Run an Instagram account with thirteen open-source Claude skills
A developer published a free, MIT-licensed set of thirteen Claude skills that help plan, write, lint and audit Instagram content, including Reels, captions, carousels and DMs. The skills only write, and the user posts everything manually.
The problem
Running an Instagram account means producing Reels, captions, comments and replies in a consistent voice, and AI-written drafts often contain obvious stock phrasing and invisible characters. Automating posting or engagement through browser tools or third-party apps breaks Instagram's Terms and can get accounts action-blocked.
How they did it
- Paste the repository URL into Claude and ask it to install the skill, or clone the repo and copy the skill folders into ~/.claude/skills/.
- Alternatively install it as a plugin with the /plugin marketplace commands, or copy the folders into a project's .claude/skills/.
- Without Claude Code, paste a single SKILL.md at the top of a chat, which loses the five local Python tools.
- Fill in templates/voice.md, copy it to ~/.claude/instagram/voice.md, and have every skill read it.
- Run commands such as /ig-reel, /ig-caption or /ig-human, then review the copy-ready output and post it yourself.
From the official docs
git clone https://github.com/Jakeschincariol/instagram-agent-skill.git
cp -r instagram-agent-skill/skills/ig-* ~/.claude/skills/Results
- The author tested the hook scorer on 74 real short-form hooks (YouTube Shorts, not Reels): AUC 0.83 against ten deliberately bad hooks, but only AUC 0.56 at separating a creator's hits from misses.
- Rewriting the formula classifier's regexes against real transcribed speech raised its coverage from 8% to 49% of hooks.
- On a deliberately bad caption, the humanizer raised the local human score from 32.5 to 79.7 (+47.2), as reported by the repository author.
As reported by the source (GitHub repository README (open source)); AgentGid did not measure these figures.
Suits a solo creator or small social team already on Claude Code who can maintain a voice.md file and post by hand. Claude Code needs a paid plan ($20/mo), and the hook scorer was tested on YouTube Shorts, with the +47.2 humanizer gain reported by the author. If you'd rather not pay, Pi (Free (OSS)) is a terminal alternative, though these skills are built for Claude.
The agent used here
Similar use cases
Run a YouTube channel with eleven Claude skills for scripts, edits and retention
An open-source MIT pack of eleven Claude skills helps a YouTube creator draft scripts, package titles and thumbnails, cut edits, read retention data and plan a week of content. It…
The pack bundles eleven skills and six dependency-free Python tools, including a hook scorer, title and thumbnail linter, dead-air detector, chapter …
Make continuous-take product launch films with the onetake agent skill
The onetake repository is a Claude Agent Skill that lets a coding agent produce product launch films, teasers and feature demos as one continuous camera take. An automated oracle …
The README lists ten example films across concept ads, launch films, app promos and feature demos, each with a finished film and a breakdown document…
Run a LinkedIn account with eleven free Claude skills and a local humanizer
An open-source MIT repository by Jake Schincariol packages eleven Claude skills for drafting LinkedIn posts, comments, replies, DMs and weekly plans. A bundled local humanizer cle…
In the author's example run on a deliberately poor draft, the human score rose from 24.8 (FLAGGED) to 69.7 (REVIEW) after humanize.py, a change of +4…
Guides
Claude Code Deploys: 6 Open-Source Repos for a Containment System, Checked
A viral post says GitHub Actions, Argo CD, Argo Rollouts, Prometheus, Sentry and OpenTelemetry turn Claude Code deploys into a containment system. We checked each: role, license, what needs Kubernetes, and what Claude Code's own permissions add.
How to Cut Token Usage in Claude Code and Cursor (2026)
Practical ways to spend fewer tokens with Claude Code and Cursor: measure first, keep context small, match the model to the task, filter what the agent reads, and the open-source tools that help.
Sonnet Builds, Opus Reviews, Haiku Reads: Does the Claude Code Advisor Save Money?
A viral post says running Sonnet, Haiku and Opus together in Claude Code gives better code for fewer tokens. We checked it against Anthropic's docs and prices: when the advisor pays off, when it costs more, and why a ready project kit matters more than the model mix.
JEV for Claude Code: A Second Opinion on Every Command, Checked
A viral post says jev-axi screens every command your Claude Code agent runs for a fraction of a cent. We read the repo, TypeSafe's docs and privacy policy: what runs locally, what is sent, how it fails, and how it compares with auto mode.