test-suite-architect

This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90% coverage targets.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/test-suite-architect/SKILL.md

The canonical home for this skill is qa-expert in daymade/claude-code-skills

Quality

Content

67%Weight 40%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 well-structured, actionable overview with real scripts, templates, and flat, verifiable references. The main quality issue is redundancy — the autonomous-execution pitch is repeated across five sections with marketing language — and a moderately oversized body that partially duplicates what the references already carry.

Suggestions

Consolidate the autonomous-execution material (Quick Start note, capability 3, the dedicated section, and Patterns 1-2) into a single section pointing to references/master_qa_prompt.md.

Remove hype language ('world-class', 'Innovation', '100x faster' repeated) in favor of factual capability statements.

Move the OWASP threat breakdown and the small/medium/large project tables into a reference file and keep one-line pointers in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body carries real, dense guidance but repeats itself noticeably: autonomous execution is promoted in at least five places ('Quick Start', capability 3, its own section, 'Reference Documents', Patterns 1-2), '100x faster/speedup' appears three times, and marketing padding ('world-class', 'Innovation', '⭐ Recommended') inflates the token budget without adding instruction.	3 / 5
Actionability	Concrete executable commands are given ('python scripts/init_qa_project.py <project-name> [output-directory]', 'python scripts/calculate_metrics.py <path/to/TEST-EXECUTION-TRACKING.csv>') along with test-case ID formats, severity definitions, and a quality gates table; the gaps are minor (e.g., bug-report examples live only in a template and no sample invocation output is shown).	4 / 5
Workflow Clarity	Multi-step processes are clearly numbered (manual execution steps 1-4, patterns 1-4) with useful checkpoints such as 'update tracking CSV immediately after EACH test (never batch)', P0 auto-escalation, and objective quality gates; a fully explicit validate-and-recover loop after metrics calculation is only implicit, keeping it just below a 5.	4 / 5
Progressive Disclosure	All referenced bundle files exist (verified against the actual references/, scripts/, assets/ layout), are one level deep with no nested reference chains, and are clearly catalogued in dedicated 'Reference Documents', 'Scripts', and 'Assets' sections; the body itself runs ~290 lines and inlines some detail (OWASP threat list, project-size adaptation tables) that could arguably live in references.	4 / 5
	Total	15 / 20 Passed

Description

88%Weight 40%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.

A strong description with an explicit 'Use when...' trigger clause and a comprehensive, concrete list of capabilities. Its main weaknesses are mild jargon ('master prompts', '100x' style claims implied by 'autonomous execution capability') and slight breadth that could cause overlap with adjacent testing-related skills.

Suggestions

Trim marketing-flavored phrasing like 'Includes autonomous execution capability via master prompts' toward the concrete action ('run test plans autonomously via bundled LLM prompts').

Add a few user-natural synonyms (e.g., 'QA process', 'test plan', 'regression testing', 'test coverage') to widen trigger coverage.

Narrow 'for any software project' to a clearer niche signal to reduce overlap with generic testing/debugging skills.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions — 'creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports' plus 'OWASP security testing' — a comprehensive, specific capability list rather than vague language.	5 / 5
Completeness	It explicitly answers 'when' ('This skill should be used when...', 'Use when creating test strategies, writing test cases...') with concrete trigger phrases, and 'what' via the full list of capabilities including OWASP security testing and coverage targets.	5 / 5
Trigger Term Quality	Strong natural phrases users would say ('test strategies', 'test cases', 'test plans', 'quality metrics', 'progress reports', 'QA team handoffs'), but a few common variations are missing and some terms lean jargon-y ('master prompts', 'autonomous execution capability').	4 / 5
Distinctiveness Conflict Risk	The QA-process niche (test case standards, P0-P4 bug tracking, OWASP, quality gates) is fairly distinct, but 'establishing comprehensive QA testing processes for any software project' is broad and could overlap with general testing/debugging or code-review skills in edge cases.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/test-suite-architect/SKILL.md
Commit: a2e6ee3

Reviewed: 2 days 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.