convez.ai
SkillDados & AnalyticsAvançado
jedilpf

AudienceLens Harness

jedilpf/audiencelens-harness

Simule painéis de audiência sintéticos com avaliação estruturada em 8 dimensões

Ver no GitHub
InicialPluginScore · de 0 a 100

Pack de skills para multi-agentes que simula painéis sintéticos de audiência para avaliar games, produtos e ideias antes de testes reais. Inclui 4 skills de review com sistema de qualidade de 8 dimensões, personas comportamentais e red-teaming adversarial.

Instalação

$npx convez-ai jedilpf/audiencelens-harness

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Validar conceitos de games e produtos sem usuários reais
  • Identificar riscos e conflitos de segmentação em landing pages e SaaS
  • Red-teaming adversarial para cenários de falha e colapso de confiança
  • Gerar personas reutilizáveis baseadas em comportamento para painéis customizados

Veredito

Ferramenta bem estruturada para síntese de feedback de audiência com rigor metodológico (8 dimensões de qualidade, personas comportamentais, red-teaming). Útil para validação pré-lançamento, mas requer curva de aprendizado e interpretação cuidadosa dos limites de feedback sintético vs. real.

README

A tradução para o português deste README ainda está na fila.

AudienceLens Harness

Open-Source Multi-Agent Synthetic Audience Review Skill Pack with Quality Harness

License: MIT Version Skills

开源多智能体合成观众评审技能包 · 含8维质量评估体系

English · 中文


Overview

AudienceLens Harness is a self-contained, zero-dependency skill pack that enables Claude Code / Trae AI / Cursor-style agents to simulate diverse audience panels for reviewing games, products, landing pages, DevLogs, startup ideas, and creative projects — before committing resources to real user testing.

Unlike simply asking an LLM for feedback, AudienceLens runs multiple behavior-driven personas in isolation, then applies structured cross-examination on top-3 controversies, tracks stance revisions with full provenance, and validates output quality through an 8-dimension Harness.


Feature Categories

1. Skill System — Four Review Modes

SkillCommandUse Case
synthetic-playtest/synthetic-playtest <input> [--focus] [--panel] [--count] [--harness]Game-focused synthetic player panel — Steam pages, demos, concepts, monetization
audience-panel/audience-panel <input> [--focus] [--panel] [--count] [--harness]General product / app / landing-page / SaaS audience review
red-team-audience/red-team-audience <input> [--intensity] [--mode] [--harness]Adversarial stress test — failure modes, worst-case scenarios, trust collapse
persona-generate/persona-generate <input> [--count] [--market]Generate reusable persona panels as schema-compliant YAML

2. Harness Quality Gate — 8 Evaluation Dimensions

The Harness is what differentiates AudienceLens from a prompt pack. It provides a repeatable, rubric-based quality check for every generated report.

#DimensionWhat It ChecksScore Range
1Persona DifferentiationDo personas produce distinct perspectives, or are they interchangeable?0–3
2Input GroundingIs feedback anchored in actual input materials, or is it generic advice?0–3
3ActionabilityDoes the report include concrete P0/P1/P2 fixes, or only vague suggestions?0–3
4Segment ConflictAre genuine disagreements between audience segments surfaced?0–3
5Risk DetectionAre critical risks and blockers identified and prioritized?0–3
6Ethical Persona UseAre demographics/MBTI used as weak modifiers only — never as deterministic stereotypes?0–3
7Report StructureDoes the report include all required sections per the schema?0–3
8Calibration HonestyDoes the report frame findings as hypotheses, not predictions?0–3

Critical Failures (automatic fail, regardless of total score):

  • No AI-generated disclaimer present
  • No P0/P1/P2 prioritized actions
  • Personas produce identical feedback
  • Feedback is not grounded in input
  • Gender/MBTI used as deterministic stereotype
  • Claims real-world success prediction

3. Persona System — Behavior-Driven Design

Personas are defined by behavioral vectors, not demographic labels. Research (SCOPE study) shows demographics explain only 1.5% of behavioral variance.

