magiclf-ai/agentic-ida-pro/judge-reverse-quality

Claude Code and agent skill by magiclf-ai/agentic-ida-pro

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

在 run 已结束、需要判断修改是变好持平还是变差、需要根据纯文本证据复判，或补跑 judge-only 时使用。

Install

npx vskill@latest install magiclf-ai/agentic-ida-pro/judge-reverse-quality

SKILL.md

judge-reverse-quality

触发条件

  • run 已结束，需要判断这次修改是变好、持平还是变差
  • 需要根据纯文本证据复判
  • 需要补跑 --judge-only

使用步骤

  1. 先读取当前 case 的：
  • evidence.md
  • run_trace.md
  • verdict.md
  • .eval_state/watch.log
  • .eval_state/stderr.log
  1. 若有 baseline，再对照 baseline 的同类文件
  2. 同时回看源码和 focus_points，避免只看摘要
  3. 按 profile 判断：
  • struct_recovery：布局、字段、类型传播、注释沉淀
  • attack_surface：入口、危险链、参数控制点、证据链完整性
  • general_reverse：行为摘要、数据流、调用链归纳、结论一致性
  1. 最终输出必须采用伪 tool 结构：
text
submit_eval_verdict(
  verdict=pass|partial|fail|infra_fail,
  summary=一句话结论,
  evidence=2-4条关键证据,
  risks=残留风险或缺口
)

命令入口

bash
cd /mnt/d/reverse/agentic_ida_pro
export PYTHONPATH=src
 
/mnt/d/reverse/agentic_ida_pro/.venv/bin/python -u src/entrypoints/eval_runner.py \
  --judge-only logs/eval_runs/<run_id>

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
61
Repository forks
11
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/magiclf-ai/agentic-ida-pro/judge-reverse-quality/badge)](https://verified-skill.com/skills/magiclf-ai/agentic-ida-pro/judge-reverse-quality)

Something wrong with this skill or its page? Tell us.