git-pr

创建包含正确远程处理的 Pull Request

Quality

70%

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 ./.cursor/skills/git-pr/SKILL.md

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.

The body is a tight, well-structured git/PR workflow with executable commands and a useful pre-flight checkpoint. Its main gap is the absence of validation/feedback steps after pushing and creating the PR, and a lack of a fully worked concrete example.

Suggestions

Add a verification step after pushing and after `gh pr create` (e.g. check the PR URL output or run `gh pr view`) to close the workflow with a feedback loop.

Include one fully worked concrete example (real username, branch, type, title) so the template is copy-paste ready without substitution.

Clarify what to do if the pre-flight `git remote -v` shows a wrong origin — currently it only comments the fix command without a re-check instruction.

Dimension	Reasoning	Score
Conciseness	The body is lean: a short pre-flight check, a compact command block, and terse notes, with no explanation of concepts Claude already knows. Every line (remote check, branch-from-main reminder, type enum) earns its place, matching 'lean and efficient; assumes Claude's competence'.	5 / 5
Actionability	It provides concrete, executable bash commands with a real example URL and concrete type values, but relies on placeholders (<github-username>, <files>, <body>) with no fully worked concrete example. This fits 'mostly executable guidance; concrete commands with minor gaps'; a 5 would require a worked example covering common cases.	4 / 5
Workflow Clarity	The sequence is clear (pre-flight check, then checkout/pull/branch/add/commit/push/pr-create) and the pre-flight remote check is an explicit checkpoint. It is not a 5 because there are no feedback loops (e.g. verify push succeeded, confirm PR opened) and not a 3 because a checkpoint is present and steps are well defined; the destructive-cap does not apply since no force/delete/batch operation is involved.	4 / 5
Progressive Disclosure	The skill is under 50 lines with three well-organized sections (飞行前检查, 命令, 注意事项) and no need for external bundle files, so per the simple-skills note it scores 5. The single pointer to .github/PULL_REQUEST_TEMPLATE.md is an appropriate one-level repo reference.	5 / 5
	Total	18 / 20 Passed

Description

53%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 states a clear purpose (creating a PR with correct remote handling) but omits any 'Use when' trigger guidance, which caps completeness and limits trigger-term coverage. It is reasonably distinct but would benefit from synonyms (PR) and an explicit use-when clause.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when creating a Pull Request or when the user asks to open/submit a PR.'

Include natural synonyms such as 'PR' and 'push' so the description matches how users actually phrase the request.

Optionally name the key concrete action that distinguishes this skill (e.g. 'verifies origin remote before pushing') to raise specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain (Pull Request) and one concrete action (创建/create) plus a qualifier (正确远程处理), but does not list several specific actions. It matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive'; it is not a 4 because it lacks multiple specific actions and not a 2 because the action is concrete rather than generic.	3 / 5
Completeness	It gives a clear 'what' (create a PR with correct remote handling) but provides no 'Use when...' trigger guidance, so per the rubric guideline completeness is capped at 3. It is not a 4 because 'when' is entirely absent rather than merely weak.	3 / 5
Trigger Term Quality	It includes the natural term 'Pull Request' but is missing common synonyms and variations users would say such as 'PR', 'remote', or 'push'. This fits 'some relevant keywords but missing common variations or synonyms'; a 4 would require broader keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The phrase is mostly distinct, targeting PR creation with remote handling, with only minor overlap risk against general git skills. It is not a 5 because it lacks explicit distinct trigger phrases, and not a 3 because it is more specific than 'could still overlap with similar skills'.	4 / 5
	Total	13 / 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: 4thfever/cultivation-world-simulator
Path: .cursor/skills/git-pr/SKILL.md
Commit: 471fe74

Reviewed: 4 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.