Chalk Labs
Need help deploying ai-product-evaluation?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/xgl1103-ai-product-evaluation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ai-product-evaluation
What's inside
- Skill name
ai-product-evaluation- Description
- 统一机会评估主链路、八维评分与 Gate;默认输出原生文档,不调用生图。
- License
- MIT
- Instructions
- 60 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- output-templates.md · references/
- templates.md · references/
SKILL.md (first lines)
# AI 产品评估与机会决策机制 ## 主链路 ```text 输入分流 → 单品拆解/机会定义 → 事实与证据台账 → 六看 → 适配度 → 创新评审 →(明确授权后)3-7-30 验证 ``` - 前沿扫描完成 A/B/C 漏斗后停止,等用户选择; - 明确单品只有在用户要求完整机制或 Gate 允许时才继续; - 六看判断外部机会是否成立;适配度判断是否适合本组织;两者不可互相替代; - 任何阶段不得自动进入 PRD、BOM、Demo、MVP、开发、量产或立项,除非用户明确授权。 ## 核心原则 AI 负责搜索、整理、初稿和提效;人负责需求、技术、供应链、商业、合规和资源投入判断。事实、判断、假设、未知分开记录;关键结论必须有来源。 ## 任务模式 1. 快速初筛(3 天):六看轻扫描 + 证据分级 + 方向判断卡; 2. 概念成案(7 天):定位、场景、技术边界、BOM 粗判、供应链、商业路径和验证任务; 3. MVP 验证(30 天):仅在明确授权后执行; 4. 完整评估:六看、证据校验、八维适配度、3-7-30 建议和 Gate; 5. 复盘沉淀:更新证据台账、评分版本、决策和复看条件。 ## 六看 市场、资本、行业、政策、用户、品类竞品六维;每维记录判断问题、事实、来源、证据等级、支持信号、反向信号、未知、当前判断和验证动作。结论为 YES / CONDITIONAL / WATCH / NO。 ## 八维评分(100 分,固定权重) - 市场/趋势确定性 10 - 用户需求强度 15 - 品类/竞品验证程度 10 - AI 价值必要性 10 - 组织能力匹配度 25 - 快速落地可行性 15 - 商业转化路径 10 - 成本与风险可控性 5 评分规则:八项必须全部整数评分;缺证保守打分并写明缺口,不得用推测补齐事实。 统一 Gate: - **80–100:高适配 / S51**,可提交创新评审; - **65–79:中适配 / S52**,补齐关键证据后复评; - **50–64:低适配 / S53**,进入观察池,不投入开发; - **0–49:不适配 / S54**,暂停并记录重启条件。 另设完整评估初筛提示:总分低于 60 时,不进入概念成案;60–64 仍属于低适配观察池,不能表述为 Go。 ## 3-7-30 每项任务注明假设、最小动作、负责人、截止日期、通过标准、结果和下一步;3 天只做初筛,7 天补齐成案证据,30 天验证必须有明确授权。 ## 产物与 image 边界 - 默认:Markdown、DOCX、原生可编辑 PPTX、XLSX; - 六看:Markdown + T-A02 XLSX; - 适配度:Markdown/DOCX + T-A04 XLSX; - 完整评估:Markdown + DOCX + 原生可编辑 PPTX,必要时附 XLSX; - 纯 PPT 使用原生 SVG/PPTX 工作流;纯 Word 使用 DOCX 原生排版; - 仅《产品机会一页卡》在用户明确要求视觉卡时允许单张 PNG 生图,且 PNG 不替代底稿。 ## Gate 停止与复评 六看 NO/WATCH 停止;CONDITIONAL 生成 Evidence Task;适配度 S52/S53/S54 停在对应状态。新订单、访谈、Demo、报价、竞品、政策或内部资源发生变化时,增量更新台账并保留版本原因。
From xgl1103/ai-product-manager-employee, MIT.
