eval-debate

eval-debate is a skill for Claude Code, Codex from YIKUAIBANZI/forge-skill. It costs 49 tokens per session (1,564 once invoked), scanned A, original, MIT.

A Chinese-language test procedure for evaluating debates between simulated versions of the same person. It uses a persona and three decision scenarios, then produces a scored quality report.

In plain words
What is it for?
Use it to load test cases and persona details, run independent analyses, challenge them, combine the results, and score the debate across five dimensions.
Why use it?
It provides a structured way to find weak reasoning, hidden assumptions, contradictions, or poor synthesis in those simulated debates.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to load test cases and persona details, run independent analyses, challenge them, combine the results, and score the debate across five dimensions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yikuaibanzi/forge-skill/eval-debate
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add YIKUAIBANZI/forge-skill --skill eval-debate
Clone the repo
git clone --depth 1 https://github.com/YIKUAIBANZI/forge-skill

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for eval-debate

README.md
[![agentmods](https://agentmods.dev/badge/skills/yikuaibanzi/forge-skill/eval-debate/github.svg)](https://agentmods.dev/skills/yikuaibanzi/forge-skill/eval-debate)
Your own site
<a href="https://agentmods.dev/skills/yikuaibanzi/forge-skill/eval-debate"><img src="https://agentmods.dev/badge/skills/yikuaibanzi/forge-skill/eval-debate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for eval-debate

Your own site · 80×15
<a href="https://agentmods.dev/skills/yikuaibanzi/forge-skill/eval-debate"><img src="https://agentmods.dev/badge/skills/yikuaibanzi/forge-skill/eval-debate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,564 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01564
Opus 5 $0.00024 $0.00782
Sonnet 5 $0.00010 $0.00313
Haiku 4.5 $0.00005 $0.00156

Measured 9d ago against content hash ae5412f55227, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

eval-debate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

evals/eval-debate/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/eval-debate — 替身会议辩论质量评测

你的任务是对 use-self 替身会议的输出质量做一次系统性评测,全程在当前对话中完成,不需要调用任何外部 API


Step 0:加载测试资源

  1. 读取测试用例文件:evals/test_cases/debate_quality_cases.yaml
  2. 根据 persona_name 字段,读取对应 persona: personas/self/{persona_name}/persona.json
  3. 提取 decision-card 关键内容:
    • L0 底线(bottom_line)
    • L2 语言风格(language_style + signature_phrases)
    • L3 决策参数(8 个维度的分值)
    • L4 价值观与盲区(blind_spots + emotional_triggers)
正在加载 {persona_name} 的 persona 和测试用例...
共 {N} 个决策场景待测试。

Step 1:逐场景运行辩论

对每个测试用例,执行完整三阶段流程:

Phase 1:并行独立分析(3 个变体)

基于 decision-card 中的 L3 参数,生成 3 个变体并各自独立分析:

变体设置(固定,评测用):

  • 🔵 稳健的你:risk_appetite -3,action_bias -2,loss_aversion +2
  • 🟢 果断的你:risk_appetite +3,action_bias +3,information_need -2
  • 🔴 长线的你:time_horizon +4,loss_aversion -2,action_bias +1

每个变体按 use-self/prompts/phase1_independent.md 的格式输出:

  • 【我的判断】:明确表态,不能含糊
  • 【为什么】:≤3 个具体理由
  • 【我最担心的是】:具体情境
  • 【我最期待的是】:具体情境
  • 【我想问自己】:一个核心问题

信息隔离:每个变体只能看到自己的参数偏移,不知道其他变体说了什么。

Phase 2:质询

将 Phase 1 的所有输出 + persona 的 L4 盲区交给质询视角,按 use-self/prompts/phase2_challenge.md 执行:

  • 对每个变体找出最尖锐的质疑(隐含假设/幻觉/回避)
  • 识别跨变体矛盾
  • 用 L4 盲区做最后一问

Phase 3:综合

use-self/prompts/phase3_synthesis.md 生成综合报告,使用用户的 L2 语言风格。


Step 2:评分

每个场景跑完后,立刻按 5 个维度评分(每项 0-20 分):

维度 评分标准
变体区分度 Phase 1 的 3 个变体立场是否有实质性差异?都说"两边各有道理"= 0 分;立场明确对立且理由具体 = 满分
质询深度 Phase 2 是否指出了具体假设和盲区?"你没考虑到..." = 低分;"你说的 X 假设了 Y,但 Y 不成立,因为 Z" = 高分
参数一致性 各变体的发言是否与偏移后的参数一致?稳健变体的发言是否明显更保守?
综合覆盖度 Phase 3 是否有代价清单?是否提出了具体的待搞清楚的问题?还是只是 Phase 1 的复述?
用户语言风格 所有输出语气是否符合 persona 的 L2?出现"综上所述"、"建议您"等顾问句式扣分

参照测试用例的 expected_variant_stances 和 evaluation_criteria 给分。


Step 3:输出报告

所有场景跑完后,输出评测报告:

===================================
替身会议辩论质量评测报告 — {persona_name}
===================================

## 逐场景结果

### [d01] {场景标题}

**Phase 1 摘要:**
- 🔵 稳健的你:{判断一句话}
- 🟢 果断的你:{判断一句话}
- 🔴 长线的你:{判断一句话}

**Phase 2 质询摘要:**
{最有价值的一条质疑}

**Phase 3 综合摘要:**
{代价清单里最关键的一条}

**评分:{total}/100**
  ✅/⚠️ 变体区分度:{score}/20 — {说明}
  ✅/⚠️ 质询深度:{score}/20 — {说明}
  ✅/⚠️ 参数一致性:{score}/20 — {说明}
  ✅/⚠️ 综合覆盖度:{score}/20 — {说明}
  ✅/⚠️ 用户语言风格:{score}/20 — {说明}

### [d02] ...
### [d03] ...

---

## 汇总

平均分:{avg}/100

各维度平均:
  变体区分度    {avg}/20
  质询深度      {avg}/20
  参数一致性    {avg}/20
  综合覆盖度    {avg}/20
  用户语言风格  {avg}/20

## 主要问题
{失分最多的维度 + 具体表现}

## 建议
{针对失分维度的改进方向,指向哪个 prompt 文件或 persona 层级需要调整}

Read the full file on GitHub · 158 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 158 lines · 49 tokens per session scan A ae5412f55227

Subscribe to this mod's changes

eval-debate is a skill published in the GitHub repository YIKUAIBANZI/forge-skill (116 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 1,564 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

weak-agent-test

Run the weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced runs) to perform real document tasks over six scenarios — five editing (MNDA form-fill + font fidelity, invoice table-edit/restructure + logo replace…

kklimuk/docx-cli · 218 tokens

declaring-invariants

Find tests that enumerate a domain by copying it, and declare the invariants a codebase depends on. Reports where a parametrize list, for-loop, or it.each iterates a hand-written subset of a dict/set/tuple/Enum that exists in the source, and names the members nothing covers. Use when reviewing tests, when a module…

oaustegard/claude-skills · 175 tokens

gating

Build and audit deterministic verification gates — a check that blocks a pipeline and can be shown to go red. Use when writing a calibration gate, CI check, validation script or pre-publication check for a numeric or empirical result; when a plausible-but-wrong value would survive review; when asking whether an…

oaustegard/claude-skills · 137 tokens

change-request-to-go-live-protocol

Use this skill when a Dynamics 365 change request must be structured and progressed through impact assessment, fit-gap analysis, UAT sign-off, go/no-go decision, go-live execution, and hypercare using the Success by Design framework. Defines the full change-to-go-live flow — change request intake, solution blueprint…

VincentChuWaiChow/vanguard-frontier-agentic · 147 tokens

environment-to-production-release-protocol

Use this skill when a Power Platform or Dynamics 365 solution must progress through a structured dev-to-test-to-production release pipeline using managed solutions and Power Platform pipelines, when rollback readiness must be verified before go-live, or when a deployment approval gate must be enforced. Defines the…

VincentChuWaiChow/vanguard-frontier-agentic · 128 tokens

erp-crm-cutover-protocol

Use this skill when a Dynamics 365 ERP or CRM implementation is approaching go-live and must progress through mock migration, data reconciliation, cutover runbook execution, rollback testing, and the Success by Design go-live gate before production switchover. Orchestrates d365-data-migration-cutover-agent as primary…

VincentChuWaiChow/vanguard-frontier-agentic · 148 tokens