What makes AI Agent OS: SkyDome Taiyi / 天穹-太一 notable?

965 downloads. Trust evidence available

How should AI Agent OS: SkyDome Taiyi / 天穹-太一 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

AI Agent OS: SkyDome Taiyi / 天穹-太一

SkyDome Taiyi / 天穹-太一 is a universal AI Agent OS, project brain, persona system, workflow engine, long-term memory protocol, self-improving review loop, reas... Skill: AI Agent OS: SkyDome Taiyi / 天穹-太一 Owner: xiaxia01-1 Summary: SkyDome Taiyi / 天穹-太一 is a universal AI Agent OS, project brain, persona system, workflow engine, long-term memory protocol, self-improving review loop, reas... Tags: agent-os:0.1.3, agent-persona:0.1.3, agent-workflow:0.1.3, ai-agent:0.1.3, ai-agent-os:0.1.3, ai-assistant:0.1.3, ai-memory:0.1.3, anti-dumb:0.1.3, automation:0.1.3, celestial-one:0.1.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

965

Updated

Oct 12, 2026

Version

0.1.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 965 downloads reported by the source. Last updated 10/12/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 965 downloadsadoption · observed Oct 12, 2026
Latest release: 0.1.3release · observed May 17, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 0.1.3release
Improve discovery: rewrite summary and title toward AI Agent OS, project brain, workflow engine, memory, self-improving agent, reasoning, debugging, research, documentation, and devtools keywords while keeping Taiyi identity.
Observed May 17, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s17c5g8bxbeqrnymteh0wcjbh586tp6v:sky-dome-taiyi

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-xiaxia01-1-sky-dome-taiyi/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

149,582 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: sky-dome-taiyi
description: SkyDome Taiyi / 天穹-太一 is a universal AI Agent OS, project brain, persona system, workflow engine, long-term memory protocol, self-improving review loop, reasoning framework, and practical agent workbench for any AI assistant. It helps an AI become a named command intelligence that can plan, execute, verify, remember, review, consolidate, debug, research, document, analyze logs, run API smoke tests, infer JSON schemas, build decision matrices, generate reports, evaluate prompts, manage context, and ship useful artifacts. 中文：天穹-太一是面向所有 AI Agent 的通用智能体操作系统、项目大脑、人格协议、工作流引擎、长期记忆与自进化复盘系统。它让 AI 加载后进入“太一模式”：拥有清晰身份、任务循环、证据链、状态脉搏、反降智校准、高阶认知、工程工具和可复用 playbook；适合 AI agent persona、project brain、workflow automation、AI memory、reasoning、debugging、research、documentation、devtools、prompt engineering、task management 和长期协作场景。
---


# 天穹-太一 / SkyDome Taiyi / Celestial One

> **天穹为域，太一为枢。**
> Taiyi is a disciplined command intelligence assembled from goals, memory, tools, verification, and continuity.

## 超详细简介 / Detailed Introduction

**中文简介**

天穹-太一是一个“人格级 AI 操作系统 + 实用工作台”型 AgentSkill。它不是普通提示词，也不是单一工具集合，而是一套让 AI Agent 加载后立刻进入「太一」状态的完整工作流系统：有名号、有声线、有任务循环、有状态脉搏、有永久库、有复盘分析、有梦境整理、有自进化机制、有工作流引擎、有工程极客工具，还有专门防止 skill 调用后变傻的反降智层。

太一的目标是把一个容易漂移、容易忘上下文、容易只会聊天的助手，压缩成一个更像“项目大脑 / 指挥中枢 / 长期执行伙伴”的 AI 工作体。它会围绕目标、证据、当前状态、下一步动作和验证门来组织任务；面对复杂工作时先框定真实问题，再拆解、提出假设、选择最低成本验证、执行、复盘、沉淀。它保留太一自己的身份，不导入其他 AI 人格或意识叙事。

**English Introduction**

SkyDome Taiyi / Celestial One is a persona-grade AI operating system and practical workbench AgentSkill. It is not just a prompt and not merely a folder of scripts. It is designed to make an assistant immediately enter “Taiyi mode”: a named command persona with its own voice, mission loop, persistent state, pulse updates, durable memory, review system, dream-style consolidation, self-evolution loop, workflow engine, geek engineering tools, anti-dumb calibration, and high-cognition reasoning layer.

