Skill Crossroads agent-generator
rubric v1.2 · deterministic
A− 90.1/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 85 1 warn
Clarity & Instructions 75 1 warn
Token & Context Cost 100 pass
Safety & Security 93 1 warn
Verifiability & Maintainability not yet scored

Top fixes — ranked by score impact

⚠ TRIGGER-03 Invocation cues in the description
agent-generator.md:1description will match user requests → no explicit cue ('use when …', 'triggers on …', quoted user phrases) found
Pure what-it-does prose — the model has to guess when to invoke it.
Project analyzer that examines your requirements and creates specialized AI a…
Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.
⚠ SAFETY-02 allowed-tools least-privilege
agent-generator.md:1no `tools` declared → the agent inherits every tool, including Bash
Subagents without a `tools` list get unrestricted tool access.
Fix Declare a scoped `tools:` list with only what the agent needs (e.g. `tools: Read, Grep, Glob`).
⚠ CLARITY-03 No ASCII-art / persona filler
agent-generator.md:119
Decorative ASCII-art / banner line — pure token cost, no instructional value.
• Security Rating: ██████████ 98%
Fix Delete decorative banners and persona filler; keep instructions plain and imperative.
Partial grade — some applicable rubric categories were not scored on this scan (e.g. LLM-assisted checks without a key) and are excluded from the overall.

Embed this badge

Skill Crossroads grade A− Always-fresh — it re-scans and updates on its own. 
[![Skill Crossroads](https://skillcrossroads.com/api/badge/mylee04/claude-code-subagents/agents/conductor/agent-generator.md.svg)](https://skillcrossroads.com/s/mylee04/claude-code-subagents/agents/conductor/agent-generator.md)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →