pr-walkthrough

Generate a static interactive D3 walkthrough of a pull request. Use when the user wants a zoomable PR map, graph/canvas PR orientation, or alternate visualization of PR system components, data flow, code dependencies, and user actions.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

A thorough, highly actionable generation skill with a well-sequenced workflow and strong validation feedback loops, backed by real one-level-deep helper scripts. Its main weakness is conciseness: several constraints and the brand palette are repeated, inflating an already large body.

Suggestions

Consolidate the system-overview negative constraints (no PR links, changed files, review comments, screenshots, specs) into a single canonical statement and reference it, instead of restating them across the intro, workflow step 4, step 6, and the validation checklist.

De-duplicate the brand color palette: since scripts/d3_canvas_runtime.py already emits Brandalf-aligned CSS, point to it rather than re-listing every hex token inline in the Brand styling section.

Trim overlap between the required UI behavior (step 6) and the validation checklist (step 7) so each control requirement is stated once.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal and task-specific (no explanations of basic concepts Claude already knows), but the system-overview negative constraints (no PR links, changed files, review comments, screenshots, specs) recur across roughly eight locations and the brand palette is restated alongside the helper script's CSS, so it could be tightened. It is not level 3 because not every token earns its place, and not level 1 because it avoids generic concept padding.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: exact bash commands (gh pr view, git diff, wrangler deploy), a full inline JSON data shape, the pinned D3 CDN URL, helper-script invocations, hex color tokens, and the GitHub diff anchor format. It is not level 2 because the code/commands are executable rather than pseudocode.	3 / 3
Workflow Clarity	An explicit eight-step numbered workflow culminates in a 14-point validation checklist with a validate->fix->regenerate feedback loop and a reusable validator script ("Do not report the walkthrough as ready if validation fails"), matching the level-3 anchor for generated-code operations. It is not level 2 because checkpoints and error recovery are explicit, not implicit.	3 / 3
Progressive Disclosure	Bundle files (scripts/d3_canvas_runtime.py and scripts/validate_d3_canvas.py) are clearly signaled, referenced by exact path and usage, and only one level deep, with well-organized sections (Output, Brand styling, Workflow, Orientation heuristics, Final response). It is not level 2 because references are clearly signaled and content is appropriately organized rather than monolithic with nested pointers.	3 / 3
	Total	11 / 12 Passed

Description

90%

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, third-person description that answers both what it does and when to use it with distinctive, natural trigger terms. Its only gap is specificity: it leads with one main action rather than enumerating multiple discrete capabilities.

Dimension	Reasoning	Score
Specificity	It names a concrete action ("Generate a static interactive D3 walkthrough of a pull request") plus the four visualization targets, but offers a single primary verb rather than multiple distinct concrete actions as the level-3 anchor requires.	2 / 3
Completeness	Both what ("Generate a static interactive D3 walkthrough of a pull request") and when ("Use when the user wants a zoomable PR map...") are explicitly stated with a clear trigger clause, satisfying the level-3 anchor; it is not level 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	Natural user phrasings are well covered ("zoomable PR map", "graph/canvas PR orientation", "alternate visualization of PR system components, data flow, code dependencies, and user actions"), matching the good-coverage anchor; not level 2 because common variations are present rather than missing.	3 / 3
Distinctiveness Conflict Risk	The D3 PR-walkthrough niche with triggers like "zoomable PR map" and "graph/canvas PR orientation" is a clear, narrow niche unlikely to fire for unrelated skills, matching the level-3 anchor; it is not level 2 because it does not overlap meaningfully with similar skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: warpdotdev/common-skills
Commit: 037b823

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.