negative-bad-primary-role

Test fixture — primary_role violates advisor-wins-ties (implementation declared as primary_role for a role:review skill)

7 stars

Best use case

negative-bad-primary-role is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Test fixture — primary_role violates advisor-wins-ties (implementation declared as primary_role for a role:review skill)

Teams using negative-bad-primary-role should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/negative-bad-primary-role/SKILL.md --create-dirs "https://raw.githubusercontent.com/0xHoneyJar/loa-freeside/main/tests/fixtures/skills/role-lint/negative-bad-primary-role/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/negative-bad-primary-role/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How negative-bad-primary-role Compares

Feature / Agentnegative-bad-primary-roleStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Test fixture — primary_role violates advisor-wins-ties (implementation declared as primary_role for a role:review skill)

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Bad primary_role Fixture

primary_role: implementation is a downgrade from role: review.
The advisor-wins-ties rule prohibits this — primary_role must be more
restrictive than role, never less. Adding plenty of review-class
keywords (review audit validate verify score consensus) so the
review-keyword heuristic does NOT trip; the failure must come from
the primary_role consistency check exclusively.