pr-writer

Create pull requests following Sentry's engineering practices.

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 ./skills/pr-writer/SKILL.md

Quality

Content

78%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 solid, actionable PR creation skill with concrete examples and clear workflow steps. Its main strengths are the executable commands, realistic PR description examples, and the practical workaround for `gh pr edit`. The primary weakness is that the content is somewhat long for a single file, with the examples section being a candidate for extraction, and there are minor verbosity issues in the prerequisites section.

Suggestions

Consider extracting the three PR description examples into a separate EXAMPLES.md file to reduce the main skill's length and improve progressive disclosure.

Trim the prerequisites section — Claude knows how to check git status; a single line like 'Ensure all changes are committed (run `sentry-skills:commit` if needed)' would suffice.

Dimension	Reasoning	Score
Conciseness	Generally efficient with minimal over-explanation. The PR description examples are useful but add length; the prerequisites section explaining how to check for uncommitted changes is slightly verbose (Claude knows git status). The issue references table and guidelines are tight. Minor trimming opportunities exist but overall respects token budget.	4 / 5
Actionability	Fully executable bash commands throughout, concrete PR description examples with realistic content, specific title format conventions, and a workaround for the broken `gh pr edit` command. The examples cover feature, bug fix, and refactor cases with copy-paste ready templates.	5 / 5
Workflow Clarity	Clear 4-step sequence from verifying branch state through creating the PR, with a prerequisite check. The workflow includes a validation step (checking uncommitted changes, verifying branch state) before proceeding. Minor gap: no explicit verification after PR creation (e.g., confirming the PR was created successfully), though this is a non-destructive operation so the impact is minimal.	4 / 5
Progressive Disclosure	The content is well-structured with clear sections and headers, but it's fairly long (~150 lines) with all content inline. The three PR description examples could be in a separate file. References to external Sentry docs are provided at the end, but the skill itself doesn't split content across files despite having enough volume to warrant it. No bundle files exist to offload to.	3 / 5
	Total	16 / 20 Passed

Description

36%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 is too terse and lacks concrete actions, trigger terms, and explicit 'when to use' guidance. While it identifies the domain (pull requests) and scopes to Sentry, it doesn't describe what specific engineering practices are followed or provide enough detail for Claude to confidently select this skill over others.

Suggestions

Add a 'Use when...' clause with trigger terms like 'PR', 'pull request', 'submit code', 'open a PR', 'code review' to help Claude know when to select this skill.

List specific concrete actions such as 'formats PR titles, writes descriptions with context, adds reviewers, follows branch naming conventions' to clarify what the skill actually does.

Include Sentry-specific terminology or conventions (e.g., specific PR templates, labeling, or CI checks) to increase distinctiveness and reduce conflict risk with generic PR skills.

Dimension	Reasoning	Score
Specificity	Names the domain (pull requests) and context (Sentry's engineering practices) but provides no concrete actions beyond 'create pull requests'. No details on what specific steps or conventions are involved.	2 / 5
Completeness	Has a vague 'what' (create pull requests) but no explicit 'when' clause. There is no 'Use when...' guidance, which per the rubric should cap completeness at 3, and the weak 'what' brings it down to 2.	2 / 5
Trigger Term Quality	'Pull requests' is a natural keyword users would say, and 'Sentry' identifies the context. However, it misses common synonyms and variations like 'PR', 'merge request', 'open a PR', or 'submit code for review'.	3 / 5
Distinctiveness Conflict Risk	'Sentry's engineering practices' provides some distinctiveness by scoping to a specific organization, but 'create pull requests' is generic enough to overlap with other PR or git workflow skills.	3 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/pr-writer/SKILL.md
Commit: fbdfd63

Reviewed: about 18 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.