response-rater

github:oimiragieo/agent-studio · first committed 2026-01-05 · source · badge

Run headless AI CLIs (Claude Code, Gemini, OpenAI Codex, Cursor Agent, GitHub Copilot) to rate an assistant response against a rubric and return actionable feedback plus a rewritten improved response; use for response quality audits, prompt/docs reviews, and "have another AI critique this answer" workflows.

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

14 commits to this file on GitHub (newest first).

2026-04-21 · commit 406628a · feat(release): v2.3.0 — durability, observability, guardrails
2026-03-06 · commit a2fda7f · chore: clean up remaining session artifacts
2026-03-06 · commit bb0e4dd · chore: add markdownlint-cli2 and auto-fix markdown formatting
2026-02-23 · commit 743232a · chore: update hooks, lib, skills, tools, docs, workflows, templates, schemas
2026-02-19 · commit dab4907 · chore: checkpoint all in-progress workspace changes
2026-01-27 · commit ee965fe · chore: framework updates and YAML syntax fix
2026-01-27 · commit 50b6418 · feat: major framework consolidation and .cjs file tracking
2026-01-23 · commit 91bfe7c · fix: resolve critical audit findings
2026-01-15 · commit 0cca2bc · feat: reorganize project structure and integrate Router Session Handler
2026-01-13 · commit a24522c · docs: add implementation artifacts and manifests
2026-01-11 · commit ea2291b · feat: add PR workflow, error logging, prettier, and optimize CLAUDE.md
2026-01-09 · commit 5992cd4 · docs: update README and GETTING_STARTED with Codex skills integration
2026-01-07 · commit e5f5d4e · docs: update CUJs and workflows with standardized format
2026-01-05 · commit 004be9d · chore: Major cleanup and CUJ validation fixes

Archived snapshots