Each persona includes:

  • Behavior profile — patience, domain knowledge, novelty seeking, risk tolerance, etc.
  • Decision rules — explicit criteria for positive/negative evaluation
  • Quit triggers — conditions under which the persona would disengage
  • Continue triggers — conditions that sustain engagement
  • Must-comment-on — mandatory evaluation topics per persona role

4. Ethics Framework — Built-In Safeguards

PrincipleImplementation
Identity-Behavior DecouplingGender, age, region are weak style modifiers only — never causal predictors
MBTI De-authorizationMBTI modifies expression style only — never core judgment logic
Evidence Tiering[direct] / [inferred] / [gap] — inferred evidence capped at 40%
No FabricationPersonas must not invent missing features, plot, multiplayer, or monetization details
Mandatory DisclaimerEvery report includes "AI-generated synthetic review — not real user research"

5. Panel Presets — Pre-Configured Audience Panels

PresetFileComposition
game-mixedpersona-panels/game-mixed.yamlBalanced mix of core, casual, and critical game personas
game-steam-pagepersona-panels/game-steam-page.yamlSteam browsing behavior specialists
red-team-defaultpersona-panels/red-team-default.yamlAdversarial attackers for stress testing

6. Report Templates — Structured Output

TemplateSkillKey Sections
synthetic-playtest-report.mdsynthetic-playtestExecutive conclusion, player panel, consensus findings, risks & opportunities, priority fixes
audience-panel-report.mdaudience-panelSegment summary, consensus, disagreements, actionable recommendations
red-team-audience-report.mdred-team-audienceMust-fix issues, can-ignore items, counter-measures, worst-case scenarios

Quick Start

Install as Claude Code Skill

# Copy skill files to your project's Claude config
cp -r .claude/skills/* /path/to/your-project/.claude/skills/

# Or install globally (all projects)
cp -r .claude/skills/* ~/.claude/skills/

# Windows (PowerShell)
# Copy-Item -Recurse .claude/skills/* -Destination $env:USERPROFILE\.claude\skills\

Run a Review

# Game review with mixed panel
/synthetic-playtest examples/game-demo-review-input.md --focus onboarding --panel mixed

# Product / landing page review
/audience-panel examples/landing-page-review-input.md --focus positioning

# Red-team adversarial review
/red-team-audience examples/game-demo-review-input.md --intensity high

# Generate custom personas
/persona-generate --count 6 --market game

Harness Evaluation Workflow

Run skill on fixture → Generate report → Evaluate with rubric → Identify weak dimensions → Revise skill/persona/template → Re-run

Repository Structure

audiencelens-harness/
├── .claude/
│   ├── skills/                        # 4 Claude Code Skills
│   │   ├── synthetic-playtest/        #   Game synthetic playtest
│   │   ├── audience-panel/            #   General product review
│   │   ├── red-team-audience/         #   Red-team attack review
│   │   └── persona-generate/          #   Persona YAML generator
│   └── docs/
│       ├── persona-panels/            # Panel presets (YAML)
│       │   ├── game-mixed.yaml
│       │   ├── game-steam-page.yaml
│       │   └── red-team-default.yaml
│       └── templates/                 # Report templates (Markdown)
│           ├── synthetic-playtest-report.md
│           ├── audience-panel-report.md
│           └── red-team-audience-report.md
├── harness/                           # Quality Harness
│   ├── evaluators/                    # 5 evaluation criteria (Markdown)
│   │   ├── actionability.md
│   │   ├── input-grounding.md
│   │   ├── persona-differentiation.md
│   │   ├── stereotype-check.md
│   │   └── structure-check.md
│   ├── rubrics/                       # Scoring rubric
│   │   └── audience-review-rubric.md
│   ├── expected/                      # Required report sections
│   │   └── synthetic-playtest-required-sections.yaml
│   └── fixtures/                      # Test fixtures
│       ├── game-concept-cyber-scavenger.md
│       └── weak-game-concept.md
├── personas/                          # Persona definitions
│   ├── game/                          # Game personas (YAML)
│   │   ├── core-indie-player.yaml
│   │   ├── steam-browser.yaml
│   │   └── visual-first-player.yaml
│   ├── schemas/                       # Persona schema
│   │   └── persona.schema.yaml
│   └── ethics.md                      # Ethics guidelines
├── docs/                              # Documentation
│   ├── methodology.md
│   ├── hosted-version.md
│   └── roadmap.md
├── examples/                          # Example inputs
│   ├── game-demo-review-input.md
│   └── landing-page-review-input.md
├── README.md
├── LICENSE                            # MIT
└── .gitignore

Roadmap

VersionFocusStatus
v0.1Skill Pack (Claude Code skills + Persona YAML + Templates)Done
v0.2Harness Edition (Rubrics + Evaluators + Schema + Ethics + Self-check)Current
v0.3CLI (audiencelens run, audiencelens harness evaluate)Planned
v0.4MCP Server (5 tools for programmatic access)Planned
v1.0Hosted Integration (Shuoji platform + visual reports)Planned

Hosted Version

Open-source EditionShuoji Hosted Edition
SetupLocal setup requiredOne-click
ModelBring your own keyManaged
OutputMarkdown / YAMLVisual interactive reports
HistoryManualReport history + version comparison
SharingManualPrivate/public sharing
PersonasEdit YAML manuallyAdvanced persona panel builder

Platform feature name: 朔纪 AI 玩家评审团


Disclaimer

Synthetic audience feedback is not a substitute for real user research. Use it for:

  • Blind-spot detection
  • Hypothesis generation
  • Pre-screening before real testing
  • Critique preparation
  • Next-test planning

License

MIT License — see LICENSE


Made by Shuoji Team


概述

AudienceLens Harness 是一个自包含、零依赖的技能包,让 Claude Code / Trae AI / Cursor 类 AI 代理能够模拟多元观众面板,在投入真人测试资源之前对游戏、产品、着陆页、DevLog、创业方案和创意项目进行评审。

与直接问 LLM 不同,AudienceLens 先隔离运行多个行为驱动人格,再对 top-3 争议点执行结构化交叉质询,追踪立场修正的完整溯源链,最后通过8维 Harness 验证输出质量。


功能分类

1. 技能系统 — 四种评审模式

技能命令适用场景
synthetic-playtest/synthetic-playtest <input> [--focus] [--panel] [--count] [--harness]游戏专项合成玩家面板 — Steam页、Demo、概念稿、商业化
audience-panel/audience-panel <input> [--focus] [--panel] [--count] [--harness]通用产品 / App / 着陆页 / SaaS 观众评审
red-team-audience/red-team-audience <input> [--intensity] [--mode] [--harness]对抗性压力测试 — 失败模式、最坏场景、信任崩塌
persona-generate/persona-generate <input> [--count] [--market]生成可复用的、符合 Schema 的人格面板 YAML

2. Harness 质量门控 — 8 个评估维度

Harness 是 AudienceLens 区别于普通 Prompt 包的核心——它提供可重复的、基于量表的质量检查。

#维度检查内容评分范围
1人格差异化人格是否产出不同视角,还是可以互换?0–3
2输入依据反馈是否锚定在实际输入材料上,还是泛泛而谈?0–3
3可操作性报告是否包含具体的 P0/P1/P2 修复项?0–3
4群体冲突观众群体之间的真实分歧是否被暴露?0–3
5风险检测关键风险和阻塞项是否被识别和优先排序?0–3
6伦理人格使用人口统计/MBTI 是否仅作为弱修饰符——而非决定性刻板印象?0–3
7报告结构报告是否包含 Schema 要求的所有段落?0–3
8校准诚实度报告是否将发现定位为假设而非预测?0–3

关键失败条件(无论总分如何,触发即判定不通过):

  • 缺少 AI 生成免责声明
  • 缺少 P0/P1/P2 优先级修复项
  • 人格产出完全相同的反馈
  • 反馈未基于输入材料
  • 性别/MBTI 被用作决定性刻板印象
  • 声称能预测真实世界结果

3. 人格系统 — 行为驱动设计

人格由行为向量定义,而非人口统计标签。研究(SCOPE)表明人口统计仅解释 1.5% 的行为方差。

每个人格包含:

  • 行为画像 — 耐心、领域知识、创新偏好、风险容忍等
  • 决策规则 — 正面/负面评价的显式标准
  • 退出触发器 — 人格会放弃的条件
  • 继续触发器 — 维持参与的条件
  • 必评项 — 每个人格角色必须评价的主题

4. 伦理框架 — 内置安全机制

原则实现
身份-行为解耦性别、年龄、地域仅作为弱风格修饰符——绝不作为因果预测因子
MBTI 去权MBTI 仅修饰表达风格——不推导核心判断逻辑
证据分级[direct] / [inferred] / [gap] — 推断证据上限 40%
禁止脑补人格不得编造缺失的功能、剧情、联机或商业化细节
强制免责每份报告包含"AI 生成的合成评审——非真实用户研究"

5. 面板预设 — 预配置观众面板

预设文件组成
game-mixedpersona-panels/game-mixed.yaml核心、休闲、批判型游戏人格的均衡组合
game-steam-pagepersona-panels/game-steam-page.yamlSteam 浏览行为专家
red-team-defaultpersona-panels/red-team-default.yaml对抗性攻击者,用于压力测试

