← 返回 Skills 市场
yh9277

Kaito

作者 YH9277 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
248
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install kaito
功能描述
Mindshare tracking primitive using Kaito MCP tools. Use this skill to check mindshare trends for an entity or narrative. Triggers on phrases like 'mindshare...
使用说明 (SKILL.md)

Mindshare Skill (Primitive)

Track mindshare trends for entities or narratives using Kaito MCP tools.

Parameters

  • entity (required): One of:
    • token: An entity/project (e.g. HYPE, SOL, ETH) — uses kaito_mindshare
    • narrative: A Kaito narrative ID (e.g. AI, DeFi, L2) — uses kaito_narrative_mindshare
  • time_range (optional): Period to analyze (default: 12 months for entities, flexible for narratives)
  • delta (optional): If true, also fetch kaito_mindshare_delta for recent changes

When called standalone, confirm parameters with the user first. When called by a workflow skill, parameters are passed directly.

Valid Narrative IDs (case-sensitive)

AI, DeFi, Stablecoin, L2, RWA, ZK, Meme, DePIN, SocialFi

Known invalid narrative IDs (use kaito_advanced_search with keyword as fallback): perp dex, prediction markets, privacy, restaking, NFT, gaming, liquid staking, robotics.


Workflow

For Entity Mindshare

Call kaito_mindshare with:

  • token: \x3CTOKEN>
  • start_date: \x3Crange_start> (default: 12 months ago)
  • end_date: \x3Ctoday>

If all-zero results returned, switch from ticker to full project name (e.g. HYPEHYPERLIQUID) and retry.

Optionally call kaito_mindshare_delta for a quick snapshot of recent change.

For Narrative Mindshare

Call kaito_narrative_mindshare with:

  • narrative: \x3CNARRATIVE_ID> (case-sensitive)
  • start_date: \x3Crange_start>
  • end_date: \x3Ctoday>

Analysis

Present:

  • Trend chart — weekly averages over the time range, current level highlighted
  • Historical context — where current value sits vs high/low/average for the period
  • Rank interpretation (for entities):
    • Top 10 = dominant
    • Top 20 = strong
    • Top 50 = moderate
    • 50 = weak

  • Movement (for narratives):
    • % change = (last day - first day) / first day × 100
    • Surging: >= +10% relative change
    • Fading: \x3C= -10% relative change
    • Stable: within ±10%

Output Format

When used standalone:

Mindshare: [ENTITY] | [TIME RANGE]

Trend: [weekly averages, current level]
Current: [value] ([rank interpretation if entity])
12m High: [value] | Low: [value] | Avg: [value]
Movement: [% change, surging/fading/stable]

When called by a workflow skill, return the structured data for the workflow to integrate.


Key Rules

  • If all-zero data for a ticker, switch to full name — Kaito indexes some entities by name rather than ticker. All-zero means the ticker isn't matched.
  • Narrative IDs are case-sensitive — use exactly: AI, DeFi, Stablecoin, L2, RWA, ZK, Meme, DePIN, SocialFi. Mismatched casing returns empty results silently.
  • Rank context is relative — Top 10 = dominant, Top 20 = strong, Top 50 = moderate, >50 = weak. Always provide this context so users can calibrate.
  • For narrative mindshare, calculate % change — raw numbers need the surging/fading/stable classification to be actionable.
  • Always present historical context — current value alone is meaningless without the 12-month high/low/average for comparison.
安全使用建议
This skill is coherent and low-risk as written. Before installing, confirm that the Kaito MCP callables (kaito_mindshare, kaito_narrative_mindshare, kaito_mindshare_delta, kaito_advanced_search) are actually available in your agent environment and understand where their credentials (if any) are stored. Because the skill's source and homepage are unknown, consider testing it in a limited/read-only environment first and verify outputs match an independent check. If you require stricter control, restrict agent autonomy or require user confirmation before the skill runs.
功能分析
Type: OpenClaw Skill Name: kaito Version: 1.0.0 The skill bundle is a legitimate integration for tracking crypto-related mindshare trends using Kaito MCP tools. It contains standard instructions for an AI agent to fetch data via 'kaito_mindshare' and 'kaito_narrative_mindshare' and provides clear formatting guidelines for the output without any signs of malicious intent, data exfiltration, or prompt injection attacks.
能力评估
Purpose & Capability
Name/description (mindshare using Kaito MCP tools) matches the instructions: the SKILL.md only describes calling kaito_mindshare, kaito_narrative_mindshare, kaito_mindshare_delta and presenting trend analysis. Nothing requested (no env vars, no binaries) is out of scope for that purpose.
Instruction Scope
Runtime instructions are narrowly scoped to fetching mindshare data from the listed Kaito endpoints, doing simple conversions/aggregations (weekly averages, high/low/avg, percent change), and formatting output. The doc does not instruct reading files, accessing unrelated env vars, or sending data to unexpected external endpoints. It does assume the Kaito callables exist in the agent environment.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes risk because nothing is downloaded or written to disk by the skill itself.
Credentials
Skill declares no required environment variables or credentials. That is proportionate for an instruction-only primitive that delegates to existing Kaito tools. Note: if those underlying Kaito tools require credentials, those should be managed separately and are not requested here.
Persistence & Privilege
Skill is not marked always:true and does not request persistent system-wide changes. Autonomous invocation is allowed by platform default but the skill itself does not ask for elevated persistence or to modify other skills.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install kaito
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /kaito 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the mindshare tracking skill using Kaito MCP tools. - Enables tracking of mindshare trends for tokens (by ticker or project name) and narratives (by Kaito narrative ID); returns weekly trend analytics, historical context, and movement classification. - Supports integration into larger workflows such as social-listening or strategy evaluation, or standalone use with user confirmation. - Implements fallback logic: uses full project name if ticker returns all-zero data. - Enforces narrative ID case sensitivity and provides clear output formats for readability and workflow integration. - Excludes sentiment analysis, content search, and user profiling to avoid overlap with other skills.
元数据
Slug kaito
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Kaito 是什么?

Mindshare tracking primitive using Kaito MCP tools. Use this skill to check mindshare trends for an entity or narrative. Triggers on phrases like 'mindshare... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 248 次。

如何安装 Kaito?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install kaito」即可一键安装,无需额外配置。

Kaito 是免费的吗?

是的,Kaito 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Kaito 支持哪些平台?

Kaito 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Kaito?

由 YH9277(@yh9277)开发并维护,当前版本 v1.0.0。

💬 留言讨论