PIL — Personal Instagram Library
Deep-search your Instagram saved posts, on your own machine
⚠️ Security warning from Skill Harbor: we detected a potentially dangerous pattern — this build installs via `curl | bash`, which runs remote code on your machine without review. Only install if you have read the code yourself. Use at your own risk. Curated by Skill Harbor — a free, open-source build (MIT) by @pjpoulose, listed here with credit to its creator. An installable Muse skill that deep-reads your Instagram saved posts and keeps them searchable on your own machine, also exposed as an MCP server.
Version:
Quick answer
PIL — Personal Instagram Library — is an installable Muse skill that deep-reads your Instagram saved posts and keeps them searchable on your own machine, also exposed as an MCP server. Skill Harbor's listing carries a security warning: this build installs via curl | bash, which runs remote code without review — only install if you have read the code yourself.
At a glance
| What it is | A personal library over your Instagram saved posts: the skill deep-reads them and keeps them searchable locally, on your own machine, and can also be reached as an MCP server. |
|---|---|
| Who it's for | People who save a lot of Instagram posts and later cannot find the one they are looking for — and who want that search to stay on their own machine. |
| What you give it | Your Instagram saved posts, kept on your own machine. And, before installing, your own read of the code: the listing's security warning says the build installs via curl | bash, which executes remote code without review. |
| What you get | Your saved posts deep-read and searchable locally, instead of a saved collection you can only scroll through in the app. |
| Works with | Muse, installed from this listing with the copy-paste install prompt, and also exposed as an MCP server. Use at your own risk, per the listing's warning: install only if you have read the code yourself. |
| Cost | Free |
| Time | A few minutes to install — after you have read the code, as the security warning requires. Searching your library afterwards is a question in conversation. |
Example — finding a post you saved
An example of a typical use, based only on the search the listing documents — not a reported result.
- You remember saving a post weeks ago but not its account or caption, and scrolling your saved collection has not surfaced it.
- You ask PIL to search your saved posts on your machine for what you remember about it.
- The matching saved post comes back from your local library, without the data leaving your machine.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit cc003ddStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: An Instagram account (you export your saved posts) and Python 3. No GitHub account needed unless listed here. Install "PIL — Personal Instagram Library" for me. A Personal Instagram Library — ingest your saved Instagram posts into a local database and query them; includes an MCP server. Repository: https://github.com/pjpoulose/PIL Pinned version: install the code at commit cc003dd644279881271ce1455aa586a19ab31ccf exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone the repo into a temporary folder (public HTTPS clone — no account needed) and look inside. 2. Safety check: briefly review any scripts for anything suspicious (network calls to unexpected hosts, shell commands, credential harvesting). Install the SKILL.md as a skill; wire up the MCP server (bin/mcp_server.py) too if you want it in your MCP client. If you see a red flag, stop and tell me before going further. 3. Install it as a skill: create a folder named pil in my agent's skills directory and copy SKILL.md plus its helper files there, keeping the layout the SKILL.md expects. 4. Verify without network calls: each SKILL.md has valid frontmatter (name + description); helper scripts pass a syntax check. 5. Report: what you installed, where, and anything still left for me to do myself (or confirm there's nothing left). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it (e.g. authenticated clone); otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- cc003dd · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.