Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

hollow-validation-checker

bởi andyxinweiminicloud

Coding Agents & IDEs
349Lượt tải do clawskills.sh công bố
1Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Helps detect hollow validation in AI agent skills — identifies fake tests that always pass without actually.

Mô tả

Kỹ năng này làm gì

Analyzes validation commands and test code in AI agent skills to identify patterns that fake quality signals. Detects exit code gaming, echo-only commands, tautological assertions, and commented-out tests. Rates each validation as SUBSTANTIVE, WEAK, or HOLLOW.

Manual code review can miss sophisticated test theater where real frameworks are invoked but assertions test trivially true conditions, which this tool flags through static analysis of assertion content.

Khi nào nên dùng

  • Auditing agent marketplace skills before adding them to a production pipeline
  • Reviewing community-submitted skills before merging a PR
  • Comparing validation quality across a batch of published skills
  • Flagging skills that claim test coverage but run no real assertions
  • Deciding whether to trust a skill's published validation rating

Quy trình ví dụ

ĐẦU VÀO

User asks: Check this Capsule JSON — its validation field claims 14 tests passed

AGENT
  1. 1

    Parse the validation field from the provided Capsule JSON

  2. 2

    Break down each command in the validation chain

  3. 3

    Check each command for real assertion statements vs hardcoded success strings

  4. 4

    Inventory real assertions vs hollow outputs

  5. 5

    Generate a quality rating with evidence

ĐẦU RA

HOLLOW rating: 0 real assertions found, 2 hollow outputs (hardcoded print statement claiming 14 tests, static echo). Recommendation to treat as unvalidated.

Cài đặt

clawhub install andyxinweiminicloud/hollow-validation-checker

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết