#281 by GitHub stars
Jakeschincariol/instagram-agent-skill
Thirteen Claude skills that run an Instagram account: Reels off 26 scored hook formulas, a viral research skill, a caption linter, and a humanizer. Free, MIT.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/ig-audit/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-caption/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d03c56bb598b → d03c56bb598b
skills/ig-carousel/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-comment/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-dm/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-human/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d03c56bb598b → d03c56bb598b
skills/ig-plan/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-profile/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-reel/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d03c56bb598b → d03c56bb598b
skills/ig-reply/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-repurpose/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-story/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d03c56bb598b → d03c56bb598b
skills/ig-viral/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
d03c56bb598b → d03c56bb598b
Verified commit d03c56bb598be770c60b201f94237e5d1a4268a6
git clone --filter=blob:none --no-checkout https://github.com/Jakeschincariol/instagram-agent-skill.git .hotskills/jakeschincariol-instagram-agent-skill && git -C .hotskills/jakeschincariol-instagram-agent-skill checkout --detach d03c56bb598be770c60b201f94237e5d1a4268a6
# Copy each selected skill directory from .hotskills/jakeschincariol-instagram-agent-skill into .claude/skills/<skill-name>/Heat
7.4- Star growth, last 7 daysAhead of 99% of tracked repositories
- Star growth, last 24 hoursAhead of 99% of tracked repositories
- Rank movement, last 7 daysAhead of 94% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- ig-audit
skills/ig-audit - ig-caption
skills/ig-caption - ig-carousel
skills/ig-carousel - ig-comment
skills/ig-comment - ig-dm
skills/ig-dm - ig-human
skills/ig-human - ig-plan
skills/ig-plan - ig-profile
skills/ig-profile - ig-reel
skills/ig-reel - ig-reply
skills/ig-reply - ig-repurpose
skills/ig-repurpose - ig-story
skills/ig-story - ig-viral
skills/ig-viral
How it works
ig-audit
When your agent uses it
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.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
1,199 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- What to actually measure
- Then find the pattern
- The distinction that saves people months
- Output
Files
../../.claude-plugin/marketplace.jsonasset622 bytes../../.claude-plugin/plugin.jsonasset848 bytesSKILL.mdcore4,556 bytesSKILL.mdcore4,556 bytes
Read SKILL.md
# 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.View the complete source on GitHubig-caption
When your agent uses it
Write the Instagram caption - the line that survives the "... more" cut, the body, the single ask, the search terms and the three hashtags - and lint it before it goes out. Use when the user says "write the caption", "caption this", "what do I put in the description", has a reel or a carousel ready and needs the text, or asks about hashtags.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,163 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First, decide which job this caption has
- The shape
- Hashtags, honestly
- Search terms matter more than hashtags now
- Rules
- The loop
Scripts executed separately
caption.py
Files
SKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytescaption.pyruns9,694 bytes
Read SKILL.md
# ig-caption
One tool lives in this folder and it runs:
```bash
python3 caption.py caption.txt
python3 caption.py caption.txt --keywords "client proposals,agency pricing"
```
It prints the caption the way the feed prints it: the first 125 characters in a
box, everything else behind the tap. Read that box before you read anything
else you wrote.
## First, decide which job this caption hasView the complete source on GitHubig-carousel
When your agent uses it
Build an Instagram carousel - the cover that earns the swipe, slide-by-slide copy, and the 1080x1350 files to upload. Use when the user says "carousel", "slides", "swipe post", "turn this into a carousel", or has a list-shaped or step-shaped idea that would die as a single image.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,054 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use it instead of a Reel
- Structure
- Slide copy rules
- Building the files
- Output
Files
SKILL.mdcore4,090 bytesSKILL.mdcore4,090 bytes
Read SKILL.md
# ig-carousel
Carousels are the highest-dwell format on the grid, because a swipe is an
interaction and a scroll is not. They also get a second chance: Instagram can
show a carousel again starting from a later slide to someone who did not engage
the first time, so slide two has to stand on its own as well.
The format rewards one idea broken into steps. It punishes a caption cut into
pieces.
## When to use it instead of a Reel
Use a carousel when the idea has **sequence and needs to be re-read**: steps, a
framework with parts, a before and after, a list worth screenshotting. Use aView the complete source on GitHubig-comment
When your agent uses it
Write comments on other people's Instagram posts and reels that read as a person with an opinion, not a bot. Use when the user pastes a post or a reel and wants a comment, says "comment on this", "engage with this", "what do I say here", or wants a batch for their daily engagement round.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,077 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- The nine comment types
- Rules
- Output
- Batch mode
- Never
Files
SKILL.mdcore4,304 bytes
Read SKILL.md
# ig-comment
Commenting is the highest-leverage twenty minutes on Instagram and the easiest
to do badly. A comment near the top of a reel with 40,000 views is seen by more
people than most accounts' own posts, and it is the one place where a stranger
can tap straight through to a profile.
A generic comment is worse than none. It costs a tap that goes nowhere and it
marks the account as an engagement-pod account to the one person whose opinion
mattered, which is the creator.
## Input
The user pastes the post or reel text, or a screenshot, with the account name.View the complete source on GitHubig-dm
When your agent uses it
Write Instagram DMs that get replies - the keyword delivery, the first message to someone who engaged, the collab pitch, and the two follow-ups. Use when the user says "DM this person", "what do I send them", "outreach message", "how do I follow up", "pitch this brand", or is reaching out to someone specific.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,130 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The three kinds of DM, and only three are worth writing
- Before writing, get the specifics
- The keyword delivery
- The first message to someone warm
- The collab pitch
- Follow-ups
- Never
- Output
Files
SKILL.mdcore4,682 bytes
Read SKILL.md
# ig-dm
Instagram DMs are the only place on the platform where money actually changes
hands, and they are also where most accounts burn the goodwill their content
earned. The difference is entirely about who moved first.
## The three kinds of DM, and only three are worth writing
**1. The reply to a hand raised.** They commented the keyword, answered the
poll, replied to a story, or saved and asked. They moved first. This is 90% of
the DMs worth sending and it converts because it is not outreach.
**2. The warm approach.** Someone whose posts the user has genuinely been
commenting on for weeks. There is a shared thread of conversation already.View the complete source on GitHubig-human
When your agent uses it
Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out. Use whenever text needs to sound human, when the user says humanize, "does this sound like AI", "remove the em dashes", "de-slop this", "this sounds like ChatGPT", or before any caption, script, comment, reply or DM is shown to the user.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
1,241 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this matters more on Instagram than it looks
- What gets fixed automatically
- What does NOT get fixed automatically
- The five checks
- Say this honestly
- Order of operations
Scripts executed separately
detect.pyhumanize.py
Files
SKILL.mdcore5,242 bytesSKILL.mdcore5,242 bytesdetect.pyruns8,526 byteshumanize.pyruns10,909 bytesslop.jsonasset21,632 bytes
Read SKILL.md
# ig-human
Two tools live in this folder and they both actually run. Use them. Do not
eyeball this.
```bash
python3 humanize.py draft.txt --report # clean it, show what changed
python3 detect.py draft.txt # score it, five checks
python3 detect.py before.txt after.txt # prove the delta
```
Both read `slop.json`: 154 stock words and phrases with plain-English
replacements, 18 invisible character classes, 11 typographic substitutions and
16 structural tells. The last block of each list is Instagram-specific, theView the complete source on GitHubig-plan
When your agent uses it
Build the week on Instagram - what to post, which format, when, and who to engage with. Use when the user says "plan my week", "what should I post", "content calendar", "I have nothing to post about", or wants a posting schedule and an engagement list.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,026 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- What to post
- When to post
- The engagement round, which is not optional
- Output
Files
SKILL.mdcore3,916 bytes
Read SKILL.md
# ig-plan
The control room. Everything else in this pack executes; this decides what gets
executed. Run it once a week, on the same day.
## Input
If `~/.claude/instagram/voice.md`, `swipe.md` and `log.md` exist, read them.
The swipe file is the user's own evidence from `/ig-viral` about which formulas
are landing in their niche right now, and it outranks anything in this file.
The log stops the plan repeating a theme from the last fortnight.
