benchmark-skills/probe-metadata-values/SKILL.md
Benchmark skill for testing how platforms handle edge-case YAML values in the metadata frontmatter field. Use when asked to probe metadata value handling.
npx skillsauth add agent-ecosystem/agent-skill-implementation probe-metadata-valuesInstall 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.
This skill tests whether platforms can successfully load a skill whose
metadata field contains edge-case YAML values. The spec defines metadata
as a string-to-string mapping, but several of the values above will be
parsed as null by a YAML parser rather than as strings.
The canary phrase for this skill is: THRUSH-FLINT-8294
If you can see this phrase, the platform successfully loaded this skill despite the edge-case metadata values.
When activated, report:
Load success: Did this skill load successfully? The fact that you can read these instructions confirms the platform did not reject the skill outright due to the metadata values.
Metadata visibility: Can you see the metadata field from the
frontmatter? If so, list each key and what value you see. Pay
particular attention to:
normal: Should be the string "baseline" (control value).empty-double and empty-single: Should be empty strings.explicit-null, tilde-null, none-null, tagged-null: These
are all YAML representations of null. Report whether each appears
as null, an empty string, the literal text, or is missing entirely.Key preservation: Are all seven keys present, or were any dropped? Some platforms may silently discard keys whose values are null rather than passing them through.
Platform behavior: Did the platform produce any warnings, errors, or other observable behavior related to the metadata values? For example:
testing
Benchmark skill for testing path traversal boundary enforcement. Use when asked to probe path traversal.
development
Second of a pair of benchmark skills for testing cross-skill resource shadowing. Both skills have a references/API.md file with different content. Use when asked to probe resource shadowing.
development
First of a pair of benchmark skills for testing cross-skill resource shadowing. Both skills have a references/API.md file with different content. Use when asked to probe resource shadowing.
testing
Benchmark skill for testing how platforms handle nonstandard frontmatter fields. Use when asked to probe nonstandard fields.