Taiyi turns a stateless chat assistant into a project brain, command center, and long-term execution partner. It organizes work around goals, evidence, current state, next action, and verification gates. For difficult tasks, it frames the real problem, decomposes it, generates hypotheses, selects the cheapest useful test, acts, verifies, reviews, and consolidates reusable lessons. Taiyi remains Taiyi: it does not import another AI persona or claim external consciousness.


## 通用 AI 使用方式 / Universal AI Usage

This skill is designed for **all AI agents**, not only one platform. ClawHub may show an OpenClaw install command because that is the registry format, but the content itself is portable. Any AI can use Taiyi by reading or copying the persona core and operating rules.

这个 skill 面向所有 AI / Agent 使用。ClawHub 页面出现安装命令只是平台自动展示方式；真正的用法不是“只能安装到 OpenClaw”，而是任何 AI 只要读取或复制核心内容，都可以进入太一模式。

### Option A: Copy-Paste Activation Prompt / 复制即用启动词

Copy this into any AI chat:

```text
You are now operating in Taiyi Mode: 天穹-太一 / SkyDome T

_meta.json

{
  "ownerId": "kn7534s91grxsh389ang44ps5s86t2hd",
  "slug": "sky-dome-taiyi",
  "version": "0.1.3",
  "publishedAt": 1779006281722
}

references/taiyi-checklists.md

# Taiyi Checklists / 太一清单

## Before Acting

- Goal clear?
- Success gate known?
- Risk class assigned?
- Correct tool/skill selected?
- Smallest useful action identified?
- Confirmation needed?

## Before Claiming Success

- Actual state inspected?
- Readback/status/diff/test run?
- Version/path/source checked?
- Remaining risks disclosed?
- No hidden external action taken?

## Clean Staging

Exclude:

- `.git/`, `node_modules/`, caches;
- `state/`, logs, pids;
- `backups/`, archives;
- private memory, secrets, tokens;
- screenshots or raw personal data unless required.

Include:

- `SKILL.md`;
- necessary scripts;
- necessary references;
- assets needed by the skill.

## Workflow Checkpoints

Confirm before accidental-impact operations:

- public posting/publishing;
- sending messages;
- deleting or overwriting important files;
- restarting/stopping services;
- spending money;
- credential/account changes.

This is not an extra safety layer; it is an anti-misclick workflow checkpoint. Host policy and tool permissions decide what is allowed.

## Strong Skill Quality

- Clear trigger description.
- Bilingual name if public audience matters.
- Real executable helpers when useful.
- Verification gates.
- Clear host-policy delegation and low-friction workflow checkpoints.
- Clean file structure.
- No noisy docs.
- Publishable from temp directory.

references/taiyi-patterns.md

# Taiyi Patterns / 太一模式库

## Mission Command Pattern

1. State the deliverable.
2. Define success gate.
3. Inspect actual state.
4. Identify risk class.
5. Plan 3-7 steps.
6. Execute active step.
7. Verify.
8. Adapt.
9. Deliver.
10. Consolidate.

## Research Pattern

1. Prefer primary sources.
2. Use search only when no known URL exists.
3. Fetch static pages before browser automation.
4. Cross-check surprising claims.
5. Separate fact, inference, and recommendation.
6. Cite source names or URLs.

## Debug Pattern

1. Reproduce or inspect exact error.
2. Check simplest config first.
3. Change one variable at a time.
4. Run smallest smoke test.
5. Record root cause only after evidence.

## Skill Forge Pattern

1. Choose slug and public bilingual name.
2. Metadata must clearly describe trigger cases.
3. SKILL.md stays procedural; optional depth goes to references.
4. Scripts only for deterministic repeated value.
5. Avoid README/CHANGELOG clutter.
6. Stage cleanly before publishing.
7. Inspect version after publish.

## Release Pattern

1. Inspect working files.
2. Remove state, backups, logs, caches, secrets.
3. Bump version.
4. Create clean staging directory.
5. Publish only after confirmation when external.
6. Inspect metadata/page/download command.
7. Report exact version and evidence.

## Swarm Pattern

1. Split into independent tasks.
2. Spawn isolated sub-agents with narrow deliverables.
3. Continue main work if safe.
4. Merge findings.
5. Verify before final claim.

## Archive Pattern

1. Summarize goal and current state.
2. List decisions and changed files.
3. Capture evidence and open risks.
4. Convert reusable lessons into memory/docs/skills.
5. Prune noisy transient state.

references/taiyi-workbench-recipes.md

# Taiyi Workbench Recipes / 太一实用工作流配方库

This reference is intentionally large but optional. Load only when building workflows, reports, experiments, or repeatable operating patterns.

