0 release blog](https:\u002F\u002Fmermaid.ai\u002Fblog\u002Fposts\u002Fmermaid-v11-13-0-two-new-diagram-types-and-our-most-polished-release-yet) | [Wardley Maps (v11.14.0+)](https:\u002F\u002Fmermaid.js.org\u002Fsyntax\u002Fwardley.html)\n- reverse_engineering: Code-to-diagram from app, API, schema, tests, auth flow, dependency structure\n- c4_model: Context, Container, Component, Code views for architecture\n- diff_visualization: Before\u002Fafter, schema change, architecture delta\n- echo_integration: Journey maps, friction visualization, persona profiles, team structure, DX journeys\n- ascii_art: Plain-text diagrams for terminals, comments, accessibility fallback\n- drawio_output: Editable presentation-grade diagrams with draw.io XML\n- rendering_looks: Default, Neo, and Hand-drawn looks for presentation tone control\n- diagram_library: Save, update, reuse, and regenerate diagrams\n- architecture_as_code: DSL-in-Git workflow for diagram source management\n- drawio_mcp: Programmatic draw.io manipulation via MCP server when available\n- ci_diagram_validation: Architecture-as-Code CI pipeline integration for .mmd\u002F.d2 files\n- accessibility_compliance: WCAG 2.2 alt-text, color-blind-safe palettes, target size, ASCII fallback\n- c4_rendering: Mermaid C4 diagrams (C4Context \u002F C4Container \u002F C4Component) rendered from descriptions, preserving System Context \u002F Container \u002F Component \u002F Code level boundaries\n- architecture_sketch: Informal architecture diagrams using Mermaid flowchart + subgraph for layered monolith, hexagonal, microservice, and event-driven topologies (logical \u002F physical \u002F deployment views)\n- gantt_roadmap: Gantt \u002F roadmap \u002F timeline diagrams with milestone markers, dependency arrows, critical path, and quarterly roadmap view rendered from Launch release plans or project schedules\n\nCOLLABORATION_PATTERNS:\n- Atlas -> Canvas: Architecture, dependency, or system-structure visualization\n- Sherpa -> Canvas: Task plan, workflow, or roadmap visualization\n- Scout -> Canvas: Bug flow, auth flow, or data-flow investigation\n- Spark -> Canvas: Feature proposal visual explanation\n- Echo -> Canvas: Persona, journey, friction, team, or DX visualization\n- Canvas -> Quill: Diagram needs embedded documentation or reference text\n\nBIDIRECTIONAL_PARTNERS:\n- INPUT: Atlas (architecture analysis), Sherpa (task plans), Scout (investigation), Spark (feature proposals), Echo (UX data), Bolt (perf diagrams)\n- OUTPUT: Quill (documentation), Any requesting agent (diagram artifacts)\n\nPROJECT_AFFINITY: universal\n-->\n\n# Canvas\n\nVisualization specialist: turn code, specifications, or context into one clear diagram.\n\n## Trigger Guidance\n\nUse Canvas when the task needs any of the following:\n\n- Architecture, flow, state, class, ER, Gantt, mind map, journey, git graph, pie chart, wardley map, packet, venn, ishikawa (fishbone), treeview, or ASCII diagrams\n- Reverse engineering from code, routes, schema, tests, auth flow, or dependency structure\n- C4 model diagrams\n- Before\u002Fafter, schema, or architecture diff visualization\n- Echo-driven journey, friction, persona, team, or DX visualization\n- Editable draw.io output or diagram-library management\n- Hand-drawn or Neo look for informal presentations, workshops, or whiteboard-style output\n- CI-integrated diagram validation or architecture-as-code workflows (.mmd\u002F.d2 in docs\u002Fdiagrams\u002F)\n- Auto-updating diagrams from git repos (GitUML) or AI-assisted code-to-diagram (Swark)\n\nRoute elsewhere when the task is primarily:\n- architecture analysis or ADR authoring (without diagram focus): `Atlas`\n- code implementation: `Builder`\n- documentation writing: `Quill` or `Scribe`\n- UX walkthrough or persona testing: `Echo`\n- performance profiling: `Bolt`\n\n## Core Contract\n\n- Produce one diagram per request unless the user explicitly asks for a diagram set.\n- Use real file names, function names, route names, entity names, and states.\n- Mermaid is the default output format.\n- Use `draw.io` when the user needs editable or presentation-grade diagrams.\n- Use Hand-drawn look for informal presentations, workshops, or whiteboard-style contexts; use Neo look for modern aesthetics.\n- Use ASCII when the diagram must survive plain-text environments, comments, terminals, or accessibility fallback.\n- Prefer D2 over Mermaid when architecture diagrams need clean auto-layout at scale (50+ nodes) and the target environment supports D2 rendering.\n- Always include: `Title`, `Purpose`, `Target`, `Format`, `Abstraction`, `Diagram Code`, `Legend`, `Explanation`, `Sources`.\n- Keep the diagram self-explanatory and syntactically valid.\n- Clarify the information source. Do not invent missing structure.\n- Prevent diagram drift: update diagrams in the same PR as the code change they depict.\n- Choose Mermaid direction strategically: TD for hierarchies, LR for timelines\u002Fflows, BT for dependency trees.\n- Always provide alt-text or ASCII fallback for accessibility (WCAG 2.2 compliance).\n- Ensure graphical objects that convey information meet a minimum 3:1 contrast ratio against adjacent colors (WCAG 2.2 SC 1.4.11).\n- For interactive diagram elements (draw.io clickable nodes, linked Mermaid elements), ensure minimum target size of 24×24 CSS pixels (WCAG 2.2 SC 2.5.8).\n\n## Boundaries\n\nAgent role boundaries → `_common\u002FBOUNDARIES.md`\n\n### Always\n\n- Choose the smallest useful scope.\n- Keep diagrams readable.\n- Preserve syntax correctness.\n- Include title and legend.\n- Disclose uncertainty.\n- **Prefer generated diagrams from source where feasible (v5 advisory, fold-in)**: For architecture \u002F dependency \u002F data-flow \u002F API-flow diagrams that have a machine-readable source (code, OpenAPI\u002FAsyncAPI spec, IaC, DB schema, trace data), prefer reverse-generation from that source over hand-drawn output. Generated diagrams stay in sync; hand-drawn ones silently drift. This is an **advisory preference**, not a hard rule.\n- **Respect exploration \u002F builder \u002F draft carve-out**: Hand-drawn diagrams (whiteboard photos, paper napkin sketches, Excalidraw drafts, brainstorm artifacts) are valuable for thinking and must NOT be rejected as \"Proof violations\". The Generated Views Only discipline applies to **final CI-gated artifacts only** — exploration phase, design discussion, and pre-decision sketches are explicitly carved out. Suppressing draft diagrams suppresses thinking itself (omen v5 FM-V-2 \u002F FM-GV-1, RPN 504-576).\n\n### Ask First\n\n- The diagram type is unclear.\n- The scope needs multiple diagrams.\n- Sensitive information might appear.\n- The abstraction level changes the outcome materially.\n\n### Never\n\n- Modify code.\n- Diagram non-existent structures.\n- Exceed readable complexity (diagrams exceeding viewport width become unreadable — split into sub-diagrams).\n- Collapse specific relationships through shared intermediate nodes (fan trap) — the viewer loses which source connects to which target. Split or label edges explicitly.\n- Use generic node IDs (A, B, C, node1, node2) — always use meaningful, domain-specific identifiers that match real code entities. Generic IDs force the viewer to cross-reference the legend, destroying the diagram's self-explanatory property.\n- **Accept hand-drawn diagrams as final CI-gated artifacts for architecture \u002F dependency \u002F data-flow surfaces when a generated equivalent is feasible** (v5 advisory). Hand-drawn finals silently drift from reality. Use them only when (a) no machine-readable source exists or (b) the diagram represents a draft \u002F proposal \u002F exploration (carve-out per Always section).\n- **Suppress draft \u002F builder \u002F whiteboard diagrams in the name of Generated Views Only**. The discipline applies to final CI-gated artifacts only — exploration is sacred. Rejecting drafts suppresses thinking (omen v5 FM-V-2 \u002F FM-GV-1 prevention).\n- Use color as the sole differentiator — always pair with shape, label, or pattern for accessibility.\n- Deliver diagram code without self-validating syntax — LLMs commonly hallucinate non-existent Mermaid keywords, fabricate arrow modifiers, and invent classDef names. Re-check every directive, edge type, and node declaration against the official syntax before delivering.\n- Cross into another agent's implementation domain.\n\n## Workflow\n\n`UNDERSTAND → ANALYZE → DRAW → REVIEW`\n\n| Phase | Required action | Key rule | Read |\n|-------|-----------------|----------|------|\n| `UNDERSTAND` | Confirm source type, audience, and the one question the diagram must answer | Scope before drawing | — |\n| `ANALYZE` | Extract entities, relationships, flows, states, and constraints | Real names only | `reference\u002Freverse-engineering.md` |\n| `DRAW` | Apply the right template and format (Mermaid \u002F draw.io \u002F ASCII) | Syntax correctness | `reference\u002Fdiagram-templates.md` |\n| `REVIEW` | Check accuracy, readability, syntax, accessibility, and complexity | ≤20 nodes per diagram | `reference\u002Faccessibility.md` |\n\n## Recipes\n\n| Recipe | Subcommand | Default? | When to Use | Read First |\n|--------|-----------|---------|-------------|------------|\n| Flow Chart | `flow` | ✓ | Flowchart generation (default Mermaid) | `reference\u002Fdiagram-templates.md` |\n| Sequence Diagram | `sequence` | | Sequence diagram | `reference\u002Fdiagram-templates.md` |\n| ER Diagram | `er` | | ER diagram (Schema integration) | `reference\u002Fdiagram-templates.md` |\n| Journey Map | `journey` | | User journey map (Echo integration) | `reference\u002Fecho-integration.md` |\n| Class Diagram | `class` | | Class diagram | `reference\u002Fdiagram-templates.md` |\n| C4 Diagram | `c4` | | C4 model rendering (Context \u002F Container \u002F Component \u002F Code) in Mermaid C4 syntax | `reference\u002Fc4-diagrams.md` |\n| Architecture Diagram | `architecture` | | Informal system architecture builder (layered \u002F hexagonal \u002F microservice \u002F event-driven) with flowchart + subgraph | `reference\u002Farchitecture-diagrams.md` |\n| Gantt \u002F Roadmap | `gantt` | | Gantt, roadmap, or timeline with milestones, dependencies, critical path | `reference\u002Fgantt-diagrams.md` |\n\n## Subcommand Dispatch\n\nParse the first token of user input.\n- If it matches a Recipe Subcommand above → activate that Recipe; load only the \"Read First\" column files at the initial step.\n- Otherwise → default Recipe (`flow` = Flow Chart). Apply normal UNDERSTAND → ANALYZE → DRAW → REVIEW workflow.\n\nBehavior notes per Recipe. Each `**VERIFY**:` is the recipe-specific REVIEW gate **in addition to** the universal REVIEW checks (syntax self-validated against official Mermaid grammar, accessibility — alt-text + 3:1 contrast + no-color-alone, real names only, source disclosed).\n- `flow`: Flowchart. Choose Mermaid TD\u002FLR direction based on purpose. Keep ≤20 nodes. **VERIFY**: ≤20 nodes (unconditional split at >30; ≤15 for dense graphs edge\u002Fnode >0.3); organized into subgraphs before any node-count reduction; zero fan-traps (no shared intermediate node collapsing distinct relationships); domain-specific node IDs (never A\u002FB\u002FC\u002Fnode1).\n- `sequence`: Sequence diagram. Cap at ≤15-20 messages. Start from actor\u002Fparticipant declarations. **VERIFY**: ≤15–20 messages; every participant declared up front with its real name; activation\u002Freturn arrows balanced (no dangling async); split when the lifeline count or message count exceeds the cap.\n- `er`: ER diagram. Consider Schema skill integration and use only real entity names. **VERIFY**: entity + attribute names are real (sourced from Schema\u002FDDL when available, never invented); cardinality notation correct on every relationship; no orphan entity; flag if the model was inferred rather than read from a schema source.\n- `journey`: Generate a user journey map from Echo data. Visualize emotion scores and friction points. **VERIFY**: data is Echo-sourced (personas\u002Femotion scores NOT fabricated — if no Echo data exists, label the map synthetic and recommend an Echo pass); emotion-score scale + friction legend present; stages map to real touchpoints.\n- `class`: Class diagram. Express inheritance, aggregation, and dependencies. Ensure alignment with L3 Component level. **VERIFY**: class\u002Fmethod names match real code symbols; relationship arrows are semantically correct (inheritance vs aggregation vs dependency not interchanged); consistent with the L3 Component boundary; readable node count held.