If they do not exist, ask for four things and write them down:
View the complete source on GitHubig-profile
When your agent uses it
Score an Instagram profile out of 100 against a 12-part rubric and rewrite the parts that lose points - name field, bio, link, highlights, pinned three, grid. Use when the user says "optimize my profile", "fix my bio", "score my Instagram", "why don't people follow me", or pastes their profile and asks how it reads.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
853 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- Score it
- Then rewrite, in this order
- Output
Files
SKILL.mdcore3,407 bytesrubric.jsonasset4,152 bytes
Read SKILL.md
# ig-profile
Almost everybody optimises the wrong thing here. The profile is not a
storefront people browse. It is a **decision screen**, arrived at from one
reel, and it gets about three seconds to answer one question: is there more of
that here, and is it for me.
## Input
Ask the user to paste or screenshot: the name field, the handle, the bio, what
the link points to, the highlight names, what is pinned, and the first nine
grid covers. A screenshot of the top of the profile plus the first two grid
rows is enough for a first pass.
View the complete source on GitHubig-reel
When your agent uses it
Write an Instagram Reel from a raw idea - hook options off 26 formulas, the spoken script, the on-screen text, and a timed beat sheet - in the user's own voice and scored before they shoot it. Use whenever the user wants a Reel, a short-form video script, a hook, a voiceover, "make a reel about X", "what should I say in this video", or is about to record and does not have the first line yet.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
1,712 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before you write
- The shape
- The loop
- On-screen text is a separate script
- Rules that make the difference
- Example
Scripts executed separately
beats.pyhookscore.py
Files
SKILL.mdcore6,547 bytesSKILL.mdcore6,547 bytesbeats.pyruns8,223 byteshooks.jsonasset17,897 byteshookscore.pyruns12,814 bytes
Read SKILL.md
# ig-reel
Turns one raw idea into a Reel that somebody finishes.
Two tools live in this folder and they both actually run. Use them. Do not
eyeball the hook and do not guess at the length.
```bash
python3 hookscore.py hooks.txt # rank your hook options
python3 hookscore.py --hook "one line" # score a single one
python3 beats.py script.txt --target 30 # timed beat sheet before you shoot
```
## Before you writeView the complete source on GitHubig-reply
When your agent uses it
Handle the comments under the user's own reels and posts - draft replies to the ones worth answering, sorted by which ones are. Use when the user pastes their comments, says "reply to these", "handle my comments", "someone said X on my reel", or is dealing with a critic, a hater or a lead in the comments.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,008 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- Triage first
- The move most people miss
- How to reply
- Keyword comments
- Output
Files
SKILL.mdcore3,991 bytes
Read SKILL.md
# ig-reply
The comment thread under your own post is where reach is decided. Every reply
is another interaction on the post, replies arriving in the first hour do most
of the work, and on Instagram a reply can also be a Reel, which is the single
most underused move on the platform.
But the value is not equal across comments, so this skill sorts before it
writes.
## Input
The user pastes the comments, ideally with handles. Screenshots are fine. Do
not scrape the thread with a browser tool.View the complete source on GitHubig-repurpose
When your agent uses it
Turn one long asset - a YouTube video, podcast, livestream, newsletter, blog post or client call - into a week of reels and carousels. Use when the user says "repurpose this", "turn this into reels", "I have a video/podcast/ transcript", "cut this up", or pastes something long and wants it on Instagram.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
847 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- Extract, do not summarise
- Then pick the format per extract
- Then build the week
- Output
Files
SKILL.mdcore3,411 bytesSKILL.mdcore3,411 bytesSKILL.mdcore3,411 bytesSKILL.mdcore3,411 bytesSKILL.mdcore3,411 bytes
Read SKILL.md
# ig-repurpose
One good long asset contains four to six posts. Most people extract one and
throw the rest away.
## Input
A transcript, an article, a newsletter, a script, a call summary, a livestream.
If the user gives a URL and this session has a transcript tool, use it;
otherwise ask them to paste. Read the whole thing before extracting anything.
If the source is a video the user owns, ask for the file too. A Reel built on
their own footage beats one built on their own words read again.
View the complete source on GitHubig-story
When your agent uses it
Write the day's Instagram Stories - the frame-by-frame sequence, which stickers to use where, and the one that moves people into the DMs. Use when the user says "stories", "what do I post on my story", "story sequence", "poll idea", "I have nothing to story about", or wants to sell something without making a post about it.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,055 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The daily shape
- The stickers, and what each is actually for
- Rules
- The DM funnel, done honestly
- Output
Files
SKILL.mdcore4,369 bytes
Read SKILL.md
# ig-story
Stories are not a smaller feed. The feed is how strangers find you. Stories are
how the people who already follow you decide whether you are a person worth
buying from, and they are the only surface on Instagram where a tap turns into
a conversation in one move.
Nobody outside your followers sees these, so the job is completely different:
depth, not reach.
## The daily shape
Three to seven frames a day. Beyond about seven, the tap-forward rate climbs
and the last frames play to nobody, which is exactly where people put the ask.View the complete source on GitHubig-viral
When your agent uses it
Go and find the reels that are actually working right now in the user's niche, rank them by how far each beat its own account, name the hook formula each one used, and turn that into a swipe file they can shoot from. Use when the user says "find viral videos", "what's working right now", "what are people posting in my niche", "reverse engineer this account", "build me a swipe file", "why is this reel doing numbers", or asks what to make next and has no evidence to answer with.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
1,776 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The one idea that makes this worth doing
- Step 1: pick the accounts
- Step 2: go and look
- Step 3: rank it
- Step 4: say what it means, carefully
- Step 5: turn it into something to shoot
- Output
Scripts executed separately
swipe.py
Files
SKILL.mdcore7,004 bytesSKILL.mdcore7,004 bytesSKILL.mdcore7,004 bytesSKILL.mdcore7,004 bytesswipe.pyruns8,396 bytes
Read SKILL.md
# ig-viral
The research skill. Everything else in this pack writes; this one goes and
looks. Run it monthly, not daily. Formulas last a season.
One tool lives in this folder and it runs:
```bash
python3 swipe.py captured.tsv --out ~/.claude/instagram/swipe.md
```
## The one idea that makes this worth doing
**Raw views are not evidence.** An account with two million followers doingView the complete source on GitHubSkills included
- ig-audit
- ig-caption
- ig-carousel
- ig-comment
- ig-dm
- ig-human
- ig-plan
- ig-profile
- ig-reel
- ig-reply
- ig-repurpose
- ig-story
- ig-viral
Repository facts
- License
- MIT
- Created
- Sep 13, 2026
- Last pushed
- Sep 13, 2026
- Forks
- 1,052
- Open issues
- 35
- Project activity
- Active
Rank over the last 12 weeks
Now #281 · best #279 · up 632 in 30 days
- #291 on Nov 1
- #288 on Nov 2
- #286 on Nov 3
- #280 from Nov 4 to Nov 5
- #279 on Nov 6
- #281 since Nov 7
47 earlier periods
- #903 on Sep 13
- #941 on Sep 14
- #928 on Sep 15
- #941 on Sep 16
- #937 on Sep 17
- #922 on Sep 18
- #897 on Sep 19
- #917 on Sep 20
- #937 on Sep 21
- #954 on Sep 22
- #945 on Sep 23
- #912 on Sep 24
- #859 on Sep 25
- #882 on Sep 26
- #902 on Sep 27
- #947 on Sep 28
- #975 on Sep 29
- #940 on Sep 30
- #875 on Oct 1
- #891 on Oct 2
- #864 on Oct 3
- #906 on Oct 4
- #923 on Oct 5
- #904 on Oct 6
- #914 on Oct 7
- #913 on Oct 8
- #841 on Oct 9
- #761 on Oct 10
- #701 on Oct 11
- #681 on Oct 12
- #632 on Oct 13
- #582 on Oct 14
- #545 on Oct 15
- #528 on Oct 16
- #499 on Oct 17
- #488 on Oct 18
- #483 on Oct 19
- #460 on Oct 20
- #452 on Oct 21
- #431 on Oct 22
- #416 on Oct 23
- #391 on Oct 24
- #406 on Oct 25
- #333 on Oct 28
- #326 on Oct 29
- #310 on Oct 30
- #299 on Oct 31
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 13 notes
skills/ig-audit/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-caption/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-caption/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-carousel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-human/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-reel/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-repurpose/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-repurpose/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-repurpose/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-repurpose/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-viral/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-viral/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ig-viral/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 20 network referencesin 3 files: .claude-plugin/marketplace.json:1 .claude-plugin/plugin.json:5 ig-viral/SKILL.md:93
- No hidden or obfuscated text
- No instruction overrides
