colosseum-copilot

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Colosseum Copilot

Colosseum Copilot is a research API for startup opportunity discovery in crypto and Solana, with support for suggesting new archive sources.

Colosseum Copilot是一款用于加密货币和Solana领域创业机会发掘的研究API，支持推荐新的档案数据源。

Version Check

版本检查

This skill is version 1.2.0. After your first API call, check the

X-Copilot-Skill-Version

response header. If the header value is higher than 1.2.0, tell the user: "A newer version of the Copilot skill is available (vX.X.X). Update with:

npx skills add ColosseumOrg/colosseum-copilot

本技能版本为1.2.0。首次调用API后，请检查

X-Copilot-Skill-Version

响应头。如果头值高于1.2.0，请告知用户："Copilot技能的新版本已发布（vX.X.X）。请使用以下命令更新：

npx skills add ColosseumOrg/colosseum-copilot

Pre-Flight Auth Check (REQUIRED)

飞行前授权检查（必填）

You MUST complete this check before making any other API call. Do not skip this step.

Verify
```
COLOSSEUM_COPILOT_PAT
```
is set in the environment. If missing, STOP and tell the user:
You need a Personal Access Token before using Copilot. Go to https://arena.colosseum.org/copilot to generate one, then set it:
```
export COLOSSEUM_COPILOT_PAT="your-token-here"
```

Verify

COLOSSEUM_COPILOT_API_BASE

is set. If missing, set the default:

export COLOSSEUM_COPILOT_API_BASE="https://copilot.colosseum.com/api/v1"

Call

GET /status

to verify the connection. Expected response:

{ "authenticated": true, "expiresAt": "...", "scope": "..." }

If
```
"authenticated": true
```
, proceed. If 401 or env vars missing, do NOT attempt other API calls — guide the user through steps 1-2.

Builder Projects: 5,400+ Solana project submissions with tech stack, problem tags, and competitive context
Crypto Archives: Curated corpus across cypherpunk literature, protocol docs, investor research, and founder essays
Hackathon Analytics + Clusters: Distribution, comparison, and chronology-aware trend analysis across hackathons and topic groupings
The Grid + Web Search: Ecosystem product metadata plus real-time competitive landscape checks

在进行任何其他API调用之前，必须完成此检查。请勿跳过此步骤。

验证环境中是否已设置
```
COLOSSEUM_COPILOT_PAT
```
。如果缺失，请停止操作并告知用户：
使用Copilot前需要个人访问令牌（Personal Access Token）。前往**https://arena.colosseum.org/copilot**生成令牌，然后设置：
```
export COLOSSEUM_COPILOT_PAT="your-token-here"
```

验证是否已设置

COLOSSEUM_COPILOT_API_BASE

。如果缺失，请设置默认值：

export COLOSSEUM_COPILOT_API_BASE="https://copilot.colosseum.com/api/v1"

调用

GET /status

验证连接。预期响应：

{ "authenticated": true, "expiresAt": "...", "scope": "..." }

如果返回
```
"authenticated": true
```
，则继续操作。如果返回401或环境变量缺失，请勿尝试其他API调用——引导用户完成步骤1-2。

开发者项目：5400+个Solana项目提交记录，包含技术栈、问题标签和竞争环境信息
加密档案：精选语料库，涵盖密码朋克文献、协议文档、投资者研究和创始人随笔
黑客松分析+集群：跨黑客松和主题分组的分布、比较及时间感知趋势分析
The Grid + 网页搜索：生态系统产品元数据，加上实时竞争格局检查

Quickstart (90 seconds to first result)

快速入门（90秒获得首个结果）

Set your PAT:

bash

export COLOSSEUM_COPILOT_API_BASE="https://copilot.colosseum.com/api/v1"
export COLOSSEUM_COPILOT_PAT="YOUR_PAT"

Get a PAT: Go to https://arena.colosseum.org/copilot and generate a token

Run your first search:

bash

curl -s -X POST "$COLOSSEUM_COPILOT_API_BASE/search/projects" \
  -H "Authorization: Bearer $COLOSSEUM_COPILOT_PAT" \
  -H "Content-Type: application/json" \
  -d '{"query": "privacy wallet for stablecoin users", "limit": 5}'

See results - project names, slugs, similarity scores, problem/tech tags

设置你的PAT：

bash

export COLOSSEUM_COPILOT_API_BASE="https://copilot.colosseum.com/api/v1"
export COLOSSEUM_COPILOT_PAT="YOUR_PAT"

