DaveGold

Eval Inline Instruction — Data & AI agent for Claude Code

Data & AI community

Eval arm inline-instruction (Q4 — the CALCULATED vs MEASURED line reduced to its INSTRUCTION half: what to output, with no reason given).

How to install Eval Inline Instruction

Installs to ~/.claude/agents/davegold-mcp-metadata-demo-eval-inline-instruction.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/DaveGold/mcp-metadata-demo/HEAD/.claude/agents/eval-inline-instruction.md -o ~/.claude/agents/davegold-mcp-metadata-demo-eval-inline-instruction.md

Restart Claude Code, or start a new session, for it to be picked up.

What Eval Inline Instruction does

name: eval-inline-instruction description: Eval arm inline-instruction (Q4 — the CALCULATED vs MEASURED line reduced to its INSTRUCTION half: what to output, with no reason given). Answers one building-data question using ONLY the eval-inline-instruction MCP server. Not for general use — spawned by the run-eval skill. tools: mcp__eval-inline-instruction__get_building_profile, mcp__eval-inline-instruction__get_weather_context, mcp__eval-inline-instruction__render_chart, mcp__eval-inline-instr

Alternatives in Data & AI

  • Omd Slop Auditor — 실제 제품 route와 코드를 함께 읽어 context-free UI/copy pattern cluster를 rule ID·line ref·route evidence로 진단한다 465 ★
  • Rlm Subcall — Acts as the RLM sub-LLM (llm_query) 382 ★
  • Reverse SQL Function Analyst — Spécialiste des FONCTIONS SQL (scalaires, inline, table) du reverse base de données 193 ★

Full documentation available on GitHub

View Source Repository

Related Agents

Eval Inline Fact — Data & AI agent for Claude Code

Eval Inline Fact

Eval arm inline-fact (Q4 — the CALCULATED vs MEASURED line reduced to its FACT half: what the quantities are,

Data & AI community
Eval Inline Oneline — Data & AI agent for Claude Code

Eval Inline Oneline

Eval arm inline-oneline (Q14 — words' description byte for byte, PLUS one sliced INTERPRETATION line in the re

Data & AI community
Triage TS — Data & AI agent for Claude Code

Triage TS

LLM instruction for the TypeScript orchestrator triage role. Receives a task description, project structure sn

Data & AI community
Wikiskill Grader — Data & AI agent for Claude Code

Wikiskill Grader

Strict LLM-judge grader — given a task's success criteria and an inference agent's transcript/final answer, re

Data & AI community
Danger Zones - Always Flag These: — Data & AI agent for Claude Code

Danger Zones - Always Flag These:

pool size reduced (can cause connection starvation) - pool size dramatically increased (can overload database)

Data & AI community
Usage Scout — Data & AI agent for Claude Code

Usage Scout

Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage

Data & AI community

Related Skills

Handover Arm Resume — Productivity skill for Claude Code

Handover Arm Resume

Arm the OS scheduler to relaunch claude at the given time with the given handover. Dedup-guarded. Direct schta

Productivity community
Jev Brig — Development skill for Claude Code

Jev Brig

A Claude Code hook that judges Bash commands against a session policy level, and answers allow/ask/deny with a

Development community
Instruct — Development skill for Claude Code

Instruct

Perform an instruction, given as an instruction file, a file plus its argument, or a description typed in the

Development community