split-pr

Analyzes current changes and suggests how to split them into smaller, reviewable PRs

Quality

57%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/split-pr/SKILL.md

Quality

Content

65%

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 and templates, but it is over-long for a single file and lacks an explicit validation feedback loop in its workflow. Tightening redundant sections and moving patterns/examples into a reference file would improve conciseness and progressive disclosure.

Suggestions

Add an explicit validation feedback loop, e.g. 'After drafting each proposed PR, verify it builds and passes tests independently; if not, re-group files before finalizing the plan.'

Collapse the redundant 'Notes', 'User Interaction', and 'Best Practices' sections into the workflow steps to reduce token cost.

Move the 'Common Split Patterns' and 'Examples' blocks into a referenced file (e.g. SPLIT_PATTERNS.md) to shrink the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concepts Claude already knows, but it is verbose: the 'Notes', 'User Interaction', and 'Best Practices' sections restate content from the workflow and 'Next Steps', so it 'could be tightened'.	2 / 3
Actionability	It provides fully executable git commands, a concrete copy-paste-ready PR proposal template, and worked examples with specific file counts and line estimates, matching 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	The six numbered steps give a clear sequence with an evaluation checkpoint (step 2) and dependency ordering (step 5), but there is no explicit validate-then-fix feedback loop within the workflow, which the rubric treats as missing checkpoints for a batch/multi-PR operation.	2 / 3
Progressive Disclosure	The skill is a single ~210-line file with no bundle references (references/, scripts/, assets/ are empty); the substantial 'Common Split Patterns' and 'Examples' sections are inline content that could be split into reference files, matching 'content that should be separate is inline'.	2 / 3
	Total	9 / 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 clear and on-domain but lacks an explicit use-trigger clause and fuller trigger-term coverage, leaving every dimension at the midpoint. Adding a 'Use when...' clause with natural phrasing like 'split a large pull request' would lift completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when a pull request is too large to review or when the user asks to split changes into smaller PRs.'

Include the full term 'pull request' alongside 'PRs' so natural-language triggers match more user phrasings.

Sharpen the action list by naming concrete outputs (e.g. 'proposes a file-by-file split plan with dependencies and creation order') to push specificity toward 3.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain and two actions ("Analyzes current changes" and "suggests how to split them into smaller, reviewable PRs") but does not enumerate multiple specific actions like the score-3 anchor; it sits at 'names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It clearly states what the skill does but provides no explicit "Use when..." trigger clause, so per the guideline a missing trigger clause caps completeness at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	It includes relevant natural terms such as "split", "smaller", and "PRs", but omits common variations like the full phrase "pull request" or "too big/too large", landing at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The PR-splitting niche is somewhat specific, but "current changes" is generic and without explicit triggers it could overlap with general git/PR workflow skills, matching 'somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	8 / 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: stacklok/toolhive
Path: .claude/skills/split-pr/SKILL.md
Commit: cd373ec

Reviewed: 2 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.