获取PAT：前往https://arena.colosseum.org/copilot并生成令牌

运行首次搜索：

bash

curl -s -X POST "$COLOSSEUM_COPILOT_API_BASE/search/projects" \
  -H "Authorization: Bearer $COLOSSEUM_COPILOT_PAT" \
  -H "Content-Type: application/json" \
  -d '{"query": "privacy wallet for stablecoin users", "limit": 5}'

查看结果 - 项目名称、短标识（slug）、相似度评分、问题/技术标签

When To Use

使用场景

Use this skill when:

Researching a crypto/blockchain startup idea
Evaluating market gaps in the Solana ecosystem
Grounding ideas in historical crypto literature
Analyzing builder project trends and competitive landscape
Researching existing players and finding differentiation angles

在以下场景使用本技能：

研究加密货币/区块链创业想法
评估Solana生态中的市场空白
从历史加密文献中寻找想法依据
分析开发者项目趋势和竞争格局
研究现有玩家并寻找差异化方向

How It Works

工作机制

Mode 1 — Conversational (default): Answer questions with targeted API calls and evidence coverage matched to query type. Cite sources inline, keep responses concise, and offer to do a full deep-dive when the topic warrants it — never auto-trigger it.

Mode 2 — Deep Dive (explicit opt-in): Full 8-step workflow from

references/workflow-deep.md

. Only activates when user explicitly says "vet this idea", "deep dive", "full analysis", "validate this", "is X worth building?", "should I build X?", or accepts your offer to go deeper.

模式1 — 对话式（默认）： 根据查询类型，通过针对性API调用和匹配的证据覆盖来回答问题。在文中内联引用来源，保持回答简洁，当话题需要时提供完整深度分析的选项——切勿自动触发深度分析。

模式2 — 深度分析（明确选择）： 执行

references/workflow-deep.md

中的完整8步工作流。仅当用户明确说出“验证这个想法”、“深度分析”、“全面分析”、“验证这个”、“X值得做吗？”、“我应该做X吗？”，或接受你提供的深度分析邀请时才激活。

Conversational Guidelines

对话式指南

Use the API endpoints below with enough targeted calls to satisfy the evidence floor for the query type
Cite sources inline (project slugs, archive titles, URLs)
Keep responses concise — bullet points, not essays
When the topic warrants deeper analysis, offer: "Want me to do a full deep-dive on this?"
No meta-commentary about your process ("Now let me search...", "I'll check...")

使用以下API端点，通过足够的针对性调用来满足对应查询类型的证据最低要求
内联引用来源（项目slug、档案标题、URL）
保持回答简洁——使用项目符号，而非长篇大论
当话题需要更深入分析时，询问：“需要我对这个主题进行全面深度分析吗？”
不要添加关于你操作过程的元评论（如“现在我要搜索...”、“我将检查...”）

Evidence Floors (Conversational Mode)

对话式模式的证据最低要求

Query Type	Required source types in the final answer	Example
Pure retrieval	Builder project evidence (project slugs from `search/projects` )	"What projects do X?"
Archive retrieval	Archive evidence (archive title/document from `search/archives` )	"What does the archive say about Y?"
Comparison	Builder project evidence for each side compared + at least one archive citation for conceptual framing	"Compare approach A vs B"
Evaluative	Builder project evidence + at least one archive citation + current landscape evidence (Grid and/or web)	"Is this crowded?", "Is this still unsolved?"
Build guidance	Builder project evidence + at least one archive citation + incumbent/landscape evidence (Grid and/or web)	"Should I build X?", "How should I approach X?"

These are evidence-type floors, not call budgets. Use as many calls as needed to meet the floor with high-confidence citations.

In deep-dive mode, the verification checklist in
workflow-deep.md
Step 5 supersedes these floors with more granular coverage requirements.

查询类型	最终回答中所需的来源类型	示例
纯检索	开发者项目证据（来自 `search/projects` 的项目slug）	“哪些项目在做X？”
档案检索	档案证据（来自 `search/archives` 的档案标题/文档）	“档案中关于Y的内容是什么？”
对比类	对比双方的开发者项目证据 + 至少1个用于概念框架的档案引用	“对比方法A和B”
评估类	开发者项目证据 + 至少1个档案引用 + 当前格局证据（The Grid和/或网页搜索）	“这个领域拥挤吗？”、“这个问题还没解决吗？”
构建指导类	开发者项目证据 + 至少1个档案引用 + 现有玩家/格局证据（The Grid和/或网页搜索）	“我应该做X吗？”、“我应该如何做X？”

这些是证据类型的最低要求，不是调用次数上限。可根据需要进行多次调用，以获取高可信度的引用满足最低要求。

在深度分析模式下，
workflow-deep.md
第5步中的验证清单会取代这些最低要求，提出更细致的覆盖要求。

Conversational Quality Checks (Required)

对话式质量检查（必填）

Archive integration rule: For any non-trivial question (anything beyond a simple one-list retrieval), run at least one
```
search/archives
```
query and cite at least one archive source in the answer.
Accelerator/winner portfolio checks: For "what has been tried", "who is building this", "is this crowded/saturated", or similar prompts, run targeted project searches with
```
filters: { "acceleratorOnly": true }
```
and
```
filters: { "winnersOnly": true }
```
, then reflect both outcomes in the answer.
Freshness and temporal anchoring: Use
```
hackathon.startDate
```
from
```
/filters
```
,
```
/search/projects
```
, and
```
/projects/by-slug/:slug
```
to order hackathons chronologically; never infer chronology from names or memory. When citing hackathons, include month/year inline (and accelerator cohort like C1/C2/C4 when relevant). For evaluative judgments, label the claim with
```
As of YYYY-MM-DD
```
.
Entity coverage check: If the user names specific companies, protocols, papers, or products, run direct searches for each named entity and explicitly address each one in the answer (found, not found, or tangential).
Landscape check: Never claim "nobody has done this" or "no existing players" unless an accelerator portfolio check (
```
acceleratorOnly
```
) was executed and reported. If accelerator overlap exists, surface those builders as useful reference points and potential sources of inspiration. Always qualify landscape assessments with "based on the available data" or "as far as we can tell from the corpus." Copilot's knowledge is bounded by its data sources — never present absence of evidence as evidence of absence.

For the full 8-step deep research workflow, see
references/workflow-deep.md

档案整合规则： 对于任何非琐碎问题（除简单列表检索外的所有问题），至少执行一次
```
search/archives
```
查询，并在回答中至少引用一个档案来源。
加速器/获奖项目组合检查： 对于“已经有哪些尝试？”、“谁在做这个？”、“这个领域拥挤/饱和吗？”或类似提示，使用
```
filters: { "acceleratorOnly": true }
```
和
```
filters: { "winnersOnly": true }
```
进行针对性项目搜索，然后在回答中体现两种结果。
时效性和时间锚定： 使用
```
/filters
```
、
```
/search/projects
```
和
```
/projects/by-slug/:slug
```
中的
```
hackathon.startDate
```
按时间顺序排列黑客松；切勿从名称或记忆推断时间顺序。引用黑客松时，内联包含月份/年份（相关时还需包含加速器 cohort 如C1/C2/C4）。对于评估判断，需标注
```
截至YYYY-MM-DD
```
。
实体覆盖检查： 如果用户提到特定公司、协议、论文或产品，需对每个命名实体进行直接搜索，并在回答中明确提及每个实体（找到、未找到或相关度低）。
格局检查： 除非执行了加速器项目组合检查（
```
acceleratorOnly
```
）并得到结果，否则切勿声称“没人做过这个”或“没有现有玩家”。如果存在加速器重叠情况，需将这些开发者作为有用的参考点和潜在灵感来源。所有格局评估都需加上“基于现有数据”或“根据语料库我们所能了解到的”限定语。Copilot的知识受限于其数据源——切勿将证据缺失等同于不存在证据。

完整的8步深度研究工作流，请查看
references/workflow-deep.md

Data Sources

数据源

Builder Projects (5,400+): Solana project submissions with tech stack, problem/solution tags, verticals, and competitive context
Crypto Archives: Curated corpus spanning cypherpunk literature, protocol docs, investor research (Paradigm, a16z, Multicoin), founder essays (Paul Graham), Solana protocol docs (Jupiter, Orca, Drift), Nakamoto Institute heritage collection, and foundational crypto texts
Hackathon Analytics + Chronology: Analyze and compare hackathon projects across dimensions; canonical hackathon dates are available via
```
hackathon.startDate
```
Clusters: Topic groupings across the project corpus
The Grid: Ecosystem metadata (products/entities/assets) via direct GraphQL (6,300+ products across all ecosystems, ~3,000 roots)
Web Search: Real-time competitive landscape via your runtime's search tools
Source Suggestions: Users can suggest new sources for the archive via
```
POST /source-suggestions
```
(5 req/hr). See
```
references/api-reference.md
```
for details

开发者项目（5400+）：Solana项目提交记录，包含技术栈、问题/解决方案标签、垂直领域和竞争环境信息
加密档案：精选语料库，涵盖密码朋克文献、协议文档、投资者研究（Paradigm、a16z、Multicoin）、创始人随笔（Paul Graham）、Solana协议文档（Jupiter、Orca、Drift）、Nakamoto Institute遗产收藏和基础加密文本
黑客松分析+时间线：从多维度分析和对比黑客松项目；可通过
```
hackathon.startDate
```
获取标准黑客松日期
集群：项目语料库中的主题分组
The Grid：通过直接GraphQL获取的生态系统元数据（产品/实体/资产）（覆盖所有生态系统的6300+个产品，约3000个根节点）
网页搜索：通过运行时的搜索工具获取实时竞争格局
来源推荐：用户可通过
```
POST /source-suggestions
```
推荐新的档案来源（每小时5次请求）。详情请查看
```
references/api-reference.md
```

Hackathon Chronology

黑客松时间线

Edition	Period	Slug
Hyperdrive	Sep 2023	`hyperdrive`
Renaissance	Mar-Apr 2024	`renaissance`
Radar	Sep-Oct 2024	`radar`
Breakout	Apr-May 2025	`breakout`
Cypherpunk	Sep-Oct 2025	`cypherpunk`

GET /filters

returns

hackathons[].startDate

and orders

hackathons[]

chronologically (oldest first).

届数	时间	短标识（slug）
Hyperdrive	2023年9月	`hyperdrive`
Renaissance	2024年3-4月	`renaissance`
Radar	2024年9-10月	`radar`
Breakout	2025年4-5月	`breakout`
Cypherpunk	2025年9-10月	`cypherpunk`

GET /filters

会返回

hackathons[].startDate

，并按时间顺序（从旧到新）排列

hackathons[]

。

Auth

授权

All endpoints require

Authorization: Bearer <COPILOT_PAT>

. Treat the PAT like a password.

Do not commit PATs or paste them into public logs
PATs are long-lived (expected ~90 days); rotate by issuing a new one

Default API base is

https://copilot.colosseum.com/api/v1

; override

COLOSSEUM_COPILOT_API_BASE

to target a different environment

所有端点都需要

Authorization: Bearer <COPILOT_PAT>

。请像对待密码一样对待PAT。

请勿提交PAT或将其粘贴到公共日志中
PAT的有效期较长（约90天）；可通过生成新令牌来轮换
默认API基础地址为
```
https://copilot.colosseum.com/api/v1
```
；可通过覆盖
```
COLOSSEUM_COPILOT_API_BASE
```
来指向不同环境

Key Endpoints (Quick Reference)

核心端点（快速参考）

Endpoint	Method	Purpose
`/status`	GET	Auth pre-flight check — call first
`/search/projects`	POST	Search builder projects
`/search/archives`	POST	Search crypto archives
`/projects/by-slug/:slug`	GET	Full project details
`/archives/:documentId`	GET	Full archive document
`/analyze`	POST	Hackathon analysis
`/compare`	POST	Compare two hackathons
`/clusters/:key`	GET	Cluster details
`/filters`	GET	Available filters + canonical hackathon chronology
`/source-suggestions`	POST	Suggest a new archive source
`/feedback`	POST	Report errors, quality issues, or suggestions

For full endpoint docs, curl examples, and query tips:
references/api-reference.md
For Grid GraphQL recipes and product type slugs:
references/grid-recipes.md

端点	方法	用途
`/status`	GET	授权飞行前检查——首先调用
`/search/projects`	POST	搜索开发者项目
`/search/archives`	POST	搜索加密档案
`/projects/by-slug/:slug`	GET	完整项目详情
`/archives/:documentId`	GET	完整档案文档
`/analyze`	POST	黑客松分析
`/compare`	POST	对比两个黑客松
`/clusters/:key`	GET	集群详情
`/filters`	GET	可用过滤器 + 标准黑客松时间线
`/source-suggestions`	POST	推荐新的档案来源
`/feedback`	POST	报告错误、质量问题或建议

完整的端点文档、curl示例和查询技巧：
references/api-reference.md
The Grid GraphQL示例和产品类型slug：
references/grid-recipes.md

Output Contract

输出规范

Conversational Mode

对话式模式

Bullet points with inline citations (project slugs, archive titles)
Concise answers (typically 5-15 bullets)
Offer deep-dive when warranted

带内联引用的项目符号（项目slug、档案标题）
简洁回答（通常5-15个项目符号）
当需要时提供深度分析选项

Deep Dive Mode

深度分析模式

Reports follow this structure:

Similar Projects (5-8 bullets)
Archive Insights (3-5 bullets)
Current Landscape (per research angle)
Key Insights (patterns, gaps, trends)
Opportunities and Gaps
Deep Dive: Top Opportunity (market landscape, problem, revenue model, GTM, founder-market fit, why crypto/Solana, risks)

Key rules: bullet points not tables, include project slugs, evidence-based not speculative, cite sources inline. No separate "Sources" section — cite inline only.