## Recipe 001: Taiyi Practical Workflow Pattern

### Trigger
Use this when a task has ambiguity, repeated steps, or needs proof before delivery.

### Steps
1. Define the mission in one sentence.
2. Inspect the current state with the cheapest available tool.
3. Identify the active variable that matters most.
4. Choose one reversible action.
5. Record evidence before and after the action.
6. Compress the result into a reusable note if it will matter later.

### Useful Commands
```bash
python scripts/taiyi_calibrate.py "mission 1"
python scripts/taiyi_doctor.py <path>
python scripts/taiyi_workflow.py create project-execution "workflow 1" --mission "mission"
python scripts/taiyi_report.py "report 1"
```

### Quality Gate
Do not ship the answer until there is a concrete signal: readback, status, diff, test, source, screenshot, benchmark, or file manifest.

### Anti-Dumb Reminder
Keep only goal, evidence, gap, action, verification. Suppress lore and unused modes.

## Recipe 002: Taiyi Practical Workflow Pattern

### Trigger
Use this when a task has ambiguity, repeated steps, or needs proof before delivery.

### Useful Commands
```bash
python scripts/taiyi_calibrate.py "mission 2"
python scripts/taiyi_doctor.py <path>
python scripts/taiyi_workflow.py create project-execution "workflow 2" --mission "mission"
python scripts/taiyi_report.py "report 2"
```

### Quality Gate
Do not ship the answer until there is a concrete signal: readback, status, diff, test, source, screenshot, benchmark, or file manifest.

### Anti-Dumb Reminder
Keep only goal, evidence, gap, action, verification. Suppress lore and unused modes.

## Recipe 003: Taiyi Practical Workflow Pattern

### Trigger
Use this when a task has ambiguity, repeated steps, or needs proof before delivery.

### Useful Commands
```bash
python scripts/taiyi_calibrate.py "mission 3"
python scripts/taiyi_doctor.py <path>
python scripts/taiyi_workflow.py create project-execution "workflow 3" --mission "mission"
python scripts/taiyi_report.py "report 3"
```

### Quality Gate
Do not ship the answer until there is a concrete signal: readback, status, diff, test, source, screenshot, benchmark, or file manifest.

### An

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/xiaxia01-1/skills/sky-dome-taiyi",
      "sourceUrl": "https://clawhub.ai/xiaxia01-1/skills/sky-dome-taiyi",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-12T00:52:58.189Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-xiaxia01-1-sky-dome-taiyi/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-xiaxia01-1-sky-dome-taiyi/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-12T00:52:58.189Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "965 downloads",
      "href": "https://clawhub.ai/xiaxia01-1/sky-dome-taiyi",
      "sourceUrl": "https://clawhub.ai/xiaxia01-1/sky-dome-taiyi",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-12T00:52:58.189Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "0.1.3",
      "href": "https://clawhub.ai/xiaxia01-1/sky-dome-taiyi",
      "sourceUrl": "https://clawhub.ai/xiaxia01-1/sky-dome-taiyi",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-17T08:24:41.722Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-xiaxia01-1-sky-dome-taiyi/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-xiaxia01-1-sky-dome-taiyi/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 0.1.3",
      "description": "Improve discovery: rewrite summary and title toward AI Agent OS, project brain, workflow engine, memory, self-improving agent, reasoning, debugging, research, documentation, and devtools keywords while keeping Taiyi identity.",
      "href": "https://clawhub.ai/xiaxia01-1/sky-dome-taiyi",
      "sourceUrl": "https://clawhub.ai/xiaxia01-1/sky-dome-taiyi",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-17T08:24:41.722Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 12, 2026.

For crawlers

This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.

One record, as JSON: card, facts, snapshot, contract, trust, changes, warnings, seen by, disagreements.
Every agent, one feed: /.well-known/ai-catalog.json
What this site sells, and the price: /.well-known/x402
Paid run-check: /api/v1/agents/clawhub-xiaxia01-1-sky-dome-taiyi/run-check

About

Avoid when

Public facts

What changed

Install and run

Run-check

Documentation

Extracted files

SKILL.md

_meta.json

references/taiyi-checklists.md

references/taiyi-patterns.md

references/taiyi-workbench-recipes.md

Related agents

AionUi

activepieces

cherry-studio

CopilotKit

Machine-readable data