pr

Creates a pull request following Storybook conventions. Use when creating PRs, opening pull requests, or submitting changes for review.

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

86%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 focused, highly actionable single-file skill that gives Claude everything needed to draft a PR — exact command, label taxonomy, template handling, and a self-verification gate. Minor conciseness tightening and richer error-recovery guidance would lift the two 4s.

Suggestions

Tighten the QA heuristics list (e.g. merge the 'paths, filesystem, Windows' and 'complex multi-area' bullets) to reduce length without losing the decision signal.

Add a short validate-fix-retry loop for the PR body step (e.g. what to do if required template sections cannot be filled) to strengthen workflow feedback.

Consider splitting the full label/CI/QA taxonomy into a REFERENCES file and keeping only the most common labels inline, to better honor progressive disclosure as the skill grows.

Dimension	Reasoning	Score
Conciseness	The body is efficient and free of concepts Claude already knows; every label and heuristic is project-specific convention it could not infer. A few heuristic bullets ('Touches paths, filesystem...') run slightly long and could be tightened, keeping it just below a 5.	4 / 5
Actionability	Provides copy-paste-ready executable guidance — the `gh pr create --draft` command with exact flag structure, concrete title-format examples, an explicit label taxonomy, and parameterized Chromatic URL patterns with substitution rules — covering the common cases fully.	5 / 5
Workflow Clarity	The sequence (title → labels → body/template → draft command) is clear with an explicit validation checkpoint ('Verify your own steps first — run through them locally before opening the PR') and a mandatory manual-testing gate. It stops short of 5 because there is a single verify step rather than full validate-fix-retry feedback loops.	4 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-organized under clear section headers with one appropriately signaled, single-level reference to a repo path (`.github/PULL_REQUEST_TEMPLATE.md`) and no nested references, making navigation trivial.	5 / 5
	Total	18 / 20 Passed

Description

82%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 well-constructed description that clearly states both its purpose and explicit trigger conditions with natural synonyms, and is scoped narrowly enough to avoid skill conflicts. The only gap is action specificity, since it names a single capability rather than enumerating several.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Creates a pull request following Storybook conventions') but lists only a single action rather than several specific capabilities, matching the 1-2 concrete actions anchor; it does not reach the 'lists several specific actions' bar of 4.	3 / 5
Completeness	Explicitly answers both what ('Creates a pull request following Storybook conventions') and when ('Use when creating PRs, opening pull requests, or submitting changes for review') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	'creating PRs, opening pull requests, or submitting changes for review' provides good natural-phrase coverage with synonyms users would say, but lacks the exhaustive synonym/extension breadth of a 5.	4 / 5
Distinctiveness Conflict Risk	The Storybook-conventions qualifier carves a clear niche with distinct triggers and minimal overlap risk against generic PR skills, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: storybookjs/storybook
Path: .agents/skills/pr/SKILL.md
Commit: 8403f24

Reviewed: about 17 hours 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.