Agent skill · data analytics · yonatangross
bare-eval
Isolated eval and grading calls with claude -p in bare mode, free of plugin and hook interference. Use when grading skill outputs, benchmarking prompts or testing trigger accuracy.
Why this skill is useful
Adds specific command patterns and grading schemas for isolated evaluation that the AI wouldn't reliably generate on its own.
What it needs
Requires jq installed locally. Requires anthropic account access. About 5k tokens when loaded. Last updated 2026-08-06. 215 stars on the source repository.
What this skill does
Bare Eval — Isolated Evaluation Calls Run claude -p --bare for fast, clean eval/grading without plugin overhead. CC 2.1.81 required. The --bare flag skips hooks, LSP, plugin sync, and skill directory walks. When to Use Grading skill outputs against assertions Trigger classification (which skill matches a prompt) Description optimization iterations Any scripted -p call that doesn't need plugins When NOT to Use Testing skill routing (needs --plugin-dir) Testing agent orchestration (needs full plugin context) Interactive sessions Prerequisites Quick Reference Call Type Command Pattern ----------- ---------------- Grading claude -p "$prompt" --bare --max-turns 1 --output-format text Trigger claude -p "$prompt" --bare --json-schema "$schema" --output-format json Streaming grade claude -p "$prompt" --bare --max-turns 1 --output-format stream-json Optimize echo "$prompt" \ claude -p --bare --max-turns 1 --output-format text Force-skill claude -p "$prompt" --bare --print --append-system-prompt "$content" @-file in prompt claude -p "grade @fixtures/case-1.md against rubric" --bare (CC 2.1.113 Remote Control autocomplete) Long harness runs (CC 2.1.199+): set CLAUDECODERETRYWATCHDOG=1 for unattended eval batches: it raises the default retry count for non-capacity transient errors to 300 and lifts the cap of 15 on CLAUDECODEMAXRETRIES, so an overnight grading run survives transient API blips instead of dying mid-batch. Pair it with the three caps so a batch neither waits out a 429 storm nor sits hours on a usage limit: CLAUDECODERETRYWATCHDOGMAXWAITMS (2.1.295), CLAUDECODERETRYWATCHDOGMAXUSAGELIMITWAITMS (2.1.301) and CLAUDECODERETRYWATCHDOGUSAGELIMITRECHECKMS (2.1.305); doctor's operator-permissions check offers any that are missing. --output-format stream-json Newline-delimited JSON events (one per token/tool-call) — lets a runner score partial output or abort early on a failing probe without waiting for the full response. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills yonatangross/bare-eval