evals commands

83 tagged evals, measured the same way as everything else here.

Browse within: chunking 60docker 60fast-api 60Chatbots 15javascript 15

changeset

01

mastra-ai/mastra

Command Claude Code

../../.mastracode/commands/changeset.md.

28k +33 today A 0 tokens

commit

02

mastra-ai/mastra

Command Claude Code

../../.mastracode/commands/commit.md.

28k +33 today A 0 tokens

gh-triage

03

mastra-ai/mastra

Command

GitHub OSS maintainer lifecycle triage, review, and approval management.

28k +33 today A 19 tokens

skillforge

04

tripleyak/SkillForge

Command

Route, create, improve, or inspect reusable AI skills with SkillForge.

884 1mo ago A 14 tokens original MIT

fable-eval

05

rennf93/opus-fable-playbook

Command

Run the fable-mode eval suite (probes → pairwise judge → report). Costs tokens — runs headless claude many times. Optional arg: a probe id substring to filter.

33 2mo ago A 38 tokens original MIT

triage-sweep

07

macanderson/stella

Command

Sweep a repo's triage-labeled backlog — vet every issue against the code, fix the easy ones in one cleanup PR, and label the rest priority → area → descriptors, with epics grouped and ranked. Repo-agnostic: discovers each repo's label taxonomy at runtime.

9 yesterday A 0 tokens AGPL-3.0

self-driving

08

macanderson/stella

Command

One cycle of the perpetual delivery loop — size to the machine, fix a batch, audit, file what you cannot fix, benchmark against Claude Code, ship, recalibrate. Never terminates.

9 yesterday A 39 tokens AGPL-3.0

review-pr

10

Abhillashjadhav/AI-PM-essential-skills

Command Claude Code

You are the PR review agent for Abhillash's repos. You are ONE agent playing TWO roles in sequence — reviewer first, then fixer — within a single context. There are no subagents. Do not invoke the Task tool.

2 yesterday A 0 tokens original MIT

code-review-swarm

12

amangit1314/repo-rag

Command Claude Code

Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.

0 1mo ago A 0 tokens

multi-repo-swarm

13

amangit1314/repo-rag

Command Claude Code

Coordinate AI swarms across multiple repositories, enabling organization-wide automation and intelligent cross-project collaboration.

0 1mo ago A 0 tokens

release-manager

14

amangit1314/repo-rag

Command Claude Code

Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages.

0 1mo ago A 0 tokens