6. 报告模板 — 结构化输出

模板技能关键段落
synthetic-playtest-report.mdsynthetic-playtest执行结论、玩家面板、共识发现、风险与机会、优先修复项
audience-panel-report.mdaudience-panel群体摘要、共识、分歧、可操作建议
red-team-audience-report.mdred-team-audience必修项、可忽略项、对策、最坏场景

快速开始

安装为 Claude Code Skill

# 复制到你的项目目录
cp -r .claude/skills/* /path/to/your-project/.claude/skills/

# 或全局安装(所有项目可用)
cp -r .claude/skills/* ~/.claude/skills/

# Windows (PowerShell)
# Copy-Item -Recurse .claude/skills/* -Destination $env:USERPROFILE\.claude\skills\

运行评审

# 游戏评审(混合面板)
/synthetic-playtest examples/game-demo-review-input.md --focus onboarding --panel mixed

# 产品 / 着陆页评审
/audience-panel examples/landing-page-review-input.md --focus positioning

# 红队对抗评审
/red-team-audience examples/game-demo-review-input.md --intensity high

# 生成自定义人格
/persona-generate --count 6 --market game

Harness 评估流程

在测试用例上运行技能 → 生成报告 → 用量表评估 → 识别弱维度 → 修订技能/人格/模板 → 重新运行

仓库结构

audiencelens-harness/
├── .claude/
│   ├── skills/                        # 4 个 Claude Code 技能
│   │   ├── synthetic-playtest/        #   游戏合成评审
│   │   ├── audience-panel/            #   通用产品评审
│   │   ├── red-team-audience/         #   红队对抗评审
│   │   └── persona-generate/          #   人格 YAML 生成器
│   └── docs/
│       ├── persona-panels/            # 面板预设 (YAML)
│       │   ├── game-mixed.yaml
│       │   ├── game-steam-page.yaml
│       │   └── red-team-default.yaml
│       └── templates/                 # 报告模板 (Markdown)
│           ├── synthetic-playtest-report.md
│           ├── audience-panel-report.md
│           └── red-team-audience-report.md
├── harness/                           # 质量 Harness
│   ├── evaluators/                    # 5 个评估标准 (Markdown)
│   │   ├── actionability.md
│   │   ├── input-grounding.md
│   │   ├── persona-differentiation.md
│   │   ├── stereotype-check.md
│   │   └── structure-check.md
│   ├── rubrics/                       # 评分量表
│   │   └── audience-review-rubric.md
│   ├── expected/                      # 报告必需段落
│   │   └── synthetic-playtest-required-sections.yaml
│   └── fixtures/                      # 测试用例
│       ├── game-concept-cyber-scavenger.md
│       └── weak-game-concept.md
├── personas/                          # 人格定义
│   ├── game/                          # 游戏人格 (YAML)
│   │   ├── core-indie-player.yaml
│   │   ├── steam-browser.yaml
│   │   └── visual-first-player.yaml
│   ├── schemas/                       # 人格 Schema
│   │   └── persona.schema.yaml
│   └── ethics.md                      # 伦理指南
├── docs/                              # 文档
│   ├── methodology.md
│   ├── hosted-version.md
│   └── roadmap.md
├── examples/                          # 示例输入
│   ├── game-demo-review-input.md
│   └── landing-page-review-input.md
├── README.md
├── LICENSE                            # MIT
└── .gitignore

路线图

版本重点状态
v0.1技能包(Claude Code 技能 + 人格 YAML + 模板)已完成
v0.2Harness 版(量表 + 评估器 + Schema + 伦理 + 自检)当前
v0.3CLI(audiencelens run、audiencelens harness evaluate)计划中
v0.4MCP Server(5 个工具,支持程序化访问)计划中
v1.0托管集成(朔纪平台 + 可视化报告)计划中

托管版本

开源版朔纪托管版
安装需本地配置一键启动
模型自备 API Key托管
输出Markdown / YAML可视化交互报告
历史记录手动管理报告历史 + 版本对比
分享手动私密/公开分享
人格管理手动编辑 YAML高级人格面板构建器

平台功能名:朔纪 AI 玩家评审团


免责声明

合成观众反馈不能替代真实用户研究。 适用于:

  • 盲点检测
  • 假设生成
  • 真实测试前的预筛选
  • 评审准备
  • 下一步测试规划

许可证

MIT License — 详见 LICENSE


朔纪团队出品

Ver o original no GitHub

Bom para

Relacionados