pr

Creates a pull request for the current branch.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is highly actionable with executable commands and a well-sequenced, validated workflow, but it carries some motivational padding and keeps detailed subagent specs inline rather than practicing real progressive disclosure.

Suggestions

Trim rhetorical/motivational padding (e.g. the 'Subtle bugs ... seem safe to skip' sentence and one of the repeated 'MANDATORY — DO NOT SKIP' flags) to tighten conciseness.

Move the four detailed subagent prompt blocks into a reference file (e.g. references/review-subagents.md) and link to it from Phase 2, leaving the triage rules inline as the overview.

Consider a brief 'Quick reference' overview of the five phases at the top so the main file reads as an overview pointing to detail.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete commands and no beginner-concept padding, but carries motivational padding such as 'Subtle bugs ... hide in exactly the changes that seem safe to skip' and repeated 'MANDATORY — DO NOT SKIP' flags that could be tightened, fitting 'mostly efficient but includes some unnecessary explanation.'	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands throughout ('git status', 'git merge-base main HEAD', 'gh pr list --head <parent-branch>', 'git diff main...HEAD', 'gh pr create', 'gh pr edit <number> --add-label no-changelog') plus precise file-classification rules, matching the score-3 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The Phase 1–5 sequence is clear with explicit validation checkpoints (pre-flight stops on unstaged/untracked/main-branch; blocker triage with fix/proceed/abort branches) and a feedback loop (fix blockers then re-review), matching 'clear sequence with explicit validation steps; feedback loops for error recovery.'	3 / 3
Progressive Disclosure	No bundle files exist and there is one clearly-signaled one-level reference (the changelog doc), with well-organized phase headers, but at ~135 lines the detailed four-subagent prompt blocks live inline rather than being split into reference files, fitting 'some structure ... content that should be separate is inline' rather than a true overview-to-details split.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concise and names a concrete single task, but it lacks any 'Use when...' trigger guidance and only offers one natural keyword, leaving both completeness and trigger coverage at the middle level.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to create or open a pull request, or mentions PRs for the current branch.'

Include the common abbreviation 'PR' alongside 'pull request' to broaden natural trigger-term coverage.

Optionally name additional concrete actions (e.g. draft/stacked PR creation, changelog updates) to raise specificity above a single action.

Dimension	Reasoning	Score
Specificity	The phrase 'Creates a pull request' names the domain and one concrete action, but lists only a single action rather than multiple specific ones, matching 'names domain and some actions, but not comprehensive' rather than the score-3 multi-action anchor.	2 / 3
Completeness	It clearly answers what ('Creates a pull request for the current branch') but provides no 'Use when...' clause or explicit trigger for when, so per the guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	'pull request' is a natural term a user would say, but the description misses common variations like 'PR' and offers only one trigger, fitting 'some relevant keywords but missing common variations' rather than the broad coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	PR creation is a recognizable niche, but without explicit trigger terms it could overlap with broader git or code-review skills, fitting 'somewhat specific but could still overlap with similar skills' rather than the distinct-trigger score 3.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: MetaMask/ocap-kernel
Commit: 03b6a62

Reviewed: 13 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.