Add Eval — AI skill for Claude Code
Add automated eval (LLM-as-judge or deterministic) for an AI-powered feature.
How to install Add Eval
Installs to ~/.claude/commands/srikanthvemulapally-ai-native-boilerplate-add-eval.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/SrikanthVemulapally/ai-native-boilerplate/HEAD/.claude/commands/add-eval.md -o ~/.claude/commands/srikanthvemulapally-ai-native-boilerplate-add-eval.md Restart Claude Code, or start a new session, for it to be picked up.
What Add Eval does
name: add-eval description: Add automated eval (LLM-as-judge or deterministic) for an AI-powered feature user-invocable: true
Add eval for: $ARGUMENTS
What Are Evals?
Evals are automated tests that measure the quality of AI-powered outputs. Unlike unit tests (pass/fail on exact output), evals measure:
- Accuracy (is the answer factually correct?)
- Relevance (does it answer what was asked?)
- Format compliance (does it follow the output schema?)
- Safety (does it refuse harmful req
Alternatives in AI
- Surface — Show ranked attack surface for a target from its recon manifest + hunt memory 3.8k ★
- Launch An AI Feature — Workflow recipe — take an AI/LLM feature from a probabilistic-aware PRD to a launch-ready model card by chaini 1.3k ★
- Module Feature — Add a new feature (model + service + controller + views + routes + tests) to an existing module 407 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Design AI Feature
Design an AI-powered feature end-to-end — model selection, prompt architecture, eval framework, failure modes,
Eval From Trace
Build an LLM-as-a-Judge eval grounded in real traces from the Progress Observability Platform.
Ground Truth Evals
An LLM eval harness graded by computed ground truth, not an LLM judge. Worked example: poker, served to models
Agent Eval Workbench
MLflow-based evaluation kit for AI agents: golden-task runner, calibrated LLM judge, list-price cost accountin
Evolve Skill
SPIKE — GEPA/DSPy-style offline A/B evolution of ONE prompt-only skill's SKILL.md body against a small fixture
Harness Lint
Run the quality lint (advice rules + system-level analysis) on the agent setup; add --all for every one of the
Related Agents
Askit Quality Grader
Judges whether a skill triggers and behaves correctly by running it against its eval-set and grading the outpu
LLM Evaluator
LLM evaluation specialist. Use when designing eval suites for LLM features, calibrating LLM-as-judge prompts,
Pest Tester
Use this agent when you need to write, extend, or fix automated tests for a Laravel application — e.g. "write
