agentleFS
windsor-aiwindsor-ai/claude-windsor-ai-plugin/skills/instagram-public/SKILL.md

instagram-public

Skill1 starsChanged 51 days agoMITView on GitHub

Look up public Instagram profile and post data for any Business or Creator account through Windsor.ai — follower, following, and media counts, bio, website, and recent post performance (likes, comments) for competitor or benchmark accounts. Use for public or competitor Instagram analysis. Do not use for the user's own connected Instagram account's private insights or publishing (use /instagram for that), Instagram Ads, or other platforms.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read-only connector; there are no live write actions to run.

    line 26
  2. Very specific:

    Call get_connectors to see which target accounts are already configured (each represents a public username being monitored, with an id and …

    line 31
  3. Very specific:

    Call get_fields for instagram_public to get valid field ids.

    line 42
  4. Very specific:

    Call get_data with fields, the target account(s), and a date range for post-level fields (date_from/date_to or a date_preset like last_30d.

    line 48
  5. Distinctive:

    Benchmark against another account: run the same read for each target username and compare.

    line 58
  6. Very specific:

    If a metric the user wants isn't in get_fields, say so rather than substituting a different one.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Instagram Public (business discovery) via Windsor.ai

Windsor.ai pulls public Instagram profile and media data through Meta's Business Discovery API. The connector id is instagram_public. Pass instagram_public as the connector on every tool call; the Windsor.ai server serves all connectors, so it is never implied.

This is not the user's own account data. It looks up any public Instagram Business or Creator account — a competitor, a partner, an influencer — by username, and returns what is publicly visible: profile stats and recent post performance. It cannot see private accounts, Stories, or anything not publicly visible, and it does not publish or change anything — there are no write actions. For the user's own connected Instagram account's private insights, publishing, or comment moderation, use /instagram instead; for Instagram Ads, use /facebook-ads.

Golden rules:

  • Never guess field, account, or option names — get them from get_fields, get_connectors, and get_options. Call those first.
  • Read-only connector; there are no live write actions to run.
  • Report what the user asked for, concisely.

1. Ground yourself first

Call get_connectors to see which target accounts are already configured (each represents a public username being monitored, with an id and usually a name). If the user wants to look up a username that isn't configured yet, help them add it: get_connector_authorization_url (or get_connector_connect_info for the setup steps) and give them the setup link at https://onboard.windsor.ai/app/instagram_public — don't describe manual dashboard navigation. If several target accounts are configured and the request is ambiguous, ask which one.

2. Reading public profile and post data

  1. Call get_fields for instagram_public to get valid field ids. These span profile-level fields (follower count, follows count, media count, biography, website, username, display name) and per-post fields (type, caption, permalink, like count, comment count, timestamp), plus per-post-average fields (likes per post, comments per post). Use the exact ids returned, not these examples.
  2. Call get_data with fields, the target account(s), and a date range for post-level fields (date_from/date_to or a date_preset like last_30d; profile-level fields reflect the account's current state and ignore the date range).

Common requests → recipe:

  • Profile snapshot: follower/follows/media counts, bio, website.
  • Recent post performance: per-post like and comment counts over a date range, ranked or averaged.
  • Benchmark against another account: run the same read for each target username and compare.

If a metric the user wants isn't in get_fields, say so rather than substituting a different one. There is no story, reach, or impressions data — Business Discovery only exposes what's publicly visible.

3. Reference real data, don't fabricate

On an error, the target account is most likely private, not a Business or Creator account, or not yet added — call the relevant discovery tool and retry, or report the specific error. Never invent follower counts, engagement numbers, or post content.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.