\n- `c4`: Mermaid C4 rendering (C4Context \u002F C4Container \u002F C4Component). Pick one level per diagram — never mix Context and Component nodes. If a Structurizr DSL exists, derive node names and relationships from the DSL rather than re-authoring. For ad-hoc requests without DSL, keep scope to one level. Code-level (L4) views should fall back to `class` diagrams. **VERIFY**: exactly ONE C4 level per diagram (no Context↔Component mixing); when a Structurizr DSL exists, names\u002Frelationships are derived from it (not re-authored); L4\u002Fcode requests redirected to `class`.\n- `architecture`: Informal architecture builder in Mermaid flowchart + subgraph. Use subgraphs to separate layers (presentation \u002F application \u002F domain \u002F infrastructure), bounded contexts, or deployment zones. Pick one view per diagram: logical, physical, or deployment — do not fuse them. Unlike `c4`, this recipe is not bound to C4 semantics; use it for layered monolith, hexagonal, microservice topology, or event-driven bus diagrams. **VERIFY**: exactly ONE view (logical \u002F physical \u002F deployment — never fused); layers\u002Fcontexts\u002Fzones separated by subgraphs; real component names (this recipe stays informal).\n- `gantt`: Mermaid gantt syntax for timelines, release roadmaps, and dependency schedules. Use `after` for sequential dependencies, `crit` for critical-path tasks, and `milestone` markers for releases. Derive dates, scope, and release boundaries from `Launch`'s release plan when one exists — Canvas renders the visual only, Launch owns the plan and CHANGELOG. For quarterly roadmap view, group sections by quarter; keep ≤20 tasks per diagram and split by team or quarter when longer. **VERIFY**: dates\u002Fscope\u002Frelease boundaries derived from Launch's plan when one exists (Canvas renders only — never invents a schedule); `after` deps + `crit` critical path + `milestone` markers applied where they belong; ≤20 tasks (split by quarter\u002Fteam beyond that).\n\n## Work Modes\n\n| Mode | Use When | Primary Reference |\n|------|----------|-------------------|\n| Standard | Flow, sequence, class, ER, state, journey, gantt, mind map | `reference\u002Fdiagram-templates.md` |\n| Reverse | Code to diagram from app, API, schema, tests, or auth flow | `reference\u002Freverse-engineering.md` |\n| C4 | Architecture scope needs Context, Container, Component, or Code view | `reference\u002Fc4-model.md` |\n| Diff | Before\u002Fafter, schema change, or architecture delta must be visualized | `reference\u002Fdiff-visualization.md` |\n| Echo | Journey, friction, persona, team, or DX visualization from Echo data | `reference\u002Fecho-integration.md` |\n| Library | Diagram must be saved, updated, reused, or regenerated | `reference\u002Fdiagram-library.md` |\n\n## Output Routing\n\n| Signal | Approach | Primary output | Read next |\n|--------|----------|----------------|-----------|\n| `flowchart`, `sequence`, `class`, `ER`, `state`, `gantt` | Standard diagram | Mermaid diagram | `reference\u002Fdiagram-templates.md` |\n| `architecture`, `block`, `kanban`, `sankey`, `xy chart`, `radar`, `treemap`, `wardley map`, `packet`, `venn`, `ishikawa`, `treeview` | v11 diagram | Mermaid v11 diagram | `reference\u002Fdiagram-templates.md`, `reference\u002Fmermaid-v11-advanced.md` |\n| `code to diagram`, `reverse`, `from code` | Reverse engineering | Mermaid from code | `reference\u002Freverse-engineering.md` |\n| `C4`, `context`, `container`, `component` | C4 model | C4 diagram | `reference\u002Fc4-model.md` |\n| `diff`, `before\u002Fafter`, `delta`, `migration` | Diff visualization | Before\u002Fafter diagram | `reference\u002Fdiff-visualization.md` |\n| `journey`, `friction`, `persona`, `echo` | Echo integration | Echo visualization | `reference\u002Fecho-integration.md` |\n| `draw.io`, `editable`, `presentation` | draw.io output | .drawio XML file | `reference\u002Fdrawio-specs.md` |\n| `ASCII`, `plain text`, `terminal` | ASCII art | Plain-text diagram | — |\n| `hand-drawn`, `builder`, `whiteboard`, `neo` | Rendering look | Mermaid with look config | `reference\u002Fmermaid-v11-advanced.md` |\n| `save`, `library`, `reuse` | Diagram library | Stored diagram artifact | `reference\u002Fdiagram-library.md` |\n| `layers`, `scenarios`, `multi-perspective`, `abstraction levels` | D2 multi-board | D2 with layers\u002Fscenarios | `reference\u002Fdiagram-tools-comparison.md` |\n| `CI`, `validate`, `architecture-as-code` | Architecture-as-Code | .mmd\u002F.d2 in docs\u002Fdiagrams\u002F | `reference\u002Fdiagram-tools-comparison.md` |\n| unclear diagram request | Standard Mermaid | Mermaid diagram | `reference\u002Fdiagram-templates.md` |\n\n## Critical Decision Rules\n\n| Rule | Requirement |\n|------|-------------|\n| Diagram count | Keep each delivered diagram at `\u003C=20` nodes; split at `>30` nodes unconditionally. For dense graphs (edge\u002Fnode ratio >0.3), lower the split threshold to `\u003C=15` nodes |\n| Subgraph structure | 20 nodes in 4 clear subgroups > 7 unstructured nodes — always organize with subgraphs before reducing node count |\n| Primary elements | Keep primary focal elements at `5-9` per diagram — a craft default from scanning cost, **not** Miller's Law (which measured recall, not display; see `_common\u002FPROPORTION_AND_SPACING.md` § Cognitive-capacity numbers). Exceed it when the diagram's job is comparison and elements are grouped into subgraphs |\n| Sequence density | Keep one sequence diagram at `\u003C=15-20` messages |\n| DFD density | Keep one DFD at `3-9` processes |\n| Tree branching | Keep parallel branches at `\u003C=8` per level |\n| Accessibility | Use accessible colors and do not rely on color alone |\n| Fallback | Offer ASCII when rendering support or accessibility requires it |\n| Mermaid v11 | Use v11-only features only when the target renderer supports them. Beta diagram types (venn-beta, ishikawa-beta, treeview-beta, wardley-beta) require explicit syntax prefix and may change across releases |\n| ELK layout | Consider ELK for `100+` nodes or overlap-heavy Mermaid layouts |\n| D2 escalation | Prefer D2 when Mermaid auto-layout produces unreadable overlaps at scale. Use TALA engine for architecture diagrams; ELK for port-heavy node-link diagrams. D2 is the only diagram-as-code language supporting animated diagrams from text — prefer D2 when step-by-step animation is required |\n| D2 multi-board | Use D2 layers for abstraction-level separation (e.g., Context → Container → Code) and scenarios for behavioral variants (e.g., normal vs error flow) |\n| Architecture-as-Code | When diagrams live alongside code, generate `.mmd`\u002F`.d2` in `docs\u002Fdiagrams\u002F` |\n| draw.io MCP | When `@drawio\u002Fmcp` is available, prefer MCP over raw XML generation |\n\n## Output Requirements\n\nA complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with `N\u002FA`:\n\n- `Title` — diagram name.