360 Secure SkillHub
360 安全技能中心

challenge

读取本地知识库与挑战状态,按自适应权重生成代码库知识题,评估开发者回答并更新连续答对记录;通过时写入令牌,失败时给出解析并继续出题。

athola
athola
热度 62.82
最近更新 2026-08-26 21:12:21
分类:知识依赖:代码执行 / 读写文件 / 内部调用大模型应用场景:测验 / 概念解释

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add nm-gauntlet-challenge
Metadata
name
challenge
description
Presents adaptive codebase challenge questions with multiple-choice and trace exercises
version
1.9.8
triggers
["testing contributor knowledge of the codebase"]
metadata
{"openclaw":{"homepage":"https://github.com/athola/claude-night-market/tree/master/plugins/gauntlet","emoji":"🦞"}}
source
claude-night-market
source_plugin
gauntlet

Night Market Skill — ported from claude-night-market/gauntlet. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Run Gauntlet Challenge

Present challenges from the knowledge base and evaluate answers.

In-Loop Provider Setup

Before generating a challenge, register the in-loop variation provider so we do not call out to the Anthropic API just to spawn a sibling Claude (issue #464). Outside Claude Code this is a no-op and the default Anthropic provider remains active.

from gauntlet.providers.in_loop import (
    register_in_loop_provider_if_inside_claude_code,
)
register_in_loop_provider_if_inside_claude_code()

Steps

  1. Load state: read .gauntlet/knowledge.json and developer progress

  2. Check for pending challenge: if .gauntlet/state/pending_challenge.json exists, evaluate the developer's most recent message as an answer before generating a new one

  3. Generate challenge: use adaptive weighting to select a knowledge entry and challenge type

  4. Present challenge: show the question with context

  5. Evaluate answer: score the response (pass/partial/fail)

  6. Record result: update developer progress and streak

  7. On pass: write pass token if from pre-commit gate. Show next challenge if in session.

  8. On fail: show correct answer with explanation. Present a new challenge.

Scoring

Result Score Streak
Pass 1.0 +1
Partial 0.5 reset
Fail 0.0 reset