OpenParable
Skip to content
← Back to skills

Bug Hunter Stage4 Consensus Judge

Testing & Quality
bug-hunter-stage4-consensus-judge

Bug Hunter Stage4 Consensus Judge is an Agent Skill for testing & quality published in the DragonOS-Community/DragonOS repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

bug-hunter 阶段 4 技能。负责对缺陷桶执行加权共识投票,筛选过阈值问题,并输出裁决级结构化评审报告。

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/DragonOS-Community/DragonOS/blob/HEAD/.agents/skills/bug-hunter/subskills/bug-hunter-stage4-consensus-judge/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/bug-hunter-stage4-consensus-judge, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Stage 4 共识裁决

步骤

  1. 读取 artifacts/buckets.json。
  2. 根据 persona 权重运行 scripts/weighted_vote.py --threshold 0.6。
    • 默认从 references/persona_matrix.json 读取权重。
    • 可用 --weights 叠加历史学习权重(兼容扁平映射与 suggested_weights 包装格式)。
  3. 运行 scripts/render_report.py 生成 Markdown 报告。
  4. 输出:
    • artifacts/verdict.json
    • artifacts/bug_hunter_report.md

裁决规则

  • 仅保留加权分数超过阈值的问题。
  • 对没有 fix_code 的条目额外惩罚 10%。
  • 严重级别排序:critical > major > minor。