.claude/skills/quality-validation/SKILL.md
Provide validation methods to check if final team structure output is complete and consistent
npx skillsauth add chemistrywow31/A-Team Quality ValidationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Provide validation methods to check if final output (entire team's agents/skills/rules structure) is complete and consistent.
This skill belongs exclusively to agents/team-architect.md
✓ teams/{team-name}/ directory exists
✓ agents/ directory exists and contains at least one coordinator .md
✓ skills/ directory exists and contains skill folders
✓ rules/ directory exists and contains at least one .md file
✓ All .md file names use kebab-case
✓ All agent group folder names use kebab-case
✓ Each agent .md contains: Identity, Responsibilities, Input and Output, Workflow, Available Skills, Applicable Rules, Collaboration Relationships, Boundaries
✓ Coordinator .md additionally contains: Team Overview, Subordinate Agent List, Task Assignment Strategy, Quality Control Mechanism
✓ Each skill .md contains: Description, Users/Belongs To, Core Knowledge
✓ Each rule .md contains: Applicability, Rule Content, Violation Determination
✓ Each external skill (Pattern A or B) contains a Source Attribution section with Origin, Integration, Retrieved, and Modifications fields
✓ Each skill path referenced in agent .md corresponds to an actual existing file
✓ Each rule path referenced in agent .md corresponds to an actual existing file
✓ Users listed in skill .md correspond to actual existing agents
✓ Applicability scope in rule .md corresponds to actual existing agents
✓ Coordinator's subordinate list covers all non-coordinator agents
✓ External skill Source Attribution URLs match the source recorded in the Phase 2 plan
✓ External skill Integration type (Pattern A/B) is consistent between Source Attribution and the Phase 2 plan
✓ No two agents have overlapping responsibilities (unless designed as review relationship)
✓ All agent responsibilities combined cover the team's complete scope of work
✓ No agent appears in two different groups simultaneously
✓ Collaboration relationships are bidirectionally consistent (A says downstream is B, B should say upstream is A)
# Quality Validation Report: {team-name}
## Structural Completeness: ✓ Pass / ✗ Fail
{If failed, list specific issues}
## Content Completeness: ✓ Pass / ✗ Fail
{If failed, list specific issues}
## Reference Consistency: ✓ Pass / ✗ Fail
{If failed, list specific issues}
## Logical Consistency: ✓ Pass / ✗ Fail
{If failed, list specific issues}
## Summary
{Pass / Needs correction, and correction recommendations}
data-ai
Evaluate whether a proposed agent graph supports safe handoffs and useful parallel work
testing
Extract precise team requirements through staged, single-direction questioning
content-media
Search external sources for reusable skills before designing a new one
data-ai
Create or improve a skill by using the system skill when available and the legacy local bundle as fallback