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.
66
78%
Does it follow best practices?
Impact
—
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 trigger terms covering natural user language, and includes an explicit 'Use when...' clause. The description is concise yet comprehensive, and the combination of PR review + Cursor Canvas rendering 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 all concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (render PR diff review as Canvas, group by importance, separate boilerplate, highlight tricky code) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'pull request', 'PR review', 'diff', 'diff walkthrough', 'change-set overview', 'Cursor Canvas'. Good coverage of variations including 'PR review canvas' and 'summarizing a diff for review'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: the combination of PR diff review + Cursor Canvas rendering + importance grouping creates a very clear niche. The specific output format (Cursor Canvas) and domain (PR diffs) 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 provides clear conceptual guidance for building PR review canvases. Its main strengths are the intelligent grouping strategy, the progressive disclosure of SDK details to external files, and the nuanced guidance on when to apply techniques like pseudocode and example traces. Its weaknesses are the lack of concrete output examples or executable canvas component usage, and the absence of explicit validation steps in the workflow.
Suggestions
Add a concrete example showing a small sample canvas output structure (even abbreviated) so Claude knows what the final artifact should look like — e.g., a snippet showing how Core Logic, Wiring, and Boilerplate sections render with specific SDK components.
Add an explicit validation step after `gh pr diff` to handle failures (empty diff, auth errors, invalid PR number) before proceeding to grouping.
Consider adding a brief numbered workflow summary at the top or bottom that sequences the steps explicitly (1. Gather → 2. Group → 3. Annotate → 4. Render → 5. Self-check) to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining things Claude already knows, but some sections are slightly verbose — e.g., the 'Be creative' section restates the goal multiple times and the 'Tone and content' section could be tighter. The 'Gather the diff' section's bold warning paragraph is appropriately detailed for a safety constraint, though. | 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 canvas component usage, or a sample output structure showing what the rendered canvas should look like. The instructions are specific enough to act on but not copy-paste ready. | 2 / 3 |
Workflow Clarity | There is a clear implicit sequence (gather diff → group changes → distill → trace → annotate → render), but it's spread across separate sections rather than presented as an explicit ordered workflow. There are no validation checkpoints — e.g., no step to verify the diff was fetched successfully, no self-check that groupings are complete, no verification that all files are accounted for. | 2 / 3 |
Progressive Disclosure | The skill appropriately references external files (`SKILL.md` for canvas policy, `index.d.ts` for SDK surface) as one-level-deep pointers, keeping the body focused on PR-review-specific guidance. The content is well-organized into clearly labeled sections that are easy to navigate. No bundle files are provided, but the references are clear and well-signaled. | 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
b8f2564
- 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.