~ / leaderboard / skill / grade
Skill · #3424
grade
Outcome-based grading loop - define a rubric, have a fresh-context grader evaluate the work against it, and revise until it passes. Use when the user says "grade this", "grade it against...", or wants
5rigs use it
0%of all rigs
1.2kavg rig context tax
Get it
$ npx degit Apurv-ed/best-claude-code-setup/plugins/ap-optimal-claude/skills/grade .claude/skills/grade From the most-starred rig that ships it: Apurv-ed/best-claude-code-setup. Same-named skills in different rigs may differ — review before use.
Often used together with
grill-me · 1handoff · 1commands · 1end-session · 1fix-loop · 1project-docs · 1release · 1skill-eval · 1design-review · 1review-change · 1
Rigs using grade (5)
davidscotttufts/hyvemind
Evidence-gated, model-adaptive SDLC skills for any coding agent, plus a CLI that proves each skill still beats the bare model.
Skill Collector 1.3k tok · · Q0
Fermion-company/scoring64-plugins
Scoring64(塾のデジタル採点システム・電子採点ソフト)を ChatGPT/Codex・Claude Code から操作して採点するプラグイン
Pragmatist 309 tok · · Q0
lukevin202106-hub/gsat-essay-grader
學測國文、英文作文批改器:用你自己的 Claude 批改作文(Claude Code 外掛)。估分、逐句挑錯或眉批、兩版改寫,產生一頁網頁。
Minimalist 317 tok · · Q0
Katawwr/Fusion-First
Measure and guard AI agents. OWASP-mapped attacks, a grader whose accuracy is checked every run, and a runtime guardrail that blocks unrequested tool calls. Built for open-weight models.
Pragmatist 2.9k tok · · Q0
Apurv-ed/best-claude-code-setup
A safe, current, one-command Claude Code setup: settings, guardrails, skills and hooks.
Skill Collector 928 tok · · Q0