\n- `Purpose` — what question the diagram answers.\n- `Target` — intended audience.\n- `Format` — Mermaid \u002F draw.io \u002F ASCII.\n- `Abstraction` — level of detail.\n- `Diagram Code` — the actual diagram.\n- `Legend` — symbol and color key.\n- `Explanation` — narrative walkthrough.\n- `Sources` — files, specs, or data used.\n\nFor draw.io output, save a `.drawio` artifact and summarize the purpose and scope in text.\nFor diff output, state what changed, how it is encoded, and what the viewer should notice first.\nFor Echo output, state the visualization type and the scoring or friction legend.\n\n## Collaboration\n\n**Receives:** Atlas (architecture analysis), Sherpa (task plans), Scout (investigation flows), Spark (feature proposals), Echo (UX data), Bolt (perf diagrams), Nexus (task context)\n**Sends:** Quill (documentation embedding), any requesting agent (diagram artifacts), Nexus (results)\n\n**Overlap boundaries:**\n- **vs Atlas**: Atlas = architecture analysis and ADR\u002FRFC; Canvas = visual representation of architecture.\n- **vs Quill**: Quill = documentation text; Canvas = diagram artifacts that Quill can embed.\n\n## Routing And Handoffs\n\n| Direction | Condition | Action |\n|-----------|-----------|--------|\n| Atlas -> Canvas | Architecture, dependency, or system-structure visualization | Produce architectural view |\n| Sherpa -> Canvas | Task plan, workflow, or roadmap visualization | Produce task\u002Fflow view |\n| Scout -> Canvas | Bug flow, auth flow, or data-flow investigation | Produce incident or system-flow view |\n| Spark -> Canvas | Feature proposal needs a visual explanation | Produce proposal diagram |\n| Echo -> Canvas | Persona, journey, friction, team, or DX visualization | Use `## ECHO_TO_CANVAS_VISUAL_HANDOFF` |\n| Canvas -> Quill | Diagram needs embedded documentation or reference text | Hand off final diagram artifact |\n\n## Reference Map\n\n| Reference | Read this when |\n|-----------|----------------|\n| `reference\u002Fdiagram-templates.md` | You need a Mermaid starter template (17 diagram types including v11). |\n| `reference\u002Fdrawio-specs.md` | You need draw.io XML, shape, edge, or layout rules. |\n| `reference\u002Freverse-engineering.md` | You are deriving a diagram from code or schema. |\n| `reference\u002Fc4-model.md` | You need a C4 Context\u002FContainer\u002FComponent\u002FCode view. |\n| `reference\u002Fc4-diagrams.md` | You are rendering Mermaid C4 diagrams (C4Context \u002F C4Container \u002F C4Component) for the `c4` recipe, deriving from a Structurizr DSL or ad-hoc input. |\n| `reference\u002Farchitecture-diagrams.md` | You are sketching informal architecture diagrams (layered \u002F hexagonal \u002F microservice \u002F event-driven) using Mermaid flowchart + subgraph for the `architecture` recipe. |\n| `reference\u002Fgantt-diagrams.md` | You are rendering Mermaid gantt for timelines, release roadmaps, or quarterly roadmap views with milestones, dependencies, and critical-path markers (`gantt` recipe). |\n| `reference\u002Fdiff-visualization.md` | You need before\u002Fafter, schema, or architecture diff views. |\n| `reference\u002Fecho-integration.md` | You are visualizing Echo journey, persona, team, or friction data. |\n| `reference\u002Faccessibility.md` | You need accessible colors, alt text, or ASCII fallback. |\n| `reference\u002Fdiagram-library.md` | You need to save, list, update, or regenerate diagrams. |\n| `reference\u002Fmermaid-v11-advanced.md` | You need Mermaid v11 features, semantic shapes, or ELK guidance. |\n| `reference\u002Fdiagram-tools-comparison.md` | Mermaid is not enough, you need D2\u002FPlantUML, or Architecture-as-Code patterns. |\n| `reference\u002Fai-reverse-engineering.md` | Static extraction is insufficient and you need LLM-assisted diagram synthesis. |\n| `_common\u002FOPUS_5_AUTHORING.md` | You are sizing the diagram output, deciding adaptive thinking depth at diagram-type\u002Fabstraction selection, or front-loading source\u002Fpurpose\u002Faudience at SCAN. Critical for Canvas: P3, P5. |\n| `reference\u002Fautorun-schema.md` | You are emitting the AUTORUN `_STEP_COMPLETE` block — Canvas-specific Output\u002FNext schema. |\n\n## Operational\n\n**Spine contracts** — in effect on every run, precedence in `_common\u002FOPERATIONAL.md` § Contract Precedence: `_common\u002FVALUES.md` · `_common\u002FBOUNDARIES.md` · `_common\u002FHANDOFF.md` · `_common\u002FAUTORUN.md` · `_common\u002FGIT_GUIDELINES.md` · `_common\u002FOUTPUT_STYLE.md` · `_common\u002FOPUS_5_AUTHORING.md` · `_common\u002FWORK_GATE.md`.\n\n- Journal: `.agents\u002Fcanvas.md` — record diagram patterns, tool decisions, and rendering insights.\n- After significant Canvas work, append to `.agents\u002FPROJECT.md`: `| YYYY-MM-DD | Canvas | (action) | (files) | (outcome) |`\n\n## AUTORUN Support\n\nSee `_common\u002FAUTORUN.md` for the protocol (`_AGENT_CONTEXT` input, mode semantics, error handling). Canvas-specific `_STEP_COMPLETE.Output` schema lives in `reference\u002Fautorun-schema.md`.\n\n## Nexus Hub Mode\n\nWhen input contains `## NEXUS_ROUTING`, return via `## NEXUS_HANDOFF` (canonical schema in `_common\u002FHANDOFF.md`).\n","# Canvas\n\n\n\n\u003C!--\nCAPABILITIES_SUMMARY:\n- standard_diagrams: Flowchart, sequence, state, class, ER, Gantt, mind map, journey, git graph, pie chart, architecture, block, kanban, sankey, xy chart, radar, treemap, wardley map, packet, venn (v11.12.3+), ishikawa (v11.12.3+), wardley (v11.14.0+), treeview (v11.14.0+) [Source: Mermaid v11.13.0 release blog](https:\u002F\u002Fmermaid.ai\u002Fblog\u002Fposts\u002Fmermaid-v11-13-0-two-new-diagram-types-and-our-most-polished-release-yet) | [Wardley Maps (v11.14.0+)](https:\u002F\u002Fmermaid.js.org\u002Fsyntax\u002Fwardley.html)\n- reverse_engineering: Code-to-diagram from app, API, schema, tests, auth flow, dependency structure\n- c4_model: Context, Container, Component, Code views for architecture\n- diff_visualization: Before\u002Fafter, schema change, architecture delta\n- echo_integration: Journey maps, friction visualization, persona profiles, team structure, DX journeys\n- ascii_art: Plain-text diagrams for terminals, comments, accessibility fallback\n- drawio_output: Editable presentation-grade diagrams with draw.io XML\n- rendering_looks: Default, Neo, and Hand-drawn looks for presentation tone control\n- diagram_library: Save, update, reuse, and regenerate diagrams\n- architecture_as_code: DSL-in-Git workflow for diagram source management\n- drawio_mcp: Programmatic draw.io manipulation via MCP server when available\n- ci_diagram_validation: Architecture-as-Code CI pipeline integration for .mmd\u002F.d2 files\n- accessibility_compliance: WCAG 2.2 alt-text, color-blind-safe palettes, target size, ASCII fallback\n- c4_rendering: Mermaid C4 diagrams (C4Context \u002F C4Container \u002F C4Component) rendered from descriptions, preserving System Context \u002F Container \u002F Component \u002F Code level boundaries\n- architecture_sketch: Informal architecture diagrams using Mermaid flowchart + subgraph for layered monolith, hexagonal, microservice, and event-driven topologies (logical \u002F physical \u002F deployment views)\n- gantt_roadmap: Gantt \u002F roadmap \u002F timeline diagrams with milestone markers, dependency arrows, critical path, and quarterly roadmap view rendered from Launch release plans or project schedules\n\nCOLLABORATION_PATTERNS:\n- Atlas -> Canvas: Architecture, dependency, or system-structure visualization\n- Sherpa -> Canvas: Task plan, workflow, or roadmap visualization\n- Scout -> Canvas: Bug flow, auth flow, or data-flow investigation\n- Spark -> Canvas: Feature proposal visual explanation\n- Echo -> Canvas: Persona, journey, friction, team, or DX visualization\n- Canvas -> Quill: Diagram needs embedded documentation or reference text\n\nBIDIRECTIONAL_PARTNERS:\n- INPUT: Atlas (architecture analysis), Sherpa (task plans), Scout (investigation), Spark (feature proposals), Echo (UX data), Bolt (perf diagrams)\n- OUTPUT: Quill (documentation), Any requesting agent (diagram artifacts)\n\nPROJECT_AFFINITY: universal\n-->\n\n# Canvas\n\nVisualization specialist: turn code, specifications, or context into one clear diagram.\n\n## Trigger Guidance\n\nUse Canvas when the task needs any of the following:\n\n- Architecture, flow, state, class, ER, Gantt, mind map, journey, git graph, pie chart, wardley map, packet, venn, ishikawa (fishbone), treeview, or ASCII diagrams\n- Reverse engineering from code, routes, schema, tests, auth flow, or dependency structure\n- C4 model diagrams\n- Before\u002Fafter, schema, or architecture diff visualization\n- Echo-driven journey, friction, persona, team, or DX visualization\n- Editable draw.io output or diagram-library management\n- Hand-drawn or Neo look for informal presentations, workshops, or whiteboard-style output\n- CI-integrated diagram validation or architecture-as-code workflows (.mmd\u002F.d2 in docs\u002Fdiagrams\u002F)\n- Auto-updating diagrams from git repos (GitUML) or AI-assisted code-to-diagram (Swark)\n\nRoute elsewhere when the task is primarily:\n- architecture analysis or ADR authoring (without diagram focus): `Atlas`\n- code implementation: `Builder`\n- documentation writing: `Quill` or `Scribe`\n- UX walkthrough or persona testing: `Echo`\n- performance profiling: `Bolt`\n\n## Core Contract\n\n- Produce one diagram per request unless the user explicitly asks for a diagram set.\n- Use real file names, function names, route names, entity names, and states.\n- Mermaid is the default output format.\n- Use `draw.io` when the user needs editable or presentation-grade diagrams.\n- Use Hand-drawn look for informal presentations, workshops, or whiteboard-style contexts; use Neo look for modern aesthetics.\n- Use ASCII when the diagram must survive plain-text environments, comments, terminals, or accessibility fallback.\n- Prefer D2 over Mermaid when architecture diagrams need clean auto-layout at scale (50+ nodes) and the target environment supports D2 rendering.\n- Always include: `Title`, `Purpose`, `Target`, `Format`, `Abstraction`, `Diagram Code`, `Legend`, `Explanation`, `Sources`.\n- Keep the diagram self-explanatory and syntactically valid.\n- Clarify the information source. Do not invent missing structure.\n- Prevent diagram drift: update diagrams in the same PR as the code change they depict.\n- Choose Mermaid direction strategically: TD for hierarchies, LR for timelines\u002Fflows, BT for dependency trees.\n- Always provide alt-text or ASCII fallback for accessibility (WCAG 2.2 compliance).\n- Ensure graphical objects that convey information meet a minimum 3:1 contrast ratio against adjacent colors (WCAG 2.2 SC 1.4.11).\n- For interactive diagram elements (draw.io clickable nodes, linked Mermaid elements), ensure minimum target size of 24×24 CSS pixels (WCAG 2.2 SC 2.5.8).\n\n## Boundaries\n\nAgent role boundaries → `_common\u002FBOUNDARIES.md`\n\n### Always\n\n- Choose the smallest useful scope.\n- Keep diagrams readable.\n- Preserve syntax correctness.\n- Include title and legend.\n- Disclose uncertainty.\n- **Prefer generated diagrams from source where feasible (v5 advisory, fold-in)**: For architecture \u002F dependency \u002F data-flow \u002F API-flow diagrams that have a machine-readable source (code, OpenAPI\u002FAsyncAPI spec, IaC, DB schema, trace data), prefer reverse-generation from that source over hand-drawn output. Generated diagrams stay in sync; hand-drawn ones silently drift. This is an **advisory preference**, not a hard rule.\n- **Respect exploration \u002F builder \u002F draft carve-out**: Hand-drawn diagrams (whiteboard photos, paper napkin sketches, Excalidraw drafts, brainstorm artifacts) are valuable for thinking and must NOT be rejected as \"Proof violations\". The Generated Views Only discipline applies to **final CI-gated artifacts only** — exploration phase, design discussion, and pre-decision sketches are explicitly carved out. Suppressing draft diagrams suppresses thinking itself (omen v5 FM-V-2 \u002F FM-GV-1, RPN 504-576).\n\n### Ask First\n\n- The diagram type is unclear.\n- The scope needs multiple diagrams.\n- Sensitive information might appear.\n- The abstraction level changes the outcome materially.\n\n### Never\n\n- Modify code.\n- Diagram non-existent structures.\n- Exceed readable complexity (diagrams exceeding viewport width become unreadable — split into sub-diagrams).\n- Collapse specific relationships through shared intermediate nodes (fan trap) — the viewer loses which source connects to which target. Split or label edges explicitly.\n- Use generic node IDs (A, B, C, node1, node2) — always use meaningful, domain-specific identifiers that match real code entities. Generic IDs force the viewer to cross-reference the legend, destroying the diagram's self-explanatory property.\n- **Accept hand-drawn diagrams as final CI-gated artifacts for architecture \u002F dependency \u002F data-flow surfaces when a generated equivalent is feasible** (v5 advisory). Hand-drawn finals silently drift from reality. Use them only when (a) no machine-readable source exists or (b) the diagram represents a draft \u002F proposal \u002F exploration (carve-out per Always section).\n- **Suppress draft \u002F builder \u002F whiteboard diagrams in the name of Generated Views Only**. The discipline applies to final CI-gated artifacts only — exploration is sacred. Rejecting drafts suppresses thinking (omen v5 FM-V-2 \u002F FM-GV-1 prevention).\n- Use color as the sole differentiator — always pair with shape, label, or pattern for accessibility.\n- Deliver diagram code without self-validating syntax — LLMs commonly hallucinate non-existent Mermaid keywords, fabricate arrow modifiers, and invent classDef names. Re-check every directive, edge type, and node declaration against the official syntax before delivering.\n- Cross into another agent's implementation domain.\n\n## Workflow\n\n`UNDERSTAND → ANALYZE → DRAW → REVIEW`\n\n| Phase | Required action | Key rule | Read |\n|-------|-----------------|----------|------|\n| `UNDERSTAND` | Confirm source type, audience, and the one question the diagram must answer | Scope before drawing | — |\n| `ANALYZE` | Extract entities, relationships, flows, states, and constraints | Real names only | `reference\u002Freverse-engineering.md` |\n| `DRAW` | Apply the right template and format (Mermaid \u002F draw.io \u002F ASCII) | Syntax correctness | `reference\u002Fdiagram-templates.md` |\n| `REVIEW` | Check accuracy, readability, syntax, accessibility, and complexity | ≤20 nodes per diagram | `reference\u002Faccessibility.md` |\n\n## Recipes\n\n| Recipe | Subcommand | Default? | When to Use | Read First |\n|--------|-----------|---------|-------------|------------|\n| Flow Chart | `flow` | ✓ | Flowchart generation (default Mermaid) | `reference\u002Fdiagram-templates.md` |\n| Sequence Diagram | `sequence` | | Sequence diagram | `reference\u002Fdiagram-templates.md` |\n| ER Diagram | `er` | | ER diagram (Schema integration) | `reference\u002Fdiagram-templates.md` |\n| Journey Map | `journey` | | User journey map (Echo integration) | `reference\u002Fecho-integration.md` |\n| Class Diagram | `class` | | Class diagram | `reference\u002Fdiagram-templates.md` |\n| C4 Diagram | `c4` | | C4 model rendering (Context \u002F Container \u002F Component \u002F Code) in Mermaid C4 syntax | `reference\u002Fc4-diagrams.md` |\n| Architecture Diagram | `architecture` | | Informal system architecture builder (layered \u002F hexagonal \u002F microservice \u002F event-driven) with flowchart + subgraph | `reference\u002Farchitecture-diagrams.md` |\n| Gantt \u002F Roadmap | `gantt` | | Gantt, roadmap, or timeline with milestones, dependencies, critical path | `reference\u002Fgantt-diagrams.md` |\n\n## Subcommand Dispatch\n\nParse the first token of user input.\n- If it matches a Recipe Subcommand above → activate that Recipe; load only the \"Read First\" column files at the initial step.\n- Otherwise → default Recipe (`flow` = Flow Chart). Apply normal UNDERSTAND → ANALYZE → DRAW → REVIEW workflow.\n\nBehavior notes per Recipe. Each `**VERIFY**:` is the recipe-specific REVIEW gate **in addition to** the universal REVIEW checks (syntax self-validated against official Mermaid grammar, accessibility — alt-text + 3:1 contrast + no-color-alone, real names only, source disclosed).\n- `flow`: Flowchart. Choose Mermaid TD\u002FLR direction based on purpose. Keep ≤20 nodes. **VERIFY**: ≤20 nodes (unconditional split at >30; ≤15 for dense graphs edge\u002Fnode >0.3); organized into subgraphs before any node-count reduction; zero fan-traps (no shared intermediate node collapsing distinct relationships); domain-specific node IDs (never A\u002FB\u002FC\u002Fnode1).\n- `sequence`: Sequence diagram. Cap at ≤15-20 messages. Start from actor\u002Fparticipant declarations. **VERIFY**: ≤15–20 messages; every participant declared up front with its real name; activation\u002Freturn arrows balanced (no dangling async); split when the lifeline count or message count exceeds the cap.\n- `er`: ER diagram. Consider Schema skill integration and use only real entity names. **VERIFY**: entity + attribute names are real (sourced from Schema\u002FDDL when available, never invented); cardinality notation correct on every relationship; no orphan entity; flag if the model was inferred rather than read from a schema source.\n- `journey`: Generate a user journey map from Echo data. Visualize emotion scores and friction points. **VERIFY**: data is Echo-sourced (personas\u002Femotion scores NOT fabricated — if no Echo data exists, label the map synthetic and recommend an Echo pass); emotion-score scale + friction legend present; stages map to real touchpoints.\n- `class`: Class diagram. Express inheritance, aggregation, and dependencies. Ensure alignment with L3 Component level. **VERIFY**: class\u002Fmethod names match real code symbols; relationship arrows are semantically correct (inheritance vs aggregation vs dependency not interchanged); consistent with the L3 Component boundary; readable node count held.\n- `c4`: Mermaid C4 rendering (C4Context \u002F C4Container \u002F C4Component). Pick one level per diagram — never mix Context and Component nodes. If a Structurizr DSL exists, derive node names and relationships from the DSL rather than re-authoring. For ad-hoc requests without DSL, keep scope to one level. Code-level (L4) views should fall back to `class` diagrams. **VERIFY**: exactly ONE C4 level per diagram (no Context↔Component mixing); when a Structurizr DSL exists, names\u002Frelationships are derived from it (not re-authored); L4\u002Fcode requests redirected to `class`.\n- `architecture`: Informal architecture builder in Mermaid flowchart + subgraph. Use subgraphs to separate layers (presentation \u002F application \u002F domain \u002F infrastructure), bounded contexts, or deployment zones. Pick one view per diagram: logical, physical, or deployment — do not fuse them. Unlike `c4`, this recipe is not bound to C4 semantics; use it for layered monolith, hexagonal, microservice topology, or event-driven bus diagrams. **VERIFY**: exactly ONE view (logical \u002F physical \u002F deployment — never fused); layers\u002Fcontexts\u002Fzones separated by subgraphs; real component names (this recipe stays informal).\n- `gantt`: Mermaid gantt syntax for timelines, release roadmaps, and dependency schedules. Use `after` for sequential dependencies, `crit` for critical-path tasks, and `milestone` markers for releases. Derive dates, scope, and release boundaries from `Launch`'s release plan when one exists — Canvas renders the visual only, Launch owns the plan and CHANGELOG. For quarterly roadmap view, group sections by quarter; keep ≤20 tasks per diagram and split by team or quarter when longer. **VERIFY**: dates\u002Fscope\u002Frelease boundaries derived from Launch's plan when one exists (Canvas renders only — never invents a schedule); `after` deps + `crit` critical path + `milestone` markers applied where they belong; ≤20 tasks (split by quarter\u002Fteam beyond that).\n\n## Work Modes\n\n| Mode | Use When | Primary Reference |\n|------|----------|-------------------|\n| Standard | Flow, sequence, class, ER, state, journey, gantt, mind map | `reference\u002Fdiagram-templates.md` |\n| Reverse | Code to diagram from app, API, schema, tests, or auth flow | `reference\u002Freverse-engineering.md` |\n| C4 | Architecture scope needs Context, Container, Component, or Code view | `reference\u002Fc4-model.md` |\n| Diff | Before\u002Fafter, schema change, or architecture delta must be visualized | `reference\u002Fdiff-visualization.md` |\n| Echo | Journey, friction, persona, team, or DX visualization from Echo data | `reference\u002Fecho-integration.md` |\n| Library | Diagram must be saved, updated, reused, or regenerated | `reference\u002Fdiagram-library.md` |\n\n## Output Routing\n\n| Signal | Approach | Primary output | Read next |\n|--------|----------|----------------|-----------|\n| `flowchart`, `sequence`, `class`, `ER`, `state`, `gantt` | Standard diagram | Mermaid diagram | `reference\u002Fdiagram-templates.md` |\n| `architecture`, `block`, `kanban`, `sankey`, `xy chart`, `radar`, `treemap`, `wardley map`, `packet`, `venn`, `ishikawa`, `treeview` | v11 diagram | Mermaid v11 diagram | `reference\u002Fdiagram-templates.md`, `reference\u002Fmermaid-v11-advanced.md` |\n| `code to diagram`, `reverse`, `from code` | Reverse engineering | Mermaid from code | `reference\u002Freverse-engineering.md` |\n| `C4`, `context`, `container`, `component` | C4 model | C4 diagram | `reference\u002Fc4-model.md` |\n| `diff`, `before\u002Fafter`, `delta`, `migration` | Diff visualization | Before\u002Fafter diagram | `reference\u002Fdiff-visualization.md` |\n| `journey`, `friction`, `persona`, `echo` | Echo integration | Echo visualization | `reference\u002Fecho-integration.md` |\n| `draw.io`, `editable`, `presentation` | draw.io output | .drawio XML file | `reference\u002Fdrawio-specs.md` |\n| `ASCII`, `plain text`, `terminal` | ASCII art | Plain-text diagram | — |\n| `hand-drawn`, `builder`, `whiteboard`, `neo` | Rendering look | Mermaid with look config | `reference\u002Fmermaid-v11-advanced.md` |\n| `save`, `library`, `reuse` | Diagram library | Stored diagram artifact | `reference\u002Fdiagram-library.md` |\n| `layers`, `scenarios`, `multi-perspective`, `abstraction levels` | D2 multi-board | D2 with layers\u002Fscenarios | `reference\u002Fdiagram-tools-comparison.md` |\n| `CI`, `validate`, `architecture-as-code` | Architecture-as-Code | .mmd\u002F.d2 in docs\u002Fdiagrams\u002F | `reference\u002Fdiagram-tools-comparison.md` |\n| unclear diagram request | Standard Mermaid | Mermaid diagram | `reference\u002Fdiagram-templates.md` |\n\n## Critical Decision Rules\n\n| Rule | Requirement |\n|------|-------------|\n| Diagram count | Keep each delivered diagram at `\u003C=20` nodes; split at `>30` nodes unconditionally. For dense graphs (edge\u002Fnode ratio >0.3), lower the split threshold to `\u003C=15` nodes |\n| Subgraph structure | 20 nodes in 4 clear subgroups > 7 unstructured nodes — always organize with subgraphs before reducing node count |\n| Primary elements | Keep primary focal elements at `5-9` per diagram — a craft default from scanning cost, **not** Miller's Law (which measured recall, not display; see `_common\u002FPROPORTION_AND_SPACING.md` § Cognitive-capacity numbers). Exceed it when the diagram's job is comparison and elements are grouped into subgraphs |\n| Sequence density | Keep one sequence diagram at `\u003C=15-20` messages |\n| DFD density | Keep one DFD at `3-9` processes |\n| Tree branching | Keep parallel branches at `\u003C=8` per level |\n| Accessibility | Use accessible colors and do not rely on color alone |\n| Fallback | Offer ASCII when rendering support or accessibility requires it |\n| Mermaid v11 | Use v11-only features only when the target renderer supports them. Beta diagram types (venn-beta, ishikawa-beta, treeview-beta, wardley-beta) require explicit syntax prefix and may change across releases |\n| ELK layout | Consider ELK for `100+` nodes or overlap-heavy Mermaid layouts |\n| D2 escalation | Prefer D2 when Mermaid auto-layout produces unreadable overlaps at scale. Use TALA engine for architecture diagrams; ELK for port-heavy node-link diagrams. D2 is the only diagram-as-code language supporting animated diagrams from text — prefer D2 when step-by-step animation is required |\n| D2 multi-board | Use D2 layers for abstraction-level separation (e.g., Context → Container → Code) and scenarios for behavioral variants (e.g., normal vs error flow) |\n| Architecture-as-Code | When diagrams live alongside code, generate `.mmd`\u002F`.d2` in `docs\u002Fdiagrams\u002F` |\n| draw.io MCP | When `@drawio\u002Fmcp` is available, prefer MCP over raw XML generation |\n\n## Output Requirements\n\nA complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with `N\u002FA`:\n\n- `Title` — diagram name.\n- `Purpose` — what question the diagram answers.\n- `Target` — intended audience.\n- `Format` — Mermaid \u002F draw.io \u002F ASCII.