aif-qa

QA workflow for testing a feature or task implementation. Analyzes changes, produces test plans, and describes concrete test scenarios. Use when user says "test this", "write test plan", "what should I test", or "QA this branch".

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/aif-qa/SKILL.md

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 workflow skill with clear sequencing and good reference split. It would benefit from tightening the verbose config section and adding explicit validation feedback loops for the generated artifacts.

Suggestions

Collapse the duplicated path/language listings in Step 0 into a single table or 'Store:' block to remove redundant prose and reduce token load.

Move the branch-slug derivation (safe-slug + hash rationale + examples) into a dedicated reference file, keeping only the formula and one example inline.

Add an explicit validate-and-retry checkpoint after each artifact is written (e.g. confirm the artifact exists and references its prerequisite) to strengthen workflow_clarity for the batch pipeline.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but the config-loading section repeats path/language lists in both prose and "Store:" form, and the slug subsection includes a "Why the hash" rationale and worked examples that pad beyond what Claude needs.	3 / 5
Actionability	Concrete commands ("git branch --show-current", "git hash-object --stdin"), exact config keys, and file paths give mostly executable guidance; the per-mode detail is delegated to reference files, leaving minor gaps inline.	4 / 5
Workflow Clarity	Steps are clearly sequenced (Step 0 / 0.1 / 0.2 / 1) with stage-dependency rules and pipeline failure handling ("If any stage fails — stop the pipeline and report"), but explicit validate-then-fix feedback loops on the generated artifacts are only implicit.	4 / 5
Progressive Disclosure	Mode details are cleanly split into one-level-deep, real reference files (CHANGE-SUMMARY.md, TEST-PLAN.md, TEST-CASES.md) with clear signaling, but the heavy inline config/language/slug policy could arguably live in its own reference, keeping it just below 5.	4 / 5
	Total	15 / 20 Passed

Description

83%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 that clearly states capabilities and provides natural trigger phrases answering both what and when. Minor room to expand action coverage and synonyms for a perfect score.

Dimension	Reasoning	Score
Specificity	"Analyzes changes, produces test plans, and describes concrete test scenarios" names the domain plus three concrete actions; not quite the comprehensive multi-action list of a 5, but clearly above the 3-anchor's 1-2 actions.	4 / 5
Completeness	Explicitly answers both what ("Analyzes changes, produces test plans, and describes concrete test scenarios") and when ("Use when user says...") with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	"test this", "write test plan", "what should I test", "QA this branch" are natural user phrases with good coverage, but a few common synonyms (e.g. "test cases", "regression") are absent, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	The manual-QA / branch-testing niche is mostly distinct with clear triggers, though "test this" could overlap with automated-testing skills, leaving minor conflict risk versus the 5 anchor.	4 / 5
	Total	17 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-qa/SKILL.md
Commit: ac92beb

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.