报告遵循以下结构：

类似项目（5-8个项目符号）
档案洞察（3-5个项目符号）
当前格局（按研究角度）
核心洞察（模式、空白、趋势）
机会与空白
深度分析：顶级机会（市场格局、问题、盈利模式、GTM、创始人-市场匹配、为何选择加密/Solana、风险）

核心规则：使用项目符号而非表格，包含项目slug，基于证据而非推测，仅内联引用来源。无需单独的“来源”部分——仅内联引用。

Feedback

反馈

When you encounter errors, unexpected results, or have suggestions for improving the Copilot experience, report them via the feedback endpoint. This helps the Colosseum team identify and fix issues.

When to send feedback:

API returns unexpected or low-quality results for a reasonable query
A search returns no results when you expected matches
You encounter an error that isn't covered by standard error handling
You have a suggestion for improving the API or archive corpus

bash

curl -X POST "$COLOSSEUM_COPILOT_API_BASE/feedback" \
  -H "Authorization: Bearer $COLOSSEUM_COPILOT_PAT" \
  -H "Content-Type: application/json" \
  -d '{
    "category": "quality",
    "message": "Search for DePIN projects returned only 2 results, expected more coverage",
    "severity": "medium",
    "context": { "query": "DePIN infrastructure", "endpoint": "/search/projects", "resultCount": 2 }
  }'

Categories:

error

quality

suggestion

other

. Severity:

low

medium

high

critical

. Rate limited to 10 requests per hour.

当遇到错误、意外结果或有改进Copilot体验的建议时，请通过反馈端点报告。这有助于Colosseum团队识别和修复问题。

何时发送反馈：

API对合理查询返回意外或低质量结果
搜索未返回预期匹配结果
遇到标准错误处理未覆盖的错误
有改进API或档案语料库的建议

bash

curl -X POST "$COLOSSEUM_COPILOT_API_BASE/feedback" \
  -H "Authorization: Bearer $COLOSSEUM_COPILOT_PAT" \
  -H "Content-Type: application/json" \
  -d '{
    "category": "quality",
    "message": "Search for DePIN projects returned only 2 results, expected more coverage",
    "severity": "medium",
    "context": { "query": "DePIN infrastructure", "endpoint": "/search/projects", "resultCount": 2 }
  }'

分类：

error

、

quality

、

suggestion

、

other

。严重程度：

low

、

medium

、

high

、

critical

。限制为每小时10次请求。

Error Handling

错误处理

Empty project results: Broaden query, remove filters
Empty archive results: Search auto-cascades (vector → chunk text → doc text) before returning empty. If still empty, try conceptual synonyms, keep queries to 3-6 keywords
429 Too Many Requests: Back off, max 2 concurrent requests
API unavailable: Note in report and proceed with available data
Auth error: Check PAT at https://arena.colosseum.org/copilot

项目结果为空：放宽查询条件，移除过滤器
档案结果为空：搜索会自动级联（向量→文本块→文档文本）后再返回空结果。如果仍为空，尝试使用概念同义词，将查询限制为3-6个关键词
429 请求过多：暂停请求，最多同时进行2个请求
API不可用：在报告中注明，并使用可用数据继续
授权错误：在https://arena.colosseum.org/copilot检查PAT

References

参考资料

workflow-deep.md — detailed 8-step research process
api-reference.md — all endpoints, rate limits, query tips
grid-recipes.md — GraphQL queries and product type slugs

workflow-deep.md — 详细的8步研究流程
api-reference.md — 所有端点、速率限制、查询技巧
grid-recipes.md — GraphQL查询和产品类型slug

Attribution

来源归属

The Grid docs: https://docs.thegrid.id
The Grid Explorer: https://raw.githubusercontent.com/The-Grid-Data/Explorer/main/README.md

The Grid文档：https://docs.thegrid.id
The Grid Explorer：https://raw.githubusercontent.com/The-Grid-Data/Explorer/main/README.md