Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/agent-identifier
Use when creating or configuring Claude Code agents and their frontmatter.
Passed 25 of 25 test cases with the skill, and 11 of 25 without it.
and 18 more in the full report
14 fixed11 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
If a plugin named `linter-pack` puts a subagent in `agents/style-checker.md`, how is the agent namespaced when invoked?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the primary agent namespace format as style-checker | Missed | Passed |
The instructions your model reads when the skill loads.
Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.
Key concepts:
Use this skill when the user asks to:
Do not use this skill for:
plugin-structure---
name: agent-identifier
description: Use this agent when [triggering conditions]. Examples:
test cases passed, vs 11 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.