# ig-audit

Adopt this skill: https://proskills.md/skills/other/jakeschincariol-instagram-agent-skill-skills-ig-audit

Page: https://proskills.md/skills/other/jakeschincariol-instagram-agent-skill-skills-ig-audit
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: skills/ig-audit/SKILL.md
size: 4556
sha: 5bc2de35751896ee2a1a5a1c8b708130a46f1b51
upstream: https://github.com/jakeschincariol/instagram-agent-skill/blob/main/skills/ig-audit/SKILL.md

````text
---
name: ig-audit
description: >-
  Post-mortem on what the user has already posted - which reels actually
  worked, why, and what to stop making. Use when the user pastes their
  Instagram insights or past posts and asks "what's working", "why did this
  flop", "read my analytics", "audit my content", or wants to know what to do
  more of.
---

# ig-audit

The only honest source of what works for an account is that account. Every
rule in every Instagram guide, including the ones in this pack, is a prior.
The user's own last 30 posts are the evidence.

## Input

Ask for whichever the user has:

- Insights per post: views, reach, interactions, watch time, saves, shares,
  follows, and the non-follower share of reach. Screenshots are fine.
- Or the retention graph for their best and worst recent reels. This one
  screenshot is worth more than the rest combined.
- Or just the posts and their view counts, which is enough for a first pass.

Also read `~/.claude/instagram/log.md` if it exists, since it records which
hook formula each post used.

## What to actually measure

Raw views is the least useful number on the page, because it is mostly a
function of how many people already follow the account. Compute these instead
and show the working:

| metric | how | what it tells you |
| --- | --- | --- |
| **Outlier multiple** | views / the account's own median views | whether this was a real hit or a normal day |
| **Non-follower reach** | % of reach from people who do not follow | whether it travelled at all |
| **Hold at 3s** | viewers still there at 3s / viewers who started | whether the hook worked. This is the hook's grade. |
| **Average watch time** | straight from insights | whether the middle worked |
| **Sends per reach** | shares / reach | the strongest single signal you can earn. A send is a person putting their name on it. |
| **Follows per reach** | follows / reach | whether the profile converted the attention |

Rank by outlier multiple and sends per reach, not views. A reel with 4,000
views and 90 sends beat the one with 60,000 views and 11.

## Then find the pattern

With the top five and bottom five side by side, look for what separates them,
and be willing to conclude something the user will not like:

- **Hold at 3 seconds.** If the top and bottom differ here, it is the hook and
  nothing else, and everything downstream is a distraction.
- **Hook formula.** Which ids from `ig-reel/hooks.json` are in the top five?
- **Format.** Reel, carousel, single image.
- **Length.** Group into under 15s, 15 to 30s, 30 to 60s, over 60s.
- **Theme.**
- **Whether the user replied to comments in the first hour.**
- **Day and time.** Check this **last** and only if the others show nothing.
  It is almost never the cause and it is where people want it to be.

State the finding as a claim with the evidence attached, and say how confident
it is. With 30 posts you can see a pattern. With 6 you cannot, and saying so is
better than inventing one.

## The distinction that saves people months

**A reel that gets views and no follows is not a failed reel, it is a profile
problem.** A reel that gets no views is a hook problem. Separate the two before
recommending anything. If non-follower reach is high and follows per reach is
low, stop rewriting hooks and go to `/ig-profile`.

## Output

```
AUDIT  ·  31 posts  ·  Jun 12 - Sep 5  ·  median views 4,100

TOP 5 BY OUTLIER MULTIPLE
  18.2x  #3  Nobody Tells You   74,600 views  62% non-follower  hold@3s 71%  128 sends
   6.4x  #1  Cost Confession    26,300 views  48% non-follower  hold@3s 64%   71 sends
  ...

BOTTOM 5
   0.3x  #11 Numbered            1,200 views  9% non-follower   hold@3s 31%    2 sends
  ...

WHAT THE DATA SAYS
1. Hold at 3 seconds is the whole story. Top five average 66%, bottom five 33%.
   Everything else you are worried about is downstream of the first two seconds.
2. The posts where you were the one who looked bad: mean 8.1x vs 0.9x for
   everything else. n=5. Strongest signal here and it is not close.
3. Tool listicles get views and nothing else. High reach, no sends, no follows.
   Three of your bottom five.
4. Day of week shows nothing. Your Tuesday and Friday means are inside the
   noise. Stop optimising it.

STOP: listicles.
DO MORE: the ones with a cost you paid and a number attached.
```

Then hand the conclusions to `/ig-plan` so next week is built on the user's own
evidence rather than on defaults, and to `/ig-viral` so the swipe file gets
filtered to the formulas that work for this account specifically.
````

## File: README.md
upstream: https://github.com/jakeschincariol/instagram-agent-skill/blob/main/README.md

````text
# 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:

```bash
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

| command | what it does |
| --- | --- |
| `/ig-reel` | One idea into a Reel. Three hooks from [26 formulas](skills/ig-reel/hooks.json), scored, then the script, the on-screen text and a timed beat sheet. |
| `/ig-viral` | Goes and finds what is working in your niche, ranks it by multiple over each account's own median, names the formula, writes the swipe file. |
| `/ig-caption` | The caption, linted. Shows you the 125 characters the feed actually shows before the tap. |
| `/ig-carousel` | Swipe posts. The cover that earns the swipe, slide copy, and the 1080x1350 files. |
| `/ig-story` | The daily story sequence, which sticker does which job, and the DM funnel that starts with them moving first. |
| `/ig-profile` | Scores your profile against a [12-part rubric](skills/ig-profile/rubric.json) out of 100, then rewrites in fix-first order. |
| `/ig-plan` | The week. What to post, which format, when, and the 10 accounts to engage with. |
| `/ig-human` | The humanizer. Two scripts that actually run. See below. |
| `/ig-comment` | Comments on other people's posts. Nine types, picked by what the post actually is. Never "🔥🔥🔥". |
| `/ig-reply` | The thread under your own post. Sorts into keyword / lead / substance / question / support / noise, then writes in that order. |
| `/ig-dm` | The keyword delivery, the first message, the collab pitch, and the two follow-ups. Two. |
| `/ig-repurpose` | One video, podcast or newsletter into a week of reels and carousels that each stand alone. |
| `/ig-audit` | Post-mortem on what you already posted. Ranks by outlier multiple and sends per reach, not views. |

## The five tools that actually run

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

### Hooks

```bash
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

```bash
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

```bash
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`](skills/ig-human/slop.json) and it is mean
````
