pr-splitter

Use when breaking a large, complex, messy, or hard-to-review pull request into multiple smaller PRs; planning stacked PRs; extracting independent changes from a branch; splitting mixed refactor and behavior changes; managing drift after review feedback; rebasing follow-up PRs as earlier PRs change; or preserving original branch intent while shipping incrementally.

Quality

96%

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

92%

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 and well-sequenced with explicit validation for risky git operations. The only weakness is progressive disclosure: a long single-file body that could offload the detailed Changesets guidance and templates into one-level-deep reference files.

Suggestions

Move the detailed Changesets section (the five-step procedure and bump-type guidance) into a references file such as CHANGESETS.md, leaving SKILL.md with a concise pointer plus the key rule to delete and recreate scoped changesets per PR.

Extract the full PR-description and scratchpad markdown templates into a references/TEMPLATES.md, keeping only brief inline sketches in SKILL.md so the overview stays lean.

With those splits, add a short 'References' section with clearly signaled one-level-deep links so navigation to the detailed material is explicit.

Dimension	Reasoning	Score
Conciseness	The body is dense with process-specific actionable guidance (git commands, changeset CLI, templates) and avoids explaining concepts Claude already knows; every section earns its tokens. It is borderline given its 131-line length, but there is no conceptual padding to trim.	3 / 3
Actionability	It provides copy-paste-ready commands — 'git branch backup/original-large-pr', 'git restore -p --source backup/original-large-pr -- path', 'pnpm changeset -s -m "..."' — plus concrete PR-description and scratchpad templates, matching the fully-executable level-3 anchor.	3 / 3
Workflow Clarity	The numbered 8-step 'Required workflow' has an explicit verification step (step 6: build/typecheck/lint/tests) and safety checkpoints (snapshot backup, don't delete the original branch) for the destructive git operations, with drift/range-diff feedback loops — matching the level-3 anchor.	3 / 3
Progressive Disclosure	Sections are well-organized, but at 131 lines everything lives inline in SKILL.md with no reference files; the verbose Changesets section and full templates are content that could appropriately be split out, so it sits at level 2 rather than 3.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 specific, trigger-rich, and clearly distinguishes the skill's niche. It explicitly answers both what the skill does and when to use it without padding or over-claims.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'breaking a large... pull request into multiple smaller PRs', 'planning stacked PRs', 'extracting independent changes', 'managing drift after review feedback', 'rebasing follow-up PRs' — rather than vague language, matching the level-3 anchor.	3 / 3
Completeness	It opens with an explicit 'Use when...' trigger clause enumerating the situations, and states clearly what the skill does (break/split/extract/rebase PRs), answering both 'what' and 'when' explicitly.	3 / 3
Trigger Term Quality	It covers natural terms a user would actually say — 'pull request', 'PRs', 'stacked PRs', 'review feedback', 'rebasing', 'split' — giving good coverage rather than technical jargon, matching the level-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The PR-splitting / stacked-PR / drift-management niche is highly specific with distinct triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	12 / 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: mastra-ai/mastra
Path: .claude/skills/pr-splitter/SKILL.md
Commit: 3b78ed9

Reviewed: about 23 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.