pr-review-canvas
Render a PR diff review as a Cursor Canvas that groups changes by reviewer importance, separates boilerplate from core logic, and highlights tricky or unexpected code. Use when reviewing a pull request, summarizing a diff for review, or when the user asks for a PR review canvas, diff walkthrough, or change-set overview.
83
78%
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 ./pr-review-canvas/skills/pr-review-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 an excellent skill description that clearly articulates specific capabilities (grouping by importance, separating boilerplate, highlighting tricky code), provides rich natural trigger terms (PR, diff, pull request, change-set), and includes an explicit 'Use when...' clause. The description is concise yet comprehensive, and the Cursor Canvas specificity makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Render a PR diff review as a Cursor Canvas', 'groups changes by reviewer importance', 'separates boilerplate from core logic', 'highlights tricky or unexpected code'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (render PR diff review as Canvas with grouped changes, separated boilerplate, highlighted tricky code) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'pull request', 'PR review', 'diff', 'diff walkthrough', 'change-set overview', 'PR review canvas', 'summarizing a diff'. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: the combination of PR diff review + Cursor Canvas rendering + specific grouping/highlighting behavior creates a clear niche. The 'Cursor Canvas' format and PR-specific focus make it unlikely to conflict with generic code review or diff tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, thoughtfully designed skill that clearly communicates the intent and strategy for building a PR review canvas. Its main weakness is the gap between conceptual guidance and concrete execution — it tells Claude *what* to do but doesn't show *what the output looks like* with a concrete example or template. The workflow is implicit rather than explicitly sequenced, though the individual sections are clear enough to follow.
Suggestions
Add a concrete example showing a small sample PR diff input and the resulting canvas structure (even abbreviated), so Claude has a clear target output format.
Consider restructuring the main flow as an explicit numbered workflow (1. Fetch diff, 2. Classify hunks, 3. Build canvas sections, 4. Add callouts/pseudocode, 5. Render) to improve workflow clarity.
Trim the 'Be creative' section — the component inventory list ('charts, tables, diff views, DAG layout...') could be shortened to 'Use any SDK component that fits' since Claude can discover these from the referenced .d.ts files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but some sections are slightly verbose — e.g., the 'Be creative' section restates the goal multiple times and lists many component types that could be trimmed. The 'Tone and content' section is reasonable but could be tighter. | 2 / 3 |
Actionability | The skill provides clear conceptual guidance (grouping strategy, when to use pseudocode, when to trace examples) and a concrete command (`gh pr diff <pr>`), but lacks executable code examples, concrete output templates, or a sample canvas structure showing what the final artifact should look like. The guidance is specific in intent but abstract in execution. | 2 / 3 |
Workflow Clarity | There is a clear implicit sequence: gather diff → group changes → distill complex logic → add callouts → write commentary. However, the steps are presented as separate sections rather than an explicit numbered workflow, and there are no validation checkpoints (e.g., confirming the diff was fetched successfully, verifying the grouping is complete before rendering). The guard clause for missing PR links is good. | 2 / 3 |
Progressive Disclosure | The skill appropriately references external files (`~/.cursor/skills-cursor/canvas/SKILL.md` and `sdk/index.d.ts`) for the canvas generation policy and component API, keeping the body focused on the PR review-specific logic. References are one level deep and clearly signaled. The content is well-organized into logical sections without being monolithic. | 3 / 3 |
Total | 9 / 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.