test-design-review
Skill0 starsChanged 6 months agoMITView on GitHub
Review test design quality for code changes against the defined test strategy. Use when reviewing a feature branch, commit, or uncommitted changes to ensure new or modified tests are well-designed, placed at the correct test level, and conform to the architecture defined in the strategy.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- shalomb/agent-skillstheir own version, first seen Aug 23, 2026
- jasonswett/llm-skillstheir own version, first seen Mar 16, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- jasonswett/llm-skills★ 194same name
- shalomb/agent-skills★ 3same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- verify-test-coverageSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 5 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
If $scope is "uncommitted" or "unstaged": analyze uncommitted changes (git diff HEAD)
- Very specific: line 20
If $scope is "last-commit": analyze the most recent commit (git diff HEAD~1 HEAD)
- Very specific: line 21
If $scope matches pattern "last-N-commits": analyze last N commits from HEAD
- Very specific: line 22
If $scope is empty or "branch": analyze diff between current feature branch and main (git diff main...HEAD)
- Very specific: line 23
If $scope is a custom git range (e.g., "commit1..commit2"): use that range
- Very specific: line 24
If $scope is unclear or not provided, ask the user what scope they want to analyze
- Distinctive: line 30
Look for the test strategy definition to understand the expected design and level structure.
- Very specific: line 34
If not found, check .claude/ directory for strategy documentation
- Distinctive: line 35
If user mentioned a specific strategy in their prompt, use that instead
- Distinctive: line 36
If no strategy file found, ask the user where the test strategy is defined
- Distinctive: line 48
Check whether new or modified tests follow that pattern — are the correct abstractions used and is the defined pattern respected throughout?
- Distinctive: line 55
Levels reviewed: only levels that had changes in the diff
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Test Design Review
Analyze the design quality of tests introduced or modified in a code change, and verify they conform to the defined test strategy.
Step 1: Detect scope of change
The scope defines which code changes to analyze for test design quality.
Scope options:
- If
$scopeis "uncommitted" or "unstaged": analyze uncommitted changes (git diff HEAD) - If
$scopeis "last-commit": analyze the most recent commit (git diff HEAD~1 HEAD) - If
$scopematches pattern "last-N-commits": analyze last N commits from HEAD - If
$scopeis empty or "branch": analyze diff between current feature branch and main (git diff main...HEAD) - If
$scopeis a custom git range (e.g., "commit1..commit2"): use that range - If
$scopeis unclear or not provided, ask the user what scope they want to analyze
Determine the appropriate git command and execute it to get the diff. Focus on test files introduced or modified in the diff.
Step 2: Locate test strategy
Look for the test strategy definition to understand the expected design and level structure.
Strategy location:
- First, check if
TEST_STRATEGY.mdexists in the repository root - If not found, check
.claude/directory for strategy documentation - If user mentioned a specific strategy in their prompt, use that instead
- If no strategy file found, ask the user where the test strategy is defined
Step 3: Review test design quality
Read the strategy file and identify all defined test levels. For each level, check whether a ### Design section exists with real content (not placeholder text in square brackets). Only evaluate levels that have test file changes present in the diff from Step 1 — levels with no changes are out of scope, do not report on them.
Test level conformance
- Using
### Purpose,### Covers, and### Excludesas the definition of what belongs at this level, evaluate whether each new or modified test belongs here based on what it does and how it is written - Flag tests whose nature or granularity contradicts the level's intent — e.g. a single field validation in an E2E test, or a full flow assertion in a unit test
Framework architecture conformance — apply only to levels with a defined ### Design section
- Identify the architectural pattern described in the
### Designsection (e.g. Screenplay pattern, Page Object Model, custom actor/DSL approach) - Check whether new or modified tests follow that pattern — are the correct abstractions used and is the defined pattern respected throughout?
- Flag any tests that bypass the defined pattern and interact with the system at a lower level than intended
Step 4: Report results
Provide a structured summary:
- Scope analyzed: what test changes were reviewed
- Levels reviewed: only levels that had changes in the diff
- Well-designed: tests that correctly follow the strategy
- Design issues found: specific tests with placement or design problems, with explanation of why
- Recommendations: concrete suggestions for each issue (e.g. move to unit level, refactor to use correct actor abstraction)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

