Agentic Eval — Development skill for Claude Code
Niche-agnostic agentic evaluator using CLEAR v2.0 framework — 6-domain assessment, 8 analysis dimensions, 6-tier source prioritization, evidence strength ratings, and decision trees.
How to install Agentic Eval
Installs to ~/.claude/commands/shaheerkhawaja-productionos-agentic-eval.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ShaheerKhawaja/ProductionOS/HEAD/.claude/commands/agentic-eval.md -o ~/.claude/commands/shaheerkhawaja-productionos-agentic-eval.md Restart Claude Code, or start a new session, for it to be picked up.
What Agentic Eval does
name: agentic-eval description: "Niche-agnostic agentic evaluator using CLEAR v2.0 framework — 6-domain assessment, 8 analysis dimensions, 6-tier source prioritization, evidence strength ratings, and decision trees. Evaluates any plan, codebase, or research output." arguments:
- name: target description: "What to evaluate: a file path, directory, or 'latest' for most recent pipeline output" required: false default: "latest"
- name: domain description: "Evaluation domain o
Alternatives in Development
- Prioritization Frameworks — Reference guide to 9 prioritization frameworks with templates 7.8k ★
- Battle — Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line 3.6k ★
- Godogen Source Repo — This repository contains two source trees for the same project: - claude/ — Claude Code source tree - codex/ 2.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Salesforce Oob Evaluator
A Claude skill that evaluates Salesforce business requirements against Out-of-the-Box (OOB) native features ,
Agent Session State
Durable, runtime-agnostic agent session state for React: approvals that survive reload, resumable streams, sub
Polywave Go
Provider-agnostic parallel agent coordination for LLMs — Anthropic, OpenAI, Ollama, or any OpenAI-compatible e
Phdtaketaketake
Connection-first PhD advisor matcher — find the right advisor by network strength, not h-index. Quantitative 4
Suunto Gym
Personalized strength-training coach for Claude Code — progressive-overload programming, Suunto recovery gatin
Pharn Dev Plan
Plan ONE increment of PHARN. Discovery-first, grounded in live state, pins the architecture content-hash, halt
Related Agents
Paper Implementer
Writes one file of a paper reproduction from its logic analysis, then compiles, imports and tests it. Use for
Book Evaluator
Independent evaluator for the book pipeline. Scores chapters it did NOT write using Genesis Score (7 dimension
Gsd Eval Planner
Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dime