More from xgl1103/ai-product-manager-employee
- 0.570score
gpt-image-relay
xgl1103
通过公网 OpenAI-compatible 中转调用 gpt-image-2 文生图并落盘 PNG。Use when 用户要生图、画 Logo、出 PNG/海报,或 image_generate 报 SSRF / No image-generation provider registered。
SkillAFreshness: AClaude Code +9 - 0.560score
pm-workflow
xgl1103
可配置的产品经理工作流助手:按个人配置生成 PRD、竞品分析、需求池、周报与路线图。
SkillAFreshness: AClaude Code +9 - 0.560score
six-lens-opportunity-scan
xgl1103
对明确机会做市场、资本、行业、政策、用户、竞品六看压力测试并输出YES/CONDITIONAL/WATCH/NO。
SkillAFreshness: AClaude Code +9 - 0.560score
product-intelligence-teardown
xgl1103
产品拆解以 Markdown、DOCX、原生可编辑 PPTX 为主;不再默认逐页生图,仅机会一页卡可单独申请视觉卡。
SkillAFreshness: AClaude Code +9 - 0.560score
fit-assessment
xgl1103
统一八维评分与 S51-S54 Gate;缺证保守评分,默认原生文档产物,不调用生图。
SkillAFreshness: AClaude Code +9 - 0.558score
modao-downloader
xgl1103
下载墨刀 AI 生成的产物(HTML/React/Vue/PRD/图片)到本地。触发词:下载墨刀、下载原型、下载产物、保存原型、导出原型。
SkillAFreshness: AClaude Code +9 - 0.558score
modao-generator
xgl1103
生成产品原型、页面、PRD时使用。通过墨刀 MCP 生成 HTML/React/Vue/PRD/图片,自动导入墨刀编辑器。
SkillAFreshness: AClaude Code +9 - 0.555score
pm-opportunity-fast-lane
xgl1103
机会扫描提速:事实台账复用,默认 Markdown/XLSX,明确请求一页卡时才单张生图。
SkillAFreshness: AClaude Code +9 - 0.555score
modao-demo
xgl1103
墨刀 Demo 生成:基于 PRD 调用墨刀 MCP 生成可交互原型。
SkillAFreshness: AClaude Code +9 - 0.555score
prd-mvp
xgl1103
MVP PRD 生成:基于商业计划书,生成最小可行产品的产品需求文档。
SkillAFreshness: AClaude Code +9 - 0.555score
frontier-opportunity-discovery
xgl1103
众筹/新品扫描:先做机会漏斗,再按真实性、机制、P/T/C与30天Demo分流A/B/C。
SkillAFreshness: AClaude Code +9 - 0.555score
innovation-opportunity-packaging
xgl1103
机会分析页使用产品锚点与原生图表;仅产品机会一页卡可使用单张生图,禁止把 image 当作通用视觉生产路径。
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 21, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from xgl1103
- 0.570score
gpt-image-relay
xgl1103
通过公网 OpenAI-compatible 中转调用 gpt-image-2 文生图并落盘 PNG。Use when 用户要生图、画 Logo、出 PNG/海报,或 image_generate 报 SSRF / No image-generation provider registered。
SkillAFreshness: AClaude Code +9 - 0.560score
six-lens-opportunity-scan
xgl1103
对明确机会做市场、资本、行业、政策、用户、竞品六看压力测试并输出YES/CONDITIONAL/WATCH/NO。
SkillAFreshness: AClaude Code +9 - 0.560score
product-intelligence-teardown
xgl1103
产品拆解以 Markdown、DOCX、原生可编辑 PPTX 为主;不再默认逐页生图,仅机会一页卡可单独申请视觉卡。
SkillAFreshness: AClaude Code +9 - 0.560score
fit-assessment
xgl1103
统一八维评分与 S51-S54 Gate;缺证保守评分,默认原生文档产物,不调用生图。
SkillAFreshness: AClaude Code +9 - 0.560score
pm-workflow
xgl1103
可配置的产品经理工作流助手:按个人配置生成 PRD、竞品分析、需求池、周报与路线图。
SkillAFreshness: AClaude Code +9 - 0.558score
modao-downloader
xgl1103
下载墨刀 AI 生成的产物(HTML/React/Vue/PRD/图片)到本地。触发词:下载墨刀、下载原型、下载产物、保存原型、导出原型。
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ai-product-evaluation running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ai-product-evaluation skill. Agent Mart. https://agentmart.dev/skills/xgl1103-ai-product-evaluation (last updated 2026-10-24)