Install
$ agentstack add skill-onebrain-ai-onebrain-bookmark ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Bookmark
Save a URL to your Bookmarks.md file in one step. Paste the link : the AI fills in the name and description, picks a category, and saves immediately.
Usage: /bookmark [url]
Step 1: Get the URL
If a URL was provided after the command, use it directly.
If not, ask: > What URL do you want to bookmark?
Step 2: Fetch the Page
Fetch the page content. Extract:
- Name: page title or product name (prefer `
or`) - Description: 1-line summary (~15 words) from meta description or page body
If fetch fails, ask: > I couldn't fetch that URL. What should I call it, how would you describe it in one line, and what category fits best?
Use the user's answers and continue normally.
Step 3: Pre-Save Checks
Duplicate check: grep [resources_folder]/Bookmarks.md for the URL ([resources_folder] from Step 2). If already present, tell the user and stop (unless they confirm to save again).
Existing summary note: grep [resources_folder]/**/*.md for url: [URL] in frontmatter. If found, record its title for use as a wikilink in the entry.
Step 4: Pick Category
Infer the best category and optional subcategory from the content : do not ask. Use the structure:
- Level 1 (
##): broad domain :AI Tools,Design,Dev Utilities,Productivity,Reading,Learning,Finance,Health,Reference - Level 2 (
###): optional refinement : only when it adds meaningful grouping
Create new categories freely when none fit.
Step 5: Save to Bookmarks.md
Build the entry:
- **[Name](URL)** : Description. → [[Summary Note Title]]
(Omit the wikilink if no summary note was found in Step 3.)
File path: [resources_folder]/Bookmarks.md ([resources_folder] from Step 2).
If the file does not exist, create it:
---
tags: [bookmarks, resources]
created: YYYY-MM-DD
updated: YYYY-MM-DD
---
# Bookmarks
Append under the correct ## / ### section (alphabetical order). Create missing sections in alphabetical position. Refresh updated in frontmatter.
Step 6: Confirm
Say in one line: 🔖 Saved to Bookmarks.md under ## {Category}. [If subcategory: / ### {Subcategory}]
Recategorize
If the user asks to move or recategorize a bookmark:
- Resolve file path using
[resources_folder] - Find the entry by name, or use the last bullet for "last bookmark"
- Remove from current section; append to target section (create
##/###as needed) - Refresh
updatedin frontmatter - Confirm in one line:
🔖 Moved {Name} from ## {Old} → ## {New}. [If subcategory: / ### {Sub}]
Known Gotchas
- Fetch failure with a bare URL. If the page cannot be fetched (timeout, 404, auth-gated), ask the user for name, description, and category rather than stopping. A bookmark with manual metadata is still useful.
- Category auto-inference. Infer category from page content, not just the domain. A GitHub repo for a productivity tool belongs under
ProductivityorDev Utilities, not under a genericGitHubcategory.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: onebrain-ai
- Source: onebrain-ai/onebrain
- License: Apache-2.0
- Homepage: https://onebrain.run
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.