CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-review-canvas

Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into core vs mechanical changes, adds reviewer annotations, and renders diffs with moved-code detection. Use when the user pastes a GitHub PR URL and asks for a review, walkthrough, or summary, or says "review this PR".

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced instruction set with copy-paste-ready commands and thoughtful handling of real failure modes (script-tag escaping, port buffering). The main weaknesses are unverifiable bundle references and inline duplication of content that belongs in the referenced files.

Suggestions

Ship styles.css, renderer.js, and template.html alongside SKILL.md (or fold their content inline) — the body currently instructs reading three files that are absent from the bundle.

Move the long pseudocode HTML example and the 'Diff features'/'Style notes' sections into a reference file (e.g., examples.md) and link to them one level deep, keeping SKILL.md as a lean overview.

Add an explicit validation checkpoint before serving, e.g. verify /tmp/pr-patches-{number}.json parses as JSON and the final HTML contains no unresolved placeholder strings.

DimensionReasoningScore

Conciseness

The body is largely lean — command blocks and lookup tables instead of prose, with high-value non-obvious notes like the fixed-port buffering explanation. Minor over-length appears in the ~27-line pseudocode HTML example and the 'Style notes'/'Diff features' sections that duplicate bundle-file content, so it sits between anchors 3 and 4, noticeably above the midpoint.

4 / 5

Actionability

Fully executable throughout: parallel gh api commands, a jq persistence command, a complete Python assembly script handling the </script> escaping hazard, a fixed-port server command with fallback ports, and a worked HTML pattern — copy-paste-ready and covering the common cases.

5 / 5

Workflow Clarity

A clear four-step sequence (fetch → analyze/write body → assemble → serve) with rationale for fragile points and error recovery for taken ports. The only gap is a missing validation checkpoint (e.g., verify the patches JSON or final HTML before serving), which keeps it below the explicit-feedback-loop anchor.

4 / 5

Progressive Disclosure

References to styles.css, renderer.js, and template.html are clearly signaled and one level deep, but none of these files exist in the bundle, and the inline 'Diff features'/'Style notes' sections plus the long HTML example duplicate content that belongs in those separate files — some structure, but organization could be better.

3 / 5

Total

16

/

20

Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete third-person capability list plus an explicit, natural trigger clause covering pasted PR URLs and review/walkthrough/summary requests. The only weaknesses are a few missing synonyms ('pull request' spelled out) and slight overlap with generic PR-review skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Fetches PR data via gh API', 'categorizes files into core vs mechanical changes', 'adds reviewer annotations', 'renders diffs with moved-code detection' — giving comprehensive coverage of the skill's capabilities, matching the top anchor exactly.

5 / 5

Completeness

It explicitly answers both questions: the 'what' is the detailed capability sentence, and the 'when' is a concrete 'Use when the user pastes a GitHub PR URL and asks for a review, walkthrough, or summary, or says "review this PR"' clause — a direct match to the 5 anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ('asks for a review, walkthrough, or summary', 'review this PR', 'pastes a GitHub PR URL'), but common synonyms like 'pull request' spelled out or 'explain this PR' are missing, placing it just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The niche (GitHub PR → interactive HTML walkthrough) is clear with distinct triggers, but generic 'review this PR'/'summary' phrasing overlaps with ordinary PR-review tooling, so minor overlap risk keeps it at 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
cursor/plugins
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.