pr-walkthrough

Create a narrated video walkthrough of a pull request with code slides and audio narration. Use when asked to create a PR walkthrough, PR video, or walkthrough video.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 a well-structured, actionable skill with a clear validated workflow and appropriate offloading of detail to a single reference file. Its main weaknesses are mild verbosity in the guidance sections and a slight mismatch between the documented file tree and the actual bundle scripts.

Suggestions

Tighten the Philosophy and Narration writing tips sections, which overlap with guidance already implied by the workflow steps.

Reconcile the file-organization tree with the actual bundle: it documents video/render.sh and build.mjs but the scripts/ bundle contains generate-audio.sh and make-video.sh.

Standardize the command path prefixes (./scripts vs ./video) so the runnable examples are copy-paste consistent with the documented layout.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence without explaining basic concepts, though the Philosophy and Narration writing tips sections contain some guidance that could be tightened or consolidated.	4 / 5
Actionability	It provides concrete executable commands (gh pr view, generate-audio.sh, render.sh) and shown JSON formats, with only minor gaps such as inconsistent path references between prose (./scripts, ./video) and the documented file tree.	4 / 5
Workflow Clarity	A clear five-step sequence (Understand, Write narration, Generate audio, Write manifest, Render) is paired with explicit validation (audio clip sanity checks, idempotent whisper transcription), automatic retry feedback loops, and a final verification checklist.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview pointing to a real one-level-deep reference (references/manifest.md, signaled at step 4) and bundle scripts, but the file-organization tree references render.sh/build.mjs that do not match the actual scripts/ bundle contents (make-video.sh).	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, clearly answering both what the skill does and when to invoke it with natural trigger phrases and a distinct niche. The only minor gap is slightly less comprehensive coverage of concrete capabilities and trigger synonyms.

Suggestions

Consider mentioning subtitles and standardized intro/outro slides in the description to make the concrete capabilities more comprehensive.

Add a couple more natural trigger synonyms (e.g. "PR demo" or "walkthrough of changes") to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	"Create a narrated video walkthrough of a pull request with code slides and audio narration" names the domain and several concrete actions (narrated video, code slides, audio narration), but stops short of comprehensive coverage of capabilities like subtitles and intro/outro slides.	4 / 5
Completeness	It explicitly states both what it does (create a narrated video walkthrough with code slides and audio narration) and when to use it ("Use when asked to create a PR walkthrough, PR video, or walkthrough video"), matching the top anchor.	5 / 5
Trigger Term Quality	"Use when asked to create a PR walkthrough, PR video, or walkthrough video" provides good natural trigger phrases a user would actually say, though a few common synonyms/variations are absent.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (PR walkthrough videos) with distinct triggers that are unlikely to fire for unrelated skills, giving 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: tldraw/tldraw
Path: skills/pr-walkthrough/SKILL.md
Commit: e8f61ac

Reviewed: 3 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.