agent-tester
Agent skill for tester - invoke with $agent-tester
38
7%
Does it follow best practices?
Impact
88%
1.14xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-tester/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides no information about what the skill does, when it should be used, or what domain it operates in. It reads more like a placeholder label than a functional description that could help Claude select the right skill.
Suggestions
Replace the entire description with concrete actions the skill performs (e.g., 'Runs unit tests, generates test cases, and validates code coverage for Python projects').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks to run tests, write test cases, check test coverage, or debug failing tests').
Specify the domain or technology scope to make the skill distinguishable from other testing-related skills (e.g., mention specific languages, frameworks, or testing types).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for tester' is extremely vague and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description provides no functional information and no trigger guidance. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'tester', which is overly generic. There are no natural keywords a user would say to invoke this skill beyond the explicit command '$agent-tester'. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'tester' is extremely generic and could overlap with any testing-related skill. There is nothing to distinguish this skill from other potential testing or agent skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a generic testing textbook rather than an actionable agent skill. It explains fundamental testing concepts Claude already knows (test pyramid, FIRST principles, AAA pattern) at great length, while failing to provide a clear operational workflow for how the tester agent should behave when invoked. The MCP tool integration section adds some project-specific value but uses non-standard syntax.
Suggestions
Remove all generic testing knowledge (test pyramid, FIRST principles, best practices list) that Claude already knows, and focus only on project-specific conventions, tool configurations, and the exact MCP commands to use.
Add a clear step-by-step workflow: e.g., 1) Check what changed, 2) Determine which test suites to run, 3) Execute tests, 4) Validate results, 5) Report via MCP memory — with explicit validation checkpoints and error recovery.
Split detailed test pattern examples (security, performance, E2E) into separate referenced files, keeping SKILL.md as a concise operational overview.
Fix MCP tool invocation syntax to be valid and copy-paste ready, showing exact tool call format the agent should use.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~250+ lines. Explains basic testing concepts Claude already knows (test pyramid, FIRST principles, AAA pattern, what unit/integration/E2E tests are). The test pyramid ASCII art, generic best practices list, and extensive boilerplate examples add little value that Claude doesn't already possess. | 1 / 3 |
Actionability | Contains executable TypeScript test examples which is good, but they are generic templates not tied to any specific project context. The MCP tool integration section uses non-standard syntax (not valid JS/TS) and the examples are illustrative rather than copy-paste ready. Much of the content describes what to do rather than providing project-specific executable guidance. | 2 / 3 |
Workflow Clarity | No clear sequential workflow for how the tester agent should actually operate when invoked. The 'Core Responsibilities' is a list of concepts, not a process. There are no validation checkpoints, no decision points for when to run which test types, and no feedback loops for handling test failures in a structured way. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline. Unit tests, integration tests, E2E tests, performance testing, security testing, and MCP integration are all dumped into one massive file with no references to external files. Content that could be split (e.g., security testing patterns, performance testing patterns) is all inline. | 1 / 3 |
Total | 5 / 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.
- Repository
- ruvnet/claude-flow
- Commit
f547cec
- Reviewed
Table of Contents
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.