Kaito
v1.0.0Mindshare tracking primitive using Kaito MCP tools. Use this skill to check mindshare trends for an entity or narrative. Triggers on phrases like 'mindshare...
⭐ 0· 183·0 current·0 all-time
by@yh9277
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & 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.
Assessment
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.Like a lobster shell, security has layers — review code before you run it.
latestvk971nbgg02n265tx338cnm730982nrqg
License
MIT-0
Free to use, modify, and redistribute. No attribution required.