Loading ToolBench

Reading the current corpus…

agent-skills MCP server · F · ToolBench

agent-skills

Evaluation harness for nimble-web-expert skill against assistant production prompts. Provides CLI evaluation infrastructure for testing web expert capabilities using Claude Code and Codex runtimes.

<=2025-11-25STREAMABLE_HTTP0 tools

39/100

Definition Quality0

Protocol Readiness0

Supportability65

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

Scoring was not performed

Score history

Overall score trend

First recorded score · v2 rubric

39/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	39	<=2025-11-25	v2