docs-canvas
Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API reference page, or wants to render structured documentation as an interactive canvas.
74
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs-canvas/skills/docs-canvas/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates specific capabilities, includes natural trigger terms, and explicitly addresses both what the skill does and when to use it. The description is well-structured, uses third person voice appropriately, and carves out a distinct niche combining documentation content with the Cursor Canvas format.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: organizing architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (render documentation-style Cursor Canvas with architecture notes, API references, walkthroughs, how-tos, TOC, cross-references) and 'when' (explicit 'Use when...' clause listing specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'docs canvas', 'documentation overview', 'architecture walkthrough', 'API reference page', 'structured documentation', 'interactive canvas'. These cover a good range of terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: documentation-style Cursor Canvas. The combination of 'Cursor Canvas' format with documentation-specific content types (architecture notes, API references) creates a well-defined scope unlikely to conflict with generic documentation or generic canvas skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is self-described as a placeholder and it shows — the content provides a reasonable structural outline for a docs canvas but lacks any concrete, executable guidance. There are no code examples, no component usage patterns, and no validation steps. It reads as a planning document rather than an actionable skill that Claude could follow to produce a docs canvas.
Suggestions
Add at least one complete, executable example showing how to compose a docs canvas using the SDK components (e.g., a minimal docs canvas with a TOC, one body section, and a reference section).
Include concrete component usage with actual prop shapes from the SDK, replacing vague directives like 'Use cards/sections' with specific code showing how to render them.
Add validation or self-check steps (e.g., 'Verify the canvas renders with no missing sections before finalizing') to establish a feedback loop in the workflow.
Remove or condense the placeholder status notice and aspirational prose ('Be creative', 'whatever fits') — replace with specific patterns and decision criteria for choosing layout approaches.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes some unnecessary filler (e.g., 'Build a canvas that presents documentation... as an interactive, navigable surface rather than as a flat markdown file' is somewhat redundant with the title). The placeholder status notice is honest but the overall content could be tighter given it's mostly an outline. | 2 / 3 |
Actionability | The skill explicitly states it is a placeholder with no full body written yet. There are no concrete code examples, no executable commands, no component usage patterns, and no copy-paste ready snippets. The guidance is entirely abstract and descriptive ('Use cards/sections', 'Use code blocks') without showing how. | 1 / 3 |
Workflow Clarity | There is a rough sequence (gather → plan → render) but steps lack specificity, have no validation checkpoints, and no feedback loops. The workflow reads more like a high-level outline than actionable steps with clear completion criteria. | 2 / 3 |
Progressive Disclosure | The skill references external files (SKILL.md, index.d.ts) for the SDK and generation policy, which is good structure. However, no bundle files are provided to verify these references, and the skill itself doesn't clearly separate overview from detailed content since it's all at one shallow level with no deeper reference files of its own. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cursor/plugins
- Commit
7dd9fea
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.