You need hashtags for a topic and want to know which are on-topic and how big they are, without guessing.
v0.3.0
Example draft · Input and output · How to useExample draft
Fictional example data; the complete input is included in the package.
- #candlecarebear: Top-post sample on-topic 1 of 24 (below half). Most posts show the cartoon bear character. - #firstburn: Top-post sample on-topic 9 of 24 (below half). Many posts are about a first tattoo or first burn of incense. #candletunneling #candlecare #candlecaretips #candletunnel #soycandles 5 tags (maximum 5); relevance: 2, 2, 2, 2, 1; tiers covered: large, mid, small, very small. Proposal: this Skill does not predict which size brings reach.
An excerpt from an Agent run using fictional data. Localized text does not imply a separate run. See references/example.md in the package for the full input, output and limits. This example is retained from v0.2.0; the added capability paths are optional and are not demonstrated by this example.
Topic, audience, seed terms, sample time and a call budget.
Relevant tag choices with dated counts and separate top/recent samples; recent-post coverage excludes Reels and cannot establish growth.
An Agent and SandBase for live data. API/model usage is charged to your SandBase account; supplied material can run offline.
Download and unpack the complete Skill folder, keep its references, and use it with a local Agent that supports Skills.
Use instagram-hashtag-research with my supplied material and scope. Use live lookups only when relevant to the task and within my budget. Deliver: Relevant tag choices with dated counts and separate top/recent samples; recent-post coverage excludes Reels and cannot establish growth.