agentleFS
fliqrlabsfliqrlabs/instagram-creator-skills/skills/profile-glowup/SKILL.md

profile-glowup

Skill5 starsChanged 18 days agoMITView on GitHub

Score an Instagram profile out of 100 and rewrite it to convert visitors into followers and leads: name-field keywords, bio, link, highlights, pinned posts, the first 9 grid tiles, and a keyword DM path in the bio. Reads the live profile through the Fliqr AI connector or from a screenshot. Use when the creator says "fix my bio", "audit my profile", "rewrite my bio", "people visit but don't follow", "optimize my Instagram profile", "what should I pin", or "highlights ideas".

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

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

    line 22
  2. Distinctive:

    Never change the profile directly.

    line 51

≈ “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

profile-glowup

The profile is the checkout page of Instagram. A reel earns the visit. The profile decides in about 3 seconds whether that visit becomes a follow, a DM or nothing.

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

Connected: get_profile (bio, website, counts), then list_media with limit: 12 for the grid and pinned posts. Offline: ask for a screenshot of the profile.

The 100-point score

PartPointsFull marks when
Name field10includes the searchable keyword ("Aditi · Reels Coach"). The name field is searchable, the bio mostly isn't.
Handle5easy to say and spell. No random numbers or underscores.
Photo5a face, close-up, readable at 40px. Or a clean logo for a brand.
Bio line 1: who it's for + the result20"I help {who} get {result}". Specific.
Bio line 2: proof10a real number or credential (a real one, never invented)
Bio line 3: the CTA15a DM keyword path ("DM 'START' for my free guide") or one clear link action
Link10one destination that matches the CTA. No link tree with 14 options unless it's curated.
Highlights103-5, in order: Start here / Results / Offer / FAQ / Free stuff. Covers consistent.
Pinned posts103 pins doing 3 jobs: best reach post (proof), best value post (save), offer or origin post (convert)
First 9 grid5a visible pillar mix, readable covers, no dead tiles

Explain every lost point in one line. Then rewrite in fix-first order: biggest point gain for the least effort.

The DM keyword in the bio

"DM me 'GUIDE'" in the bio turns profile visits into conversations with no link click needed. In connected mode, check list_automations to see whether a DM keyword flow exists for it. If it doesn't, say so. Bio keywords need a DM automation configured in the creator's dashboard (the Fliqr AI connector manages comment, story and live automations).

Output

Score, then 3 bio options (each under 150 characters, line breaks shown), the name-field rewrite, a highlight plan with cover-text ideas, the 3 pins with reasons, and grid notes. Lint each bio with python3 ../polish/scripts/polish.py bio.txt --mode bio (python on Windows). It checks the 150-character limit, the CTA, proof and slop.

Never change the profile directly. The creator pastes the changes in themselves.

<!-- 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.