ultraqa

QA cycling workflow - test, verify, fix, repeat until goal met

Quality

47%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ultraqa/SKILL.md

Quality

Discovery

32%

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 conveys a general QA iteration concept but lacks the specificity and explicit trigger guidance needed for reliable skill selection. It's missing concrete actions (what specific testing/verification it performs) and has no 'Use when...' clause to guide Claude on when to select this skill. The workflow pattern is somewhat distinctive but could easily conflict with other testing or debugging skills.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user asks to run tests iteratively, debug failing tests, or wants a test-fix-verify loop until all tests pass'

Specify concrete actions: what kind of tests (unit, integration, e2e), what verification means (coverage checks, assertion validation), and what fixing entails (code changes, configuration updates)

Include natural trigger terms users would say: 'run tests', 'fix failing tests', 'test loop', 'keep testing until it works', 'iterative testing'

Dimension	Reasoning	Score
Specificity	Names a domain (QA) and describes a workflow pattern (test, verify, fix, repeat), but lacks concrete actions like 'run unit tests', 'check coverage', or 'debug failures'. The actions are generic workflow steps rather than specific capabilities.	2 / 3
Completeness	Describes what (QA cycling workflow) but completely lacks a 'Use when...' clause or any explicit trigger guidance. There's no indication of when Claude should select this skill over others.	1 / 3
Trigger Term Quality	Includes 'QA', 'test', 'verify', 'fix' which are relevant keywords, but misses common variations users might say like 'testing', 'debug', 'quality assurance', 'run tests', 'check tests', or 'test failures'.	2 / 3
Distinctiveness Conflict Risk	The 'QA cycling' concept provides some distinction, but 'test, verify, fix' could overlap with general debugging skills, code review skills, or CI/CD skills. The workflow pattern helps but isn't unique enough.	2 / 3
	Total	7 / 12 Passed

Implementation

62%

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 autonomous QA cycling workflow with excellent workflow clarity including explicit exit conditions, failure pattern detection, and clear cycle progression. The main weaknesses are vague actionability around actual test/build commands (relies on 'project's test command' without specifics) and some redundancy in explaining goal types across multiple sections.

Suggestions

Add concrete command examples for each goal type (e.g., 'npm test', 'npm run build', 'npm run lint') or explain how to discover project-specific commands

Consider extracting the state file schema and subagent prompt templates to separate reference files to improve progressive disclosure

Remove redundancy between the Goal Parsing table and the Cycle Workflow step 1 which both enumerate the same goal types

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some redundancy (e.g., the invocation table and cycle workflow overlap in explaining goal types). The state tracking JSON example and observability output are useful but could be slightly tighter.	2 / 3
Actionability	Provides concrete Task() invocation patterns and state file structure, but the actual commands for tests/build/lint/typecheck are left vague ('Run the project's test command'). Missing executable examples of what commands to actually run.	2 / 3
Workflow Clarity	Excellent workflow structure with clear 5-step cycle, explicit exit conditions table, early exit on repeated failures (3x same failure), and max cycle limits. The validation-fix-retry loop is well-defined with clear checkpoints.	3 / 3
Progressive Disclosure	Content is well-organized with clear sections and tables, but everything is in a single file. For a skill of this complexity (~120 lines), some content like the state tracking schema or detailed subagent prompts could be referenced externally.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 48ffaac

Reviewed: 4 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.