ig-audit

The Instagram agent skill

Thirteen Claude skills that run an Instagram account. Free, MIT, no signup, no API key, nothing to connect.

One of them writes your Reels off 26 hook formulas and scores the hook before you waste a take on it. One goes and finds the reels that are actually working in your niche and ranks them by how far each beat its own account. One writes the caption and shows you exactly what the feed shows before the "... more". One scores your profile out of 100 and rewrites what lost points. One plans the week.

And one is the humanizer, which is the reason the rest are usable. It strips the em dashes, the slop vocabulary and the invisible watermark characters out of a draft, then scores what is left against a five-check panel before you ever see it.

Nothing gets posted until you say yes. These skills write. You post.

Install

Paste this into Claude:

https://github.com/Jakeschincariol/instagram-agent-skill

Install this skill, then confirm /ig-reel works.

Or do it yourself, in Claude Code:

git clone https://github.com/Jakeschincariol/instagram-agent-skill.git
cp -r instagram-agent-skill/skills/ig-* ~/.claude/skills/

Or as a plugin:

/plugin marketplace add Jakeschincariol/instagram-agent-skill
/plugin install instagram-agent

Project-local instead of global: copy the same folders into your repo's .claude/skills/. No Claude Code at all? Paste any single SKILL.md at the top of a chat and it runs as a mode. You lose the five Python tools, which is most of the point of /ig-reel and /ig-human, but the rest works.

Then spend ten minutes on templates/voice.md. Copy it to ~/.claude/instagram/voice.md and fill it in, or send Claude three of your own reels and say "write my voice.md from these". Every skill reads that file. It matters more here than on other platforms, because you have to say the words out loud.

The thirteen

The five tools that actually run

No dependencies, no network, nothing uploaded. They run on your machine, on your text.

Hooks

python3 hookscore.py hooks.txt              # rank your options
python3 beats.py script.txt --target 30     # time it before you shoot it

HOOK RANKING
==============================================================================
->  85.6 STRONG  Nobody tells you that your first 30 reels are supposed to f...
        weakest: SPECIFICITY (75)
    81.4 STRONG  I lost $18,000 because of one missing contract.
        weakest: ADDRESS (70)
    54.4 OK      Stop scrolling if you want to grow on Instagram in 2026 🔥
        weakest: STAKES (70)
        dealbreaker: Opens with "stop scrolling". Asking for attention proves
                     you have not earned it.
     9.6 WEAK    Hey guys, today I wanted to talk about content strategy
        weakest: FRONTLOAD (0)
        dealbreaker: Greeting. Nobody came to the feed to be greeted.

beats.py estimates how long each line takes to say, stacks them into timecodes, and flags the four things that kill a Reel in the edit: a hook that runs past three seconds, a beat long enough for the viewer to leave, a run of lines with nothing concrete in them, and no loop back to the first line.

BEAT SHEET  ·  73 words  ·  ~26.6s at 165 wpm  ·  target 30.0s
========================================================================
  0:00.0   2.9s  HOOK    I lost $18,000 because of one missing contract.
  0:02.9  14.6s  MID     Here is the exact clause I now put in every single...
                         ^ 14.6s on one beat
  0:17.4   2.9s          Section 4. Payment on delivery, not on approval.
  0:20.4   2.9s          Approval is a feeling. Delivery is a date.
  0:23.3   3.3s  CTA     That one word change is worth $18,000 to me.
------------------------------------------------------------------------
  - Beat 2 runs past 4s. Either split the line or change what is on screen
    inside it. A static frame is where people leave.
  - Loops: the last beat repeats "$18,000" from the hook. Second watches are
    free reach.
  - 3.5s under target. Either add 9 words or shoot it short. Short is usually
    right.

The caption

python3 caption.py caption.txt --keywords "client contracts,freelance pricing"

Instagram gives a caption about 125 characters in the feed and hides the rest behind a tap. Almost every caption that fails, fails there. So the first thing this prints is that window, as a box, the way a scrolling stranger reads it:

  WHAT THE FEED SHOWS
  +------------------------------------------------------+
  | I lost $18,000 because of one missing clause in a    |
  | contract, and the worst part is that I had read the  |
  | thing twice before I si                              |
  +-------------------------------------------- ... more +

  PASS  LENGTH            389 / 2200 characters
  WARN  FIRST LINE        133 characters, so it gets cut at 125 mid-thought
  PASS  HOOK IS CONCRETE  2 numbers or names in the visible window
  PASS  HASHTAGS          3 tags: #freelance #contracts #agencyowner
  PASS  ONE ASK           one call to action: comment a keyword
  WARN  SEARCH TERMS      1/2 present. Missing: client contracts

It enforces the current hashtag cap, which is five per post, not thirty. Instagram cut it on 18 December 2025.

The humanizer

python3 humanize.py draft.txt --report      # clean it, show every change
python3 detect.py draft.txt                  # score it, five checks
python3 detect.py before.txt after.txt       # prove the delta

What comes out automatically:

• Invisible characters. Zero-width spaces and joiners, word joiners, soft hyphens, byte-order marks, Unicode tag characters, invisible separators, non-breaking and narrow spaces. Your keyboard does not make these. They survive copy-paste and they are invisible in every editor you own.
• Typography. Em dash to comma, en dash to hyphen, curly quotes to straight, ellipsis to three dots, and the orphaned punctuation that leaves.
• The lexicon. 154 stock words and phrases with plain-English replacements. The last block of it is Instagram-specific: "stop scrolling", "in today's video", "follow for more", "tag someone who needs this", "the algorithm loves", "run don't walk". It lives in slop.json and it is mean