agentleFS
fliqrlabsfliqrlabs/instagram-creator-skills/skills/instagram-seo/SKILL.md

instagram-seo

Skill5 starsChanged 19 days agoMITView on GitHub

Make a creator findable in Instagram search and Explore: keyword research from what people type, the name field and username, keyword-rich bio, captions, on-screen text, spoken words, alt text, sized hashtags (5 max) and location tags, mapped into a keyword plan per content pillar. Use when the creator says "Instagram SEO", "show up in search", "keywords for Instagram", "nobody finds my account", "hashtag research", "what should my name field say", "searchable captions", or "alt text". Works offline, or with the Fliqr AI connector for live Instagram data.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read: the creator profile, ../instagram-playbook/algorithm.md, ../instagram-playbook/connectors.md.

    line 22
  2. Very specific:

    The audience's own words: run comment-mining (connected) or read the comments.

    line 28
  3. Distinctive:

    Size each keyword: look at the top posts under it.

    line 29

≈ “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-seo

Instagram search now leans on words, not just hashtags: the name field, bio, caption and on-screen text. Creators report that what's said out loud (through auto-captions) helps too, though Instagram hasn't confirmed it. A post that uses the words people search for can keep getting found for months.

Read: the creator profile, ../instagram-playbook/algorithm.md, ../instagram-playbook/connectors.md.

1. Keyword research (no tool needed)

  1. Seed list: 10-15 phrases the audience would type. "cake pricing", "home bakery business", "eggless cake Austin". Use the audience's own words and language: people search the way they talk.
  2. Instagram search autocomplete: the creator types each seed into Instagram search and screenshots the suggestions. Those are real searches. Ask for the screenshots, and never invent search volumes.
  3. The audience's own words: run comment-mining (connected) or read the comments. The phrases people use to ask are the phrases they search with.
  4. Size each keyword: look at the top posts under it. Huge accounts only → too broad for now. Accounts the creator's size or smaller → winnable.

Output: a keyword map with 1 primary keyword per pillar and 3-5 secondary ones.

2. Where keywords go

PlaceRule
Name fieldthe most important searchable spot. "Meera · Home Baking Coach" beats "Meera ✨🎂". Use the primary keyword.
Usernameinclude it only if it's still easy to say and spell. Don't rename an established handle for SEO.
Biothe primary keyword plus the location, if local, written for humans
Caption first linethe keyword in the hook, naturally. "Cake pricing is why most home bakers stay broke."
On-screen textthe keyword on the hook card
Spokensay the keyword naturally in the first 5 seconds (reported to help through auto-captions, and it helps viewers anyway)
Alt textphotos and carousels only: Advanced settings → Accessibility → Write alt text. Describe what's in the image for people using screen readers first. Use the keyword only if it truly describes the image. Never stuff it in.
Hashtags5 max, sized as in caption: 1-2 niche, 2 mid, 1 broad. Make one of them the primary keyword. A local business can swap the broad tag for a location tag.
Location tagalways, for local businesses

3. Audit (connected)

get_profile → check the name field and bio. list_media with limit: 25 → for each post, does the caption's first line contain a pillar keyword? Report the % of posts that are findable for each pillar, and the 5 best posts to re-caption. Editing an old caption to add keywords is allowed and costs nothing.

Output

The keyword map, the name field and bio rewrite (lint with python3 ../polish/scripts/polish.py bio.txt --mode bio, python on Windows), a caption keyword checklist for future posts, and the audit fixes. Never stuff keywords in. Written for humans first, it still has to read naturally.

<!-- brand:footer -->

Part of Instagram Creator Skills by Fliqr AI. Live Instagram data and comment-to-DM automations come from the Fliqr AI connector (fliqr.ai).

<!-- /brand:footer -->

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.