Known Bad
- 2 installs
- 416 repo stars
- Updated August 5, 2026
- boshu2/agentops
Known-bad is a Claude Code skill fixture that intentionally fails the auditor's Pass-2 checks so the auditor returns FAIL.
About
Known-bad is a test fixture for the AgentOps skill auditor. Its SKILL.md passes Pass 1 frontmatter validation but intentionally violates Pass-2 content-discipline checks by omitting the Critical Constraints, Why rationales, Output Specification, and Quality Rubric sections. It is used to confirm the auditor returns a FAIL verdict on non-conforming input.
- Test fixture that intentionally fails the skill auditor's Pass-2 checks
- Passes Pass 1 frontmatter validation but omits required content sections
- Drives the auditor to return verdict FAIL with exit 1
Known Bad by the numbers
- 2 all-time installs (skills.sh)
- Ranked #611 of 782 Skill Development skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
known-bad capabilities & compatibility
- Use cases
- testing
What known-bad says it does
This SKILL.md passes Pass 1 (frontmatter is structurally valid and name matches dir) but intentionally violates Pass-2 content-discipline checks.
Run the auditor and expect FAIL exit 1.
npx skills add https://github.com/boshu2/agentops --skill known-badAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 2 |
|---|---|
| repo stars | ★ 416 |
| Last updated | August 5, 2026 |
| Repository | boshu2/agentops ↗ |
What it does
Confirm the skill auditor returns a FAIL verdict on intentionally non-conforming input.
Who is it for?
Skip if: Real-world use; it is a deliberately non-conforming test fixture.
When should I use this skill?
You need to verify the skill auditor returns FAIL on non-conforming input.
What you get
The auditor returns verdict FAIL with at least one fail-severity finding on the fixture.
By the numbers
- passes Pass 1
- violates Pass-2 content-discipline checks
- exit 1
Files
/known-bad — Auditor FAIL test fixture
This SKILL.md passes Pass 1 (frontmatter is structurally valid and name matches dir) but intentionally violates Pass-2 content-discipline checks. The auditor should return verdict FAIL with at least one fail-severity finding.
How to use
Run the auditor and expect FAIL exit 1.
Examples
bash skills/skill-auditor/scripts/audit.sh tests/fixtures/skills/known-badNote: there is intentionally no ## ⚠️ Critical Constraints section, no **Why:** rationales, no ## Output Specification, no ## Quality Rubric, and no Checkpoint: markers. These omissions exercise multiple Pass-2 checks. The single FAIL severity check (output-spec-explicit) drives the FAIL verdict.
Related skills
Find SkillsSo their agent can intelligently recommend and install the right modular skills from the open ecosystem when they ask how to do something.3M27.9k
Lark Skill MakerRapidly create custom skills for Lark (Feishu) that can be invoked by their AI agents and automation workflows.513k
Skill CreatorGenerate, test, and iterate on new reusable agent skills directly inside their Claude or Cursor workflow.337k166k
BrainstormingTurn vague product ideas into clear, approved designs and specifications through guided collaborative dialogue before writing any code.307k265k
Writing Great SkillsCreate high-quality, reusable agent skills that other developers can discover and install from the Skillselion catalog.290k200k
Find SkillsInstantly surface the best relevant agent skills, MCP servers, and workflows across multiple registries before starting any new project.226k12