Development · Agent evaluation and testing

Runs a reference agent (Codex or Claude Code) and Qwen Code on the same scenario, captures HTTP and terminal traces, and compares them until behavior matches.

QwenLM/qwen-code

Run and maintain Con's terminal-agent benchmark against a live app session.

nowledge-co/con-terminal

A skill your agent uses when the user's Copilot Studio agent evaluations have come back and they need to interpret scores, diagnose root causes of underperforming test cases, find remediation steps…

microsoft/eval-guide

Points agents to the right sources when changing the Smithers workspace graph, generated docs, benchmark and eval evidence, or durable flows in the Smithers repository.

smithersai/smithers

Analyzes a finished pull request that involved an agent to find what slowed or helped it, and recommends specific changes to instruction files, skills and docs.

dotnet/maui

A skill your agent uses when my-pi-agent tests, typecheck, lint, Pi CLI startup, OpenCode/MCP, Feishu channel, prompt rendering, memory/state, web-console/desktop build, or UI behavior fails…

skuramatata/my-pi-agent

A skill your agent uses when my-pi-agent tests, typecheck, lint, /code workflow, verifier probes, Feishu channel handling, MCP bootstrap, skill install, or task resume behavior fails unexpectedly.

skuramatata/my-pi-agent

法律 Skill 分层质量评测工具。消费 skill-lint 的通用质量结论，再用三份测试材料、通用六维度、场景微调和律师 taste 评估法律产出，并定位最小修复单元。本技能应在审查、回归验证或发布验收法律 Skill 时使用。不要用于代替通用 Skill lint、正式法律意见或跨场景排名。

cat-xierluo/legal-skills