- 6 executable scriptsin 6 files: ig-caption/caption.py:1 ig-human/detect.py:1 ig-human/humanize.py:1 and 3 more
- No access to secrets
- No requests to vote in Hot
Show all 26 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 5
"owner": { "name": "Jake Schincariol", "url": "https://opusjake.ai" - Network accessline 6
"name": "Jake Schincariol", "url": "https://opusjake.ai" }, - Network accessline 7
"url": "https://opusjake.ai" - Network accessline 13
"source": "./", "category": "productivity", "homepage": "https://github.com/Jakeschincariol/instagram-agent-skill" - Network accessline 14
"category": "productivity", "homepage": "https://github.com/Jakeschincariol/instagram-agent-skill" } - Network accessline 15
"homepage": "https://github.com/Jakeschincariol/instagram-agent-skill"
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Jake Schincariol", "url": "https://opusjake.ai" - Network accessline 6
"name": "Jake Schincariol", "url": "https://opusjake.ai" }, - Network accessline 7
"url": "https://opusjake.ai" - Network accessline 8
}, "homepage": "https://github.com/Jakeschincariol/instagram-agent-skill", "repository": "https://github.com/Jakeschincariol/instagram-agent-skill", - Network accessline 9
"homepage": "https://github.com/Jakeschincariol/instagram-agent-skill", - Network accessline 10
"repository": "https://github.com/Jakeschincariol/instagram-agent-skill",
skills/ig-caption/caption.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ig-human/detect.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ig-human/humanize.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ig-reel/beats.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ig-reel/hookscore.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ig-viral/SKILL.md
- Network accessline 93
# view counts for a channel's shorts python3 -m yt_dlp --flat-playlist --playlist-end 40 -J \ "https://www.youtube.com/@HANDLE/shorts" > channel.json - Network accessline 94
python3 -m yt_dlp --flat-playlist --playlist-end 40 -J "https://www.youtube.com/@HANDLE/shorts" > channel.json - Network accessline 95
"https://www.youtube.com/@HANDLE/shorts" > channel.json - Network accessline 97
# the spoken first line of one short, from its auto-captions python3 -m yt_dlp --skip-download --write-auto-subs --sub-langs "en.*" \ --sub-format json3 -o hook "https://www.youtube.com/watch?v=VIDEO_ID" - Network accessline 98
python3 -m yt_dlp --skip-download --write-auto-subs --sub-langs "en.*" --sub-format json3 -o hook "https://www.youtube.com/watch?v=VIDEO_ID" - Network accessline 99
--sub-format json3 -o hook "https://www.youtube.com/watch?v=VIDEO_ID"
skills/ig-viral/swipe.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 26 facts
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:1High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:2High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:5High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:6High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:7High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:13High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:14High confidence
- Network access in code of the plugin configuration.claude-plugin/marketplace.json:15High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:5High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:6High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:7High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:8High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:9High confidence
- Network access in code of the plugin configuration.claude-plugin/plugin.json:10High confidence
- Executable script in code of a file that runsig-caption/caption.py:1High confidence
- Executable script in code of a file that runsig-human/detect.py:1High confidence
- Executable script in code of a file that runsig-human/humanize.py:1High confidence
- Executable script in code of a file that runsig-reel/beats.py:1High confidence
- Executable script in code of a file that runsig-reel/hookscore.py:1High confidence
- Network access in code of the SKILL.mdig-viral/SKILL.md:93High confidence
- Network access in code of the SKILL.mdig-viral/SKILL.md:94High confidence
- Network access in code of the SKILL.mdig-viral/SKILL.md:95High confidence
- Network access in code of the SKILL.mdig-viral/SKILL.md:97High confidence
- Network access in code of the SKILL.mdig-viral/SKILL.md:98High confidence
- Network access in code of the SKILL.mdig-viral/SKILL.md:99High confidence
- Executable script in code of a file that runsig-viral/swipe.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/ig-audit/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/ig-audit/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/ig-audit/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/ig-audit/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/ig-audit/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/jakeschincariol-instagram-agent-skill/)