Skill Crossroads agent-assembler
rubric v1.2 · deterministic
A 93.2/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 85 1 warn
Clarity & Instructions 100 pass
Token & Context Cost 100 pass
Safety & Security 81 2 warn
Verifiability & Maintainability not yet scored

Top fixes — ranked by score impact

⚠ SAFETY-03 No destructive auto-invocation
agent-assembler-old.md:23auto-invocable (no disable-model-invocation) → performs a destructive action ("deploy")
Skill appears to "deploy" but the model can auto-invoke it — a destructive action could fire without the user asking.
deploy
Fix If this action is destructive/irreversible, set `disable-model-invocation: true` so it only runs when explicitly invoked.
⚠ TRIGGER-03 Invocation cues in the description
agent-assembler-old.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.
Analyzes your project's `claude.md` to assemble a custom-built crew of AI age…
Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.
⚠ SAFETY-02 allowed-tools least-privilege
agent-assembler-old.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`).
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-assembler-old.md.svg)](https://skillcrossroads.com/s/mylee04/claude-code-subagents/agents/conductor/agent-assembler-old.md)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →