Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
73
66%
Does it follow best practices?
Impact
Pending
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 development workflow (review, test, commit, PR). However, it lacks an explicit 'Use when...' clause, which limits Claude's ability to know when to select this skill. The broad scope covering multiple workflow stages could also create overlap with more focused skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to review code, check for bugs, run or write tests, make a commit, or open/update a pull request.'
Include common trigger term variations such as 'pull request', 'code review', 'unit tests', 'push changes', 'merge request' to improve keyword coverage.
Consider clarifying the scope boundary—e.g., 'for the current feature branch'—to reduce conflict risk with standalone code review or git skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: review for bugs, check intent fit, check test coverage, run tests, write tests, commit 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 explaining when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes some natural terms like 'bugs', 'tests', 'commit', 'PR', but misses common variations users might say such as 'pull request', 'code review', 'push changes', 'merge request', or 'CI'. The terms are somewhat embedded in action phrases rather than surfaced as explicit trigger keywords. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of code review, testing, committing, and PR management is somewhat distinctive, but the broad scope covering multiple development workflow steps could overlap with separate skills for code review, testing, git operations, or PR management individually. | 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 remain somewhat abstract—providing specific commands for committing, pushing, and opening/updating PRs would make it more actionable. The guardrails and output sections add good value.
Suggestions
Add concrete commands for key workflow steps (e.g., `git add -p`, `git commit -m '...'`, `gh pr create --fill` or `gh pr edit`) to make steps 5-6 fully executable.
Add an explicit validation gate between steps 3-4 and 5-6, e.g., 'Only proceed to commit if all tests pass and no critical issues remain.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It doesn't explain what git, PRs, or diffs are. Every line adds actionable value without padding or unnecessary context. The workflow steps are terse but clear. | 3 / 3 |
Actionability | The 'Suggested Checks' section provides concrete, executable commands, but the core workflow steps (1-6) are described at a high level without specific commands or code examples for key actions like committing, pushing, opening PRs, or running tests. Steps like 'Use parallel subagents for larger diffs' lack concrete guidance. | 2 / 3 |
Workflow Clarity | The workflow has a clear 6-step sequence and step 4 includes a feedback loop (fix and re-run tests). However, validation checkpoints are implicit rather than explicit—there's no clear 'stop if X fails' gate between steps, and the criteria for 'critical issues' vs. proceeding are undefined. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~40 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.
7dd9fea
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.