Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
58
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./cursor-team-kit/skills/review-and-ship/SKILL.mdQuality
Discovery
60%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 does a good job listing specific, concrete actions spanning a code review and PR workflow. However, it lacks an explicit 'Use when...' clause, which hurts completeness and makes it harder for Claude to know exactly when to select this skill. Adding trigger guidance and a few more natural user terms would significantly improve selection accuracy.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to review code, check for bugs, run tests, prepare a pull request, or finalize work on a branch.'
Include common term variations users would naturally say, such as 'pull request', 'code review', 'push changes', 'merge request', or 'check my code'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: review branch for bugs, check intent fit, check test coverage, run/write tests, commit focused work, open/update a PR. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'bugs', 'tests', 'PR', 'commit', 'branch', and 'test coverage', but misses common user variations like 'pull request', 'code review', 'CI', 'push', 'merge', or 'lint'. Users might say 'review my code' or 'open a pull request' which aren't fully covered. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of code review + testing + PR workflow is somewhat distinctive, but individual components like 'commit' or 'write tests' could overlap with general coding skills, git skills, or testing-specific skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that covers the review-and-ship workflow at an appropriate level of abstraction. Its main weakness is that the core workflow steps are more descriptive than actionable—they tell Claude what to do conceptually but lack the concrete commands (e.g., `git add`, `git commit`, `gh pr create`) that would make them copy-paste ready. The guardrails and output sections add good value.
Suggestions
Add concrete git/gh commands to workflow steps 5 and 6 (e.g., `git add -p`, `git commit -m '...'`, `gh pr create --fill` or `gh pr edit`) to improve actionability.
Add an explicit validation gate between steps 4 and 5, such as 'Only commit when all affected tests pass' to strengthen the workflow checkpoint pattern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. Every section serves a purpose, there's no explanation of concepts Claude already knows (like what a PR is or how git works), and the content is tightly structured without padding. | 3 / 3 |
Actionability | The workflow steps are clear but mostly descriptive rather than executable. The 'Suggested Checks' section provides concrete commands, but the core workflow (steps 1-6) uses phrases like 'decide whether to add them' and 'use parallel subagents' without concrete examples of how to do so. Commit and PR creation lack specific command examples. | 2 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced and step 4 includes a feedback loop (fix and re-run tests). However, there are no explicit validation checkpoints between steps—e.g., no check that tests pass before committing, no verification that the PR was created successfully. For a workflow involving commits and PR operations, more explicit gates would strengthen it. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized into clear sections (Trigger, Workflow, Suggested Checks, Guardrails, Output) that are easy to scan and navigate. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
b8f2564
Table of Contents
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.