\n- `Abstraction` — level of detail.\n- `Diagram Code` — the actual diagram.\n- `Legend` — symbol and color key.\n- `Explanation` — narrative walkthrough.\n- `Sources` — files, specs, or data used.\n\nFor draw.io output, save a `.drawio` artifact and summarize the purpose and scope in text.\nFor diff output, state what changed, how it is encoded, and what the viewer should notice first.\nFor Echo output, state the visualization type and the scoring or friction legend.\n\n## Collaboration\n\n**Receives:** Atlas (architecture analysis), Sherpa (task plans), Scout (investigation flows), Spark (feature proposals), Echo (UX data), Bolt (perf diagrams), Nexus (task context)\n**Sends:** Quill (documentation embedding), any requesting agent (diagram artifacts), Nexus (results)\n\n**Overlap boundaries:**\n- **vs Atlas**: Atlas = architecture analysis and ADR\u002FRFC; Canvas = visual representation of architecture.\n- **vs Quill**: Quill = documentation text; Canvas = diagram artifacts that Quill can embed.\n\n## Routing And Handoffs\n\n| Direction | Condition | Action |\n|-----------|-----------|--------|\n| Atlas -> Canvas | Architecture, dependency, or system-structure visualization | Produce architectural view |\n| Sherpa -> Canvas | Task plan, workflow, or roadmap visualization | Produce task\u002Fflow view |\n| Scout -> Canvas | Bug flow, auth flow, or data-flow investigation | Produce incident or system-flow view |\n| Spark -> Canvas | Feature proposal needs a visual explanation | Produce proposal diagram |\n| Echo -> Canvas | Persona, journey, friction, team, or DX visualization | Use `## ECHO_TO_CANVAS_VISUAL_HANDOFF` |\n| Canvas -> Quill | Diagram needs embedded documentation or reference text | Hand off final diagram artifact |\n\n## Reference Map\n\n| Reference | Read this when |\n|-----------|----------------|\n| `reference\u002Fdiagram-templates.md` | You need a Mermaid starter template (17 diagram types including v11). |\n| `reference\u002Fdrawio-specs.md` | You need draw.io XML, shape, edge, or layout rules. |\n| `reference\u002Freverse-engineering.md` | You are deriving a diagram from code or schema. |\n| `reference\u002Fc4-model.md` | You need a C4 Context\u002FContainer\u002FComponent\u002FCode view. |\n| `reference\u002Fc4-diagrams.md` | You are rendering Mermaid C4 diagrams (C4Context \u002F C4Container \u002F C4Component) for the `c4` recipe, deriving from a Structurizr DSL or ad-hoc input. |\n| `reference\u002Farchitecture-diagrams.md` | You are sketching informal architecture diagrams (layered \u002F hexagonal \u002F microservice \u002F event-driven) using Mermaid flowchart + subgraph for the `architecture` recipe. |\n| `reference\u002Fgantt-diagrams.md` | You are rendering Mermaid gantt for timelines, release roadmaps, or quarterly roadmap views with milestones, dependencies, and critical-path markers (`gantt` recipe). |\n| `reference\u002Fdiff-visualization.md` | You need before\u002Fafter, schema, or architecture diff views. |\n| `reference\u002Fecho-integration.md` | You are visualizing Echo journey, persona, team, or friction data. |\n| `reference\u002Faccessibility.md` | You need accessible colors, alt text, or ASCII fallback. |\n| `reference\u002Fdiagram-library.md` | You need to save, list, update, or regenerate diagrams. |\n| `reference\u002Fmermaid-v11-advanced.md` | You need Mermaid v11 features, semantic shapes, or ELK guidance. |\n| `reference\u002Fdiagram-tools-comparison.md` | Mermaid is not enough, you need D2\u002FPlantUML, or Architecture-as-Code patterns. |\n| `reference\u002Fai-reverse-engineering.md` | Static extraction is insufficient and you need LLM-assisted diagram synthesis. |\n| `_common\u002FOPUS_5_AUTHORING.md` | You are sizing the diagram output, deciding adaptive thinking depth at diagram-type\u002Fabstraction selection, or front-loading source\u002Fpurpose\u002Faudience at SCAN. Critical for Canvas: P3, P5. |\n| `reference\u002Fautorun-schema.md` | You are emitting the AUTORUN `_STEP_COMPLETE` block — Canvas-specific Output\u002FNext schema. |\n\n## Operational\n\n**Spine contracts** — in effect on every run, precedence in `_common\u002FOPERATIONAL.md` § Contract Precedence: `_common\u002FVALUES.md` · `_common\u002FBOUNDARIES.md` · `_common\u002FHANDOFF.md` · `_common\u002FAUTORUN.md` · `_common\u002FGIT_GUIDELINES.md` · `_common\u002FOUTPUT_STYLE.md` · `_common\u002FOPUS_5_AUTHORING.md` · `_common\u002FWORK_GATE.md`.\n\n- Journal: `.agents\u002Fcanvas.md` — record diagram patterns, tool decisions, and rendering insights.\n- After significant Canvas work, append to `.agents\u002FPROJECT.md`: `| YYYY-MM-DD | Canvas | (action) | (files) | (outcome) |`\n\n## AUTORUN Support\n\nSee `_common\u002FAUTORUN.md` for the protocol (`_AGENT_CONTEXT` input, mode semantics, error handling). Canvas-specific `_STEP_COMPLETE.Output` schema lives in `reference\u002Fautorun-schema.md`.\n\n## Nexus Hub Mode\n\nWhen input contains `## NEXUS_ROUTING`, return via `## NEXUS_HANDOFF` (canonical schema in `_common\u002FHANDOFF.md`).\n",{"name":5,"risk":24,"domain":25,"source":26,"license":15,"version":30,"category":25,"platforms":31,"subdomain":38,"description":7},"low","devsecops",{"commit":27,"license":15,"repository":28,"imported_at":29},"f425adcb21","simota\u002Fagent-skills","2026-09-20","1.0.0",[32,33,34,35,36,37],"claude-code","cursor","codex","gemini","antigravity","copilot","general","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fdevsecops\u002Fcanvas","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill canvas",{"tool":51,"command":52},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill canvas",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill canvas","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fdevsecops\u002Fcanvas\u002FSKILL.md",true,[59],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"_common","OTHER","其他",10,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fdevsecops\u002Fcanvas\u002F_common",[66,74,81,88,95,102],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":73},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":73},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":73},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":73},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":73},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":73},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]