← Back to Skills Marketplace
yh9277

Kaito

by YH9277 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
248
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install kaito
Description
Mindshare tracking primitive using Kaito MCP tools. Use this skill to check mindshare trends for an entity or narrative. Triggers on phrases like 'mindshare...
README (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.
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
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.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install kaito
  3. After installation, invoke the skill by name or use /kaito
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Slug kaito
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Kaito?

Mindshare tracking primitive using Kaito MCP tools. Use this skill to check mindshare trends for an entity or narrative. Triggers on phrases like 'mindshare... It is an AI Agent Skill for Claude Code / OpenClaw, with 248 downloads so far.

How do I install Kaito?

Run "/install kaito" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Kaito free?

Yes, Kaito is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Kaito support?

Kaito is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Kaito?

It is built and maintained by YH9277 (@yh9277); the current version is v1.0.0.

💬 Comments