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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%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.

The content is highly actionable with concrete commands, a complete data model, explicit validation checkpoints and feedback loops, and effective delegation of heavy logic to helper scripts. Its main weakness is conciseness: repeated prohibition lists and restated guidance inflate the body and could be deduplicated.

Suggestions

Deduplicate the system-overview prohibition list (no PR diff links, review comments, screenshots, specs, or implementation deltas) into a single canonical statement and reference it instead of repeating it across the intro, view roles, data model, build, and validate sections.

Extract the full inline JSON data-model example and the PR-size/node-count rubric into a references/ document, keeping only the shape summary and the size table in SKILL.md.

Collapse the orientation heuristics section, which restates guidance already covered in the workflow and view-role sections, into a short bulleted checklist.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense and free of basic-concept padding, but it is noticeably verbose: the same prohibition list (system overview must avoid PR diff links, review comments, screenshots, specs, implementation deltas) recurs verbatim across at least five sections, and PR-size guidance is restated multiple times, so it could be materially tightened.	3 / 5
Actionability	Provides copy-paste-ready commands (gh/git invocations, exact pinned D3 CDN URL, helper-script CLI calls, validator command, Cloudflare deploy commands with flags), a full inline JSON data-model shape, and the GitHub diff anchor format — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	An eight-step workflow with explicit validation checkpoints and a 14-item validation checklist in step 7, plus a clear fix-and-regenerate feedback loop ('debug and regenerate before saying ready', 'fix the graph or report rendering as unverified').	5 / 5
Progressive Disclosure	Structure is good: the bulk D3 rendering and validation logic is delegated to real, clearly-signaled one-level-deep helper scripts (scripts/d3_canvas_runtime.py, scripts/validate_d3_canvas.py). Minor gaps remain because the SKILL.md still inlines a full JSON data-model example and repeated size/branding rubrics that could be split into references.	4 / 5
	Total	17 / 20 Passed

Description

87%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.

The description is strong, explicitly stating both what the skill does and concrete trigger conditions in third person, with good keyword coverage and a distinctive niche. The only soft spot is specificity, which lists capability framings rather than a comprehensive set of discrete operations.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities (static D3 walkthrough, zoomable PR map, graph/canvas orientation, visualization of components/data flow/dependencies/user actions), though the actions are framing-oriented rather than the broad set of discrete operations that define a 5.	4 / 5
Completeness	Explicitly answers both 'what' (generate a static interactive D3 walkthrough of a PR) and 'when' (Use when the user wants a zoomable PR map, graph/canvas orientation, or alternate visualization of the listed PR aspects) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('pull request', 'zoomable PR map', 'data flow', 'code dependencies', 'user actions') a user would say, but missing some synonyms and extension-style equivalents that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (canvas-based D3 PR visualization/walkthrough) with distinctive triggers unlikely to fire for general code-review or PR-summary skills, yielding minimal conflict risk.	5 / 5
	Total	18 / 20 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
Path: .agents/skills/pr-walkthrough/SKILL.md
Commit: b811c24

Reviewed: 18 minutes 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.