Skill Crossroads deep-research-specialist
rubric v1.2 · deterministic
A 94.9/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 100 pass
Clarity & Instructions 100 pass
Token & Context Cost 88 1 warn
Safety & Security 81 2 warn
Verifiability & Maintainability not yet scored

Top fixes — ranked by score impact

⚠ SAFETY-03 No destructive auto-invocation
deep-research-specialist.md:16auto-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.
⚠ TOKEN-03 Description budget footprint
deep-research-specialist.md:1
Description is 1364 chars (~455 tokens) — heavy for something loaded every turn.
Fix Tighten the description; it is always-on budget cost.
⚠ SAFETY-02 allowed-tools least-privilege
deep-research-specialist.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/NicholasSpisak/claude-code-subagents/agents/core/deep-research-specialist.md.svg)](https://skillcrossroads.com/s/NicholasSpisak/claude-code-subagents/agents/core/deep